{"object":"list","data":[{"id":"gpt-5.5","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":12,"premium":true,"context_window":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","pricing":{"prompt":"0.000005","completion":"0.00003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.4","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":4.5,"premium":false,"context_window":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","pricing":{"prompt":"0.0000025","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.4-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.6,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","pricing":{"prompt":"0.00000075","completion":"0.0000045","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.4-nano","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.3,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","pricing":{"prompt":"0.0000002","completion":"0.00000125","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.3-chat-latest","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":3.5,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...","pricing":{"prompt":"0.00000175","completion":"0.000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.3-codex","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":3.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","pricing":{"prompt":"0.00000175","completion":"0.000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.2","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":3.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","pricing":{"prompt":"0.00000175","completion":"0.000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.2-chat-latest","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":3.5,"premium":false,"context_window":128000,"max_output_tokens":32000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","pricing":{"prompt":"0.00000175","completion":"0.000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.2-codex","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":3.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","pricing":{"prompt":"0.00000175","completion":"0.000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.1","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.1-chat-latest","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.1-codex-max","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.1-codex","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.1-codex-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.8,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","pricing":{"prompt":"0.00000025","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.8,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","pricing":{"prompt":"0.00000025","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5-nano","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.3,"premium":false,"context_window":400000,"max_output_tokens":null,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","pricing":{"prompt":"0.00000005","completion":"0.0000004","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5-chat-latest","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5-search-api","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5-codex","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":400000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","pricing":{"prompt":"0.00000125","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4o","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4o-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4o-search-preview","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"GPT","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4o-mini-search-preview","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.3,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"GPT","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4.1","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.8,"premium":false,"context_window":1047576,"max_output_tokens":null,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","pricing":{"prompt":"0.000002","completion":"0.000008","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4.1-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.3,"premium":false,"context_window":1047576,"max_output_tokens":32768,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","pricing":{"prompt":"0.0000004","completion":"0.0000016","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4.1-nano","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":1047576,"max_output_tokens":32768,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","pricing":{"prompt":"0.0000001","completion":"0.0000004","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-3.5-turbo","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.4,"premium":false,"context_window":16385,"max_output_tokens":4096,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"GPT","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","pricing":{"prompt":"0.0000005","completion":"0.0000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"o4-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.6,"premium":false,"context_window":200000,"max_output_tokens":100000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","pricing":{"prompt":"0.0000011","completion":"0.0000044","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"o3-mini","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1.6,"premium":false,"context_window":200000,"max_output_tokens":100000,"input_modalities":["text","file"],"output_modalities":["text"],"modality":"text+file->text","tokenizer":"GPT","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","pricing":{"prompt":"0.0000011","completion":"0.0000044","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"o3","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":200000,"max_output_tokens":100000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","pricing":{"prompt":"0.000002","completion":"0.000008","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-laborratse","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gpt-laborratse-de","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"claude-opus-4.7","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":20,"premium":true,"required_plan":"Max","context_window":1000000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","pricing":{"prompt":"0.000005","completion":"0.000025","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"capybara","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":100,"premium":true,"required_plan":"Admin","context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"claude-opus-4.6","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":20,"premium":true,"required_plan":"Max","context_window":1000000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","pricing":{"prompt":"0.00003","completion":"0.00015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"claude-opus-4.5","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":20,"premium":true,"required_plan":"Max","context_window":200000,"max_output_tokens":64000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","pricing":{"prompt":"0.000005","completion":"0.000025","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"claude-sonnet-4.6","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":12,"premium":true,"required_plan":"Plus","context