{"object":"list","data":[{"id":"schizogpt","object":"model","created":1749028256,"owned_by":"navyai","endpoint":"/v1/chat/completions","token_multiplier":0,"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-5.6-sol","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":13,"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-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","pricing":{"prompt":"0.000005","completion":"0.00003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.6-terra","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":6,"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-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","pricing":{"prompt":"0.000001","completion":"0.000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gpt-5.6-luna","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":2,"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-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","pricing":{"prompt":"0.0000001","completion":"0.0000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"chat-latest","object":"model","created":1749028256,"owned_by":"openai","endpoint":"/v1/chat/completions","token_multiplier":13,"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":"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-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-5.1","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","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":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-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-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-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":8192,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":null,"supports_vision":false,"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":"OpenAI's fine-tuned model for searching the web for real-time information. For less expensive messages, Uses medium search context size, currently in preview, supports 128k tokens of context. Does not support image search.","pricing":{"prompt":"0.0000022727","completion":"0.0000090909","image":null,"request":null},"metadata_source":"poe","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","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-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":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 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-5","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","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":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","pricing":{"prompt":"0.00001","completion":"0.00005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"claude-opus-4.8","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","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":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","pricing":{"prompt":"0.00001","completion":"0.00005","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"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","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":"Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - 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-4.6","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","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":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","pricing":{"prompt":"0.000005","completion":"0.000025","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-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":128000,"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":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","pricing":{"prompt":"0.000002","completion":"0.00001","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","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":"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-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","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 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-3.6-flash","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":5.5,"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 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.6-flash-thinking","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":5.5,"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 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.5-flash","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":6,"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 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.5-flash-thinking","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":6,"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 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.5-flash-lite","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":2.5,"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 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.5-flash-lite-thinking","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":2.5,"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 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","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","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 is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.1-flash-lite-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","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 is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.1-flash-image","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":45,"premium":false,"context_window":131072,"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":"Gemini 3.1 Flash Image, 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 advanced...","pricing":{"prompt":"0.0000005","completion":"0.000003","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3.1-flash-lite-image","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":30,"premium":false,"context_window":65536,"max_output_tokens":66000,"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 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","pricing":{"prompt":"0.00000025","completion":"0.0000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"gemini-3-pro-image","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/chat/completions","token_multiplier":58,"premium":true,"required_plan":"Admin","context_window":131072,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text","image"],"modality":"text+image->text+image","tokenizer":"Gemini","supports_vision":true,"supports_tools":true,"supports_function_calling":true,"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":45,"premium":false,"context_window":32768,"max_output_tokens":8192,"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":"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":262144,"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":"0.0000001","completion":"0.00000034","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":262144,"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":"0.00000012","completion":"0.0000004","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":131072,"max_output_tokens":131072,"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":"0.00000005","completion":"0.00000008","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-0731","object":"model","created":1749028256,"owned_by":"deepseek","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":1048576,"max_output_tokens":393216,"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 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","pricing":{"prompt":"0.00000014","completion":"0.00000028","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":393216,"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":2.1,"premium":false,"context_window":1048576,"max_output_tokens":393216,"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":"0.000001168","completion":"0.000002336","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":16000,"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":"0.0000002574","completion":"0.0000010287","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":163840,"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":"0.000000269","completion":"0.0000004","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4.5","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":6.5,"premium":false,"context_window":500000,"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 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","pricing":{"prompt":"0.000002","completion":"0.000006","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"grok-4.3","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":3,"premium":false,"context_window":1000000,"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 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","pricing":{"prompt":"0.00000125","completion":"0.0000025","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 a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","pricing":{"prompt":"0.00000