_window":1000000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"claude-sonnet-4.5","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":12,"premium":true,"required_plan":"Plus","context_window":1000000,"max_output_tokens":64000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"claude-sonnet-4","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":12,"premium":true,"required_plan":"Plus","context_window":1000000,"max_output_tokens":64000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"claude-haiku-4.5","object":"model","created":1749028256,"owned_by":"anthropic","endpoint":"/v1/chat/completions","token_multiplier":5,"premium":true,"context_window":200000,"max_output_tokens":64000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Claude","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","pricing":{"prompt":"0.000001","completion":"0.000005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.1-pro-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":8,"premium":true,"context_window":1048576,"max_output_tokens":65536,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.1-flash-lite-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":1048576,"max_output_tokens":65536,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.1-flash-lite-preview-thinking","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":1048576,"max_output_tokens":65536,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"modality":"text+image+video+audio->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 3.1 Flash Lite Preview is the fastest and cheapest model in the Gemini 3.1 family. It provides multimodal understanding and intelligence similar to or better than Gemini 2.5 Flash at a low price that makes it perfect for high volume workloads. Supports 1M tokens of context\n\nThis bot supports optional parameters for additional customization.","pricing":{"prompt":"0.0000002525","completion":"0.0000015152","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"gemini-3.1-flash-image-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":38,"premium":false,"context_window":65536,"max_output_tokens":65536,"input_modalities":["text","image"],"output_modalities":["text","image"],"modality":"text+image->text+image","tokenizer":"Gemini","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":true,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","pricing":{"prompt":"0.0000005","completion":"0.000003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3-pro-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":8,"premium":true,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gemini-3-pro-image-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":52,"premium":true,"required_plan":"Admin","context_window":65536,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text","image"],"modality":"text+image->text+image","tokenizer":"Gemini","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":true,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3-flash-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":1048576,"max_output_tokens":65536,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3-flash-preview-thinking","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":1048576,"max_output_tokens":65536,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"modality":"text+image+video+audio->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Building on the reasoning capabilities of Gemini 3 Pro, Gemini 3 Flash is a powerful but affordable and performant model. It has exceptional world knowledge, multimodal understanding and reasoning capabilities at a fraction of the cost of equivalent models (as of December 2025).\n\nThis bot supports optional parameters for additional customization.","pricing":{"prompt":"0.000000404","completion":"0.0000024242","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"gemini-2.5-pro","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":6,"premium":false,"context_window":1048576,"max_output_tokens":65536,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-2.5-flash","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":1048576,"max_output_tokens":65535,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-2.5-flash-thinking","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":1048576,"max_output_tokens":65535,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-2.5-flash-lite","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":1048576,"max_output_tokens":65535,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-2.5-flash-image","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":38,"premium":false,"context_window":32768,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text","image"],"modality":"text+image->text+image","tokenizer":"Gemini","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":true,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-2.0-flash","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":990000,"max_output_tokens":8192,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"modality":"text+image+video+audio->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":true,"description":"Gemini 2.0 Flash is Google's most popular model yet with enhanced performance and blazingly fast response times; supports web search grounding so can intelligently answer questions related to recent events. Notably, 2.0 Flash even outperforms 1.5 Pro on key benchmarks, at twice the speed. Supports 1 million tokens of input context.","pricing":{"prompt":"0.0000001061","completion":"0.0000004242","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"gemma-4-31b-it","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":262144,"max_output_tokens":16384,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text","tokenizer":"Gemma","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","pricing":{"prompt":"0.00000013","completion":"0.00000038","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemma-4-26b-a4b-it","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":262144,"max_output_tokens":null,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text","tokenizer":"Gemma","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","pricing":{"prompt":"0.00000006","completion":"0.00000033","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemma-3-27b-it","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":16384,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","pricing":{"prompt":"0.00000008","completion":"0.00000016","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemma-3n-e4b-it","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":32768,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...","pricing":{"prompt":"0.00000006","completion":"0.00000012","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"llama-4-maverick","object":"model","created":1749028256,"owned_by":"meta","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":1048576,"max_output_tokens":16384,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Llama4","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"llama-4-scout","object":"model","created":1749028256,"owned_by":"meta","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":327680,"max_output_tokens":16384,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Llama4","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","pricing":{"prompt":"0.00000008","completion":"0.0000003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"llama-3.1-8b-instruct","object":"model","created":1749028256,"owned_by":"meta","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":16384,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Llama3","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","pricing":{"prompt":"0.00000002","completion":"0.00000005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"llama-3.3-70b-instruct","object":"model","created":1749028256,"owned_by":"meta","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Llama3","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","pricing":{"prompt":"0.0000001","completion":"0.00000032","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-v4-flash","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":1048576,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","pricing":{"prompt":"0.00000014","completion":"0.00000028","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-v4-pro","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":1048576,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","pricing":{"prompt":"0.000000435","completion":"0.00000087","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-v4","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":1048576,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","pricing":{"prompt":"0.00000014","completion":"0.00000028","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-chat","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":163840,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","pricing":{"prompt":"0.00000032","completion":"0.00000089","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-reasoner","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"deepseek-v3.2","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","pricing":{"prompt":"0.000000252","completion":"0.000000378","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-v3.1-terminus","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":163840,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","pricing":{"prompt":"0.00000021","completion":"0.00000079","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"deepseek-v3.1","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":160000,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.0091"},"metadata_source":"poe","metadata_status":"known"},{"id":"deepseek-v3-0324","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":64000,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Deepseek-v3 – the new top open-source LLM. Achieves state-of-the-art performance in tasks such as coding, mathematics, and reasoning. All data you submit to this bot is governed by the Poe privacy policy and is only sent to DeepInfra, a US-based company.\n\nSupports 64k tokens of input context and 8k tokens of output context. Quantization: FP8 (official).","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.0044"},"metadata_source":"poe","metadata_status":"known"},{"id":"deepseek-v3","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":64000,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Deepseek-v3 – the new top open-source LLM. Achieves state-of-the-art performance in tasks such as coding, mathematics, and reasoning. All data you submit to this bot is governed by the Poe privacy policy and is only sent to DeepInfra, a US-based company.\n\nSupports 64k tokens of input context and 8k tokens of output context. Quantization: FP8 (official).","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.0044"},"metadata_source":"poe","metadata_status":"known"},{"id":"deepseek-r1-0528","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":163840,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","pricing":{"prompt":"0.0000005","completion":"0.00000215","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4.20-reasoning","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":4.5,"premium":false,"context_window":2000000,"max_output_tokens":null,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"Grok","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently...","pricing":{"prompt":"0.000002","completion":"0.000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4.20-non-reasoning","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":4.5,"premium":false,"context_window":2000000,"max_output_tokens":null,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"Grok","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently...","pricing":{"prompt":"0.000002","completion":"0.000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4.1-fast-reasoning","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":2000000,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok-4.1-Fast-Reasoning is a high-performance version of xAI’s Grok 4.1 Fast, the company’s best agentic tool‑calling model. It works great in real-world use cases like customer support, deep research, and advanced analytical reasoning. Equipped with 2M‑token context window, this model processes vast information seamlessly, delivering coherent, context‑aware, and deeply reasoned insights at exceptional speed.","pricing":{"prompt":"0.000000202","completion":"0.0000005051","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-4.1-fast-non-reasoning","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":2000000,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok-4.1-Fast-Non-Reasoning is a streamlined companion to Grok 4.1 Fast, xAI’s best agentic tool‑calling model. It has 2M context window and high responsiveness but is optimized for non‑reasoning tasks — excelling at text generation, summarization, and automated workflows that demand speed and efficiency over deep logic. Ideal for high-throughput use cases like customer support automation, bulk content creation, and fast conversational responses.","pricing":{"prompt":"0.000000202","completion":"0.0000005051","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-code-fast-1","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":256000,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Grok","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...","pricing":{"prompt":"0.0000002","completion":"0.0000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":10,"premium":false,"context_window":2000000,"max_output_tokens":30000,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"Grok","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model...","pricing":{"prompt":"0.0000002","completion":"0.0000005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4-fast-reasoning","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":2000000,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 4 Fast Reasoning delivers exceptional performance for tasks requiring logical thinking and problem-solving. With a 2M token context window and state-of-the-art cost-efficiency, it handles complex reasoning tasks with accuracy and speed, making advanced AI capabilities accessible to more users.","pricing":{"prompt":"0.000000202","completion":"0.0000005051","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-4-fast-non-reasoning","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":2000000,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 4 Fast Non-Reasoning is designed for fast, efficient tasks like content generation with a 2M token context window. Combining cutting-edge performance with cost-efficiency, it ensures high-quality results for simpler, everyday applications.","pricing":{"prompt":"0.000000202","completion":"0.0000005051","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-3","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":10,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Grok","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-3-fast","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":12,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Grok","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-3-mini","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Grok","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.","pricing":{"prompt":"0.0000003","completion":"0.0000005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-3-mini-fast","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":3,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Grok","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.","pricing":{"prompt":"0.0000003","completion":"0.0000005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"codestral-2508","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":256000,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","pricing":{"prompt":"0.0000003","completion":"0.0000009","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"codestral-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":256000,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","pricing":{"prompt":"0.0000003","completion":"0.0000009","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known","metadata_resolved_from":"codestral-2508"},{"id":"devstral-small-2507","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...","pricing":{"prompt":"0.0000001","completion":"0.0000003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"devstral-small-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...","pricing":{"prompt":"0.0000001","completion":"0.0000003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known","metadata_resolved_from":"devstral-small-2507"},{"id":"labs-devstral-small-2512","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"devstral-medium-2507","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...","pricing":{"prompt":"0.0000004","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"devstral-medium-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...","pricing":{"prompt":"0.0000004","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known","metadata_resolved_from":"devstral-medium-2507"},{"id":"magistral-small-2509","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"magistral-small-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"magistral-medium-2509","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":6,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Magistral Medium 2509 (thinking) by EmpirioLabs.\nMagistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical. Context Window: 40,000k\nSupported file type uploads: PDF, XLSX, TXT, PNG, JPG, JPEG","pricing":{"prompt":"0.0000026263","completion":"0.0000065657","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"magistral-medium-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":6,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Magistral Medium 2509 (thinking) by EmpirioLabs.\nMagistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical. Context Window: 40,000k\nSupported file type uploads: PDF, XLSX, TXT, PNG, JPG, JPEG","pricing":{"prompt":"0.0000026263","completion":"0.0000065657","image":null,"request":null},"metadata_source":"poe","metadata_status":"known","metadata_resolved_from":"magistral-medium-2509"},{"id":"mistral-small-2603","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":262144,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Mistral","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"mistral-small-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":262144,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Mistral","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known","metadata_resolved_from":"mistral-small-2603"},{"id":"labs-mistral-small-creative","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"mistral-medium-2508","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":128000,"max_output_tokens":4096,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral AI's medium-sized model. Supports a context window of 32k tokens (around 24,000 words) and is stronger than Mixtral-8x7b and Mistral-7b on benchmarks across the board.","pricing":{"prompt":"0.0000027273","completion":"0.0000081818","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"mistral-medium-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":128000,"max_output_tokens":4096,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral AI's medium-sized model. Supports a context window of 32k tokens (around 24,000 words) and is stronger than Mixtral-8x7b and Mistral-7b on benchmarks across the board.","pricing":{"prompt":"0.0000027273","completion":"0.0000081818","image":null,"request":null},"metadata_source":"poe","metadata_status":"known","metadata_resolved_from":"mistral-medium-2508"},{"id":"mistral-large-2512","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":262144,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Mistral","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","pricing":{"prompt":"0.0000005","completion":"0.0000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"mistral-large-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":262144,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Mistral","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","pricing":{"prompt":"0.0000005","completion":"0.0000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known","metadata_resolved_from":"mistral-large-2512"},{"id":"pixtral-large-2411","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":7,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Mistral","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...","pricing":{"prompt":"0.000002","completion":"0.000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"pixtral-large-latest","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":7,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Mistral","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...","pricing":{"prompt":"0.000002","completion":"0.000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known","metadata_resolved_from":"pixtral-large-2411"},{"id":"sonar","object":"model","created":1749028256,"owned_by":"perplexity","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":127072,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Other","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","pricing":{"prompt":"0.000001","completion":"0.000001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"sonar-pro","object":"model","created":1749028256,"owned_by":"perplexity","endpoint":"/v1/chat/completions","token_multiplier":10,"premium":false,"context_window":200000,"max_output_tokens":8000,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Other","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"sonar-reasoning-pro","object":"model","created":1749028256,"owned_by":"perplexity","endpoint":"/v1/chat/completions","token_multiplier":6,"premium":false,"context_window":128000,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Other","supports_vision":true,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":true,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","pricing":{"prompt":"0.000002","completion":"0.000008","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"sonar-deep-research","object":"model","created":1749028256,"owned_by":"perplexity","endpoint":"/v1/chat/completions","token_multiplier":6,"premium":false,"context_window":128000,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":true,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","pricing":{"prompt":"0.000002","completion":"0.000008","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"command-a","object":"model","created":1749028256,"owned_by":"cohere","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":256000,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"command-a-vision","object":"model","created":1749028256,"owned_by":"cohere","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":256000,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"command-a-reasoning","object":"model","created":1749028256,"owned_by":"cohere","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":256000,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"command-r-7b","object":"model","created":1749028256,"owned_by":"cohere","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":128000,"max_output_tokens":4000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Cohere","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","pricing":{"prompt":"0.0000000375","completion":"0.00000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"command-r","object":"model","created":1749028256,"owned_by":"cohere","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":128000,"max_output_tokens":4000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Cohere","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"command-r-plus","object":"model","created":1749028256,"owned_by":"cohere","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":128000,"max_output_tokens":4000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Cohere","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-oss-20b","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"GPT","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","pricing":{"prompt":"0.00000003","completion":"0.00000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-oss-120b","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"GPT","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","pricing":{"prompt":"0.000000039","completion":"0.00000019","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"kimi-k2.6","object":"model","created":1749028256,"owned_by":"moonshotai","endpoint":"/v1/chat/completions","token_multiplier":2.8,"premium":false,"context_window":256000,"max_output_tokens":65536,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Other","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","pricing":{"prompt":"0.0000007448","completion":"0.000004655","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"kimi-k2.5","object":"model","created":1749028256,"owned_by":"moonshotai","endpoint":"/v1/chat/completions","token_multiplier":2.5,"premium":false,"context_window":262144,"max_output_tokens":65535,"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text","tokenizer":"Other","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","pricing":{"prompt":"0.00000044","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"kimi-k2-0905","object":"model","created":1749028256,"owned_by":"moonshotai","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","pricing":{"prompt":"0.0000004","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"kimi-k2-0905-fast","object":"model","created":1749028256,"owned_by":"moonshotai","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","pricing":{"prompt":"0.0000004","completion":"0.000002","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"minimax-m2","object":"model","created":1749028256,"owned_by":"minimax","endpoint":"/v1/chat/completions","token_multiplier":1.4,"premium":false,"context_window":196608,"max_output_tokens":196608,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","pricing":{"prompt":"0.000000255","completion":"0.000001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"minimax-m2.1","object":"model","created":1749028256,"owned_by":"minimax","endpoint":"/v1/chat/completions","token_multiplier":1.6,"premium":false,"context_window":196608,"max_output_tokens":196608,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","pricing":{"prompt":"0.00000029","completion":"0.00000095","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"minimax-m2.5","object":"model","created":1749028256,"owned_by":"minimax","endpoint":"/v1/chat/completions","token_multiplier":1.6,"premium":false,"context_window":196608,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","pricing":{"prompt":"0.00000015","completion":"0.00000115","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"minimax-m2.7","object":"model","created":1749028256,"owned_by":"minimax","endpoint":"/v1/chat/completions","token_multiplier":1.6,"premium":false,"context_window":196608,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","pricing":{"prompt":"0.0000003","completion":"0.0000012","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-5.1","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":3,"premium":false,"context_window":202752,"max_output_tokens":65535,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","pricing":{"prompt":"0.00000105","completion":"0.0000035","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-5","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":3,"premium":false,"context_window":202752,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","pricing":{"prompt":"0.0000006","completion":"0.00000208","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-4.7","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":202752,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","pricing":{"prompt":"0.00000038","completion":"0.00000174","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-4.6","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":204800,"max_output_tokens":204800,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","pricing":{"prompt":"0.00000039","completion":"0.0000019","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-4.6v","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":131072,"max_output_tokens":24000,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text","tokenizer":"Other","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","pricing":{"prompt":"0.0000003","completion":"0.0000009","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-4.5","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":131072,"max_output_tokens":98304,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","pricing":{"prompt":"0.0000006","completion":"0.0000022","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-4.5-air","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":1.8,"premium":false,"context_window":131072,"max_output_tokens":98304,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","pricing":{"prompt":"0.00000013","completion":"0.00000085","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"qwen3.5-397b-a17b","object":"model","created":1749028256,"owned_by":"alibaba","endpoint":"/v1/chat/completions","token_multiplier":3,"premium":false,"context_window":262144,"max_output_tokens":65536,"input_modalities":["text","image","video"],"output_modalities":["text"],"modality":"text+image+video->text","tokenizer":"Qwen3","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","pricing":{"prompt":"0.00000039","completion":"0.00000234","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"qwen3-coder","object":"model","created":1749028256,"owned_by":"alibaba","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":262144,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Qwen3","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","pricing":{"prompt":"0.00000022","completion":"0.0000018","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"qwen3-235b-a22b-2507","object":"model","created":1749028256,"owned_by":"alibaba","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":262144,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Qwen3","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","pricing":{"prompt":"0.000000071","completion":"0.0000001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"qwen3-235b-a22b-thinking-2507","object":"model","created":1749028256,"owned_by":"alibaba","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Qwen3","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","pricing":{"prompt":"0.0000001495","completion":"0.000001495","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"qwen3-32b","object":"model","created":1749028256,"owned_by":"alibaba","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":40960,"max_output_tokens":40960,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Qwen3","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","pricing":{"prompt":"0.00000008","completion":"0.00000024","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"nemotron-3-super","object":"model","created":1749028256,"owned_by":"nvidia","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","pricing":{"prompt":"0","completion":"0","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"phi-4","object":"model","created":1749028256,"owned_by":"microsoft","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":16384,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","pricing":{"prompt":"0.000000065","completion":"0.00000014","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"wizardlm-2-8x22b","object":"model","created":1749028256,"owned_by":"microsoft","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":65535,"max_output_tokens":8000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Mistral","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":false,"supports_json_mode":false,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...","pricing":{"prompt":"0.00000062","completion":"0.00000062","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"hermes-4-70b","object":"model","created":1749028256,"owned_by":"nousresearch","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Llama3","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...","pricing":{"prompt":"0.00000013","completion":"0.0000004","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"hermes-4-405b","object":"model","created":1749028256,"owned_by":"nousresearch","endpoint":"/v1/chat/completions","token_multiplier":4,"premium":false,"context_window":131072,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":false,"supports_function_calling":false,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","pricing":{"prompt":"0.000001","completion":"0.000003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"mercury-2","object":"model","created":1749028256,"owned_by":"inception","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":128000,"max_output_tokens":50000,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","pricing":{"prompt":"0.00000025","completion":"0.00000075","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"compound","object":"model","created":1749028256,"owned_by":"groq","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"compound-mini","object":"model","created":1749028256,"owned_by":"groq","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"venice-uncensored","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"venice-uncensored-role-play","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"deepseek-v3.2-venice","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":131072,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"DeepSeek","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","pricing":{"prompt":"0.000000252","completion":"0.000000378","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-5-venice","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":202752,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","pricing":{"prompt":"0.0000006","completion":"0.00000208","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-5.1-venice","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":202752,"max_output_tokens":65535,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","pricing":{"prompt":"0.00000105","completion":"0.0000035","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-4.7-flash-heretic","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":202752,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":"Other","supports_vision":false,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","pricing":{"prompt":"0.00000006","completion":"0.0000004","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-uncensored","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":4.5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"devious-uncensored","object":"model","created":1749028256,"owned_by":"navyai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"revenant-uncensored","object":"model","created":1749028256,"owned_by":"navyai","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"laborratse-uncensored","object":"model","created":1749028256,"owned_by":"navyai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"laborratse-de-uncensored","object":"model","created":1749028256,"owned_by":"navyai","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"emotional-36b","object":"model","created":1749028256,"owned_by":"navyai","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":true,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gpt-image-2","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/images/generations","token_multiplier":35,"premium":true,"context_window":null,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"OpenAI’s state-of-the-art image generation model as of April 21, 2026, designed for fast, high-quality image generation and editing with strong prompt adherence and flexible image sizes. It supports generating, editing, restyling, and combining images attached to the latest user query.\n\nOptional Parameters:\n\nSet aspect ratio, with options 3:2, 1:1, and 2:3.\nSet quality to low, medium, and high.\nEnable use mask by toggling it on or by typing use_mask in the prompt. This option is turned off by default.","pricing":{"prompt":"0.0000050505","completion":"0.0000323232","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"gpt-image-1.5","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/images/generations","token_multiplier":35,"premium":true,"context_window":128000,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"OpenAI's frontier image generation model in ChatGPT as of December 2025, offering exceptional prompt adherence, world knowledge, precise edits, facial preservation, level of detail, and overall quality with improved latency/generation times. It supports editing, restyling, and combining images attached to the latest user query. For a conversational image generation and editing experience\n\nOptional Parameters:\nSet aspect ratio, with options 3:2, 1:1 and 2:3. \nSet quality to low, medium and high. Default is set to high.\nEnable use mask by toggling it on or by typing 'use_mask' in the prompt. This option is turned off by default.\nDisable high fidelity by toggling it off or by typing 'use_high_fidelity'. This option is turned on by default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"dall-e-3","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/images/generations","token_multiplier":30,"premium":false,"context_window":800,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"OpenAI's most powerful image generation model. Generates high quality images with intricate details based on the user's most recent prompt.com/FLUX-dev will produce better results.\n\nOptional parameters:\nAspect Ratio to select an aspect ratio. Valid aspect ratios are 1:1, 7:4, & 4:7.","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.045"},"metadata_source":"poe","metadata_status":"known"},{"id":"dall-e-2","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/images/generations","token_multiplier":25,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"flux","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Text-to-image generation and image editing with Flux 2 [klein] 4B Base from Black Forest Labs. Enhanced realism, crisper text rendering within images, and native editing capabilities. Send up to 3 images (jpeg/ png/ webp) to use for image editing or as references.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"flux.1-schnell","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":256,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.\n\nKey Features\n1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives.\n2. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.\n3. Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes.\nBot does not support attachments.","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.0011"},"metadata_source":"poe","metadata_status":"known"},{"id":"flux.1-schnell-uncensored","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":256,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.\n\nKey Features\n1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives.\n2. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.\n3. Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes.\nBot does not support attachments.","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.0011"},"metadata_source":"poe","metadata_status":"known"},{"id":"flux.2-pro","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":10,"premium":true,"context_window":null,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Flux.2 [Pro] is Black Forest Labs' state-of-the-art model with multi-reference support, fine-grained text rendering, and other features. Supports structured JSON prompts, and allows use of hex colour codes within the prompt for precise colouring.  Send images (Up to 8 images) in jpeg/png/webp format for editing. Total megapixels (input + output) should not exceed 9 megapixels.\n\nOptional parameter:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"flux.2-flex","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":15,"premium":true,"context_window":null,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Flux.2 [Flex] is Black Forest Lab's latest model, with Multi-Reference Support, Fine-grained text rendering, and other features. Supports structured JSON prompts, and allows use of hex color codes within the prompt for precise coloring.\nSend images in jpeg/png/webp format for editing. Total megapixels (input + output) should not exceed 14 megapixels.\n\nOptional parameters:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"flux.2-dev","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":2,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Open-weight image gen (32B) model, derived from the FLUX.2 base model. The most powerful open-weight image generation and editing model available today, combining text-to-image synthesis and image editing with multiple input images in a single checkpoint.\n\nOptional parameters:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"flux.2-klein","object":"model","created":1749028256,"owned_by":"blackforest-ai","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Text-to-image generation and image editing with Flux 2 [klein] 4B Base from Black Forest Labs. Enhanced realism, crisper text rendering within images, and native editing capabilities. Send up to 3 images (jpeg/ png/ webp) to use for image editing or as references.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-imagine","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/images/generations","token_multiplier":10,"premium":true,"context_window":null,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Create creative and artistic images with Grok Imagine Image. Supports text-to-image and image-editing (single image of jpeg/png/webp format). Set aspect ratio via parameter controls.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-imagine-video","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/images/generations","token_multiplier":50,"premium":true,"context_window":256,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["video"],"modality":"text->video","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":null,"description":"Create artistic and creative videos with Grok Imagine Video. Supports text to video, image to video (single jpeg/png/webp attachment), and video editing (single mp4 video attachment). Check parameter controls for all supported controls (resolution, video duration, and aspect_ratio).","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"z-image","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Super-fast endpoint for Z-Image Turbo, hosted by fal.ai. Excels at portrait photos and realistic images.\n\nNotes:\nBot does not accept attachment.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"nano-banana-pro","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/images/generations","token_multiplier":40,"premium":true,"context_window":65536,"max_output_tokens":null,"input_modalities":["text","image"],"output_modalities":["image"],"modality":"text+image->image","tokenizer":null,"supports_vision":true,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages.\n\nThis bot supports optional parameters for additional customization.","pricing":{"prompt":"0.0000020202","completion":"0.0000121212","image":"0.0001212121","request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"nano-banana-2","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/images/generations","token_multiplier":10,"premium":false,"context_window":65536,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"Google's latest image model combines Pro-level intelligence with lightning-fast generation. It features advanced world knowledge, precise text rendering, strong subject consistency, and 4K production-ready outputs.\n\nThis bot supports optional parameters for additional customization.","pricing":{"prompt":"0.0000005051","completion":"0.0000030303","image":"0.0000606061","request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"imagen-4","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/images/generations","token_multiplier":7,"premium":true,"context_window":480,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["image"],"modality":"text->image","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":true,"supports_streaming":null,"description":"DeepMind's June 2025 text-to-image model with exceptional prompt adherence, capable of generating images with great detail, rich lighting, and few distracting artifacts. \n\nOptional parameters:\nAspect ratio of your image (1:1, 16:9, 9:16, 4:3, 3:4). \n\nNotes:\nNon-English input will be translated first. Serves the `imagen-4.0-fast-generate-preview-06-06` model from Google Vertex, and has a maximum input of 480 tokens.","pricing":{"prompt":null,"completion":null,"image":null,"request":"0.014"},"metadata_source":"poe","metadata_status":"known"},{"id":"p-image","object":"model","created":1749028256,"owned_by":"pruna-ai","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"dirtberry.1","object":"model","created":1749028256,"owned_by":"dirtberry","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"dirtberry","object":"model","created":1749028256,"owned_by":"dirtberry","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"dirtberry-pro","object":"model","created":1749028256,"owned_by":"dirtberry","endpoint":"/v1/images/generations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"cogvideox-flash","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/images/generations","token_multiplier":5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"veo-3.1","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/images/generations","token_multiplier":200,"premium":true,"required_plan":"Ultra","context_window":480,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["video"],"modality":"text->video","tokenizer":null,"supports_vision":false,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":null,"description":"Google’s Veo 3.1 is an updated version of the Veo family of models that features richer native audio, from natural conversations to synchronized sound effects, and offers greater narrative control with an improved understanding of cinematic styles. Enhanced image-to-video capabilities ensure better prompt adherence while delivering superior audio and visual quality and maintaining character consistency across multiple scenes.\n\nOptional parameters:\n- Set the aspect ratio (either `16:9` or `9:16`), which defaults to `16:9`\n- Negative prompt can be set on elements to avoid\n- Set the duration (one of `4s`, `6s`, or `8s`), which defaults to `8s`\n- Seed to set the seed (set number value)\n- Resolution (set from 720p or 1080p)\n- Reference mode. Toggle to use input images (3 max) as reference for video generation","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"omni-moderation-latest","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/moderations","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"text-embedding-3-large","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/embeddings","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"text-embedding-3-small","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/embeddings","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"text-embedding-ada-002","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/embeddings","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gemini-embedding-2-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/embeddings","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gemini-embedding-001","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/embeddings","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"whisper-1","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/audio/transcriptions","token_multiplier":1,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gpt-4o-transcribe","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/audio/transcriptions","token_multiplier":3,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","pricing":{"prompt":"0.0000025","completion":"0.00001","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-4o-mini-transcribe","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/audio/transcriptions","token_multiplier":2,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"scribe_v2","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/transcriptions","token_multiplier":5,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gpt-4o-mini-tts","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/audio/speech","token_multiplier":50,"premium":false,"context_window":128000,"max_output_tokens":16384,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->text","tokenizer":"GPT","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":false,"supports_json_mode":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":null,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","pricing":{"prompt":"0.00000015","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"tts-1","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/audio/speech","token_multiplier":80,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"tts-1-hd","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/audio/speech","token_multiplier":150,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"eleven_v3","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/speech","token_multiplier":120,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"eleven_multilingual_v2","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/speech","token_multiplier":100,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"eleven_turbo_v2_5","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/speech","token_multiplier":100,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"eleven_turbo_v2","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/speech","token_multiplier":100,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"eleven_flash_v2_5","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/speech","token_multiplier":100,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"eleven_flash_v2","object":"model","created":1749028256,"owned_by":"elevenlabs","endpoint":"/v1/audio/speech","token_multiplier":100,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":null,"output_modalities":null,"modality":null,"tokenizer":null,"supports_vision":null,"supports_tools":null,"supports_function_calling":null,"supports_reasoning":null,"supports_json_mode":null,"supports_audio_input":null,"supports_image_output":null,"supports_streaming":null,"description":null,"pricing":null,"metadata_source":null,"metadata_status":"unknown"},{"id":"gemini-2.5-flash-preview-tts","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/audio/speech","token_multiplier":50,"premium":false,"context_window":1048576,"max_output_tokens":65535,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"modality":"text+image+file+audio+video->text","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"supports_reasoning":true,"supports_json_mode":true,"supports_audio_input":true,"supports_image_output":false,"supports_streaming":null,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","request":null},"metadata_source":"openrouter","metadata_status":"known"}]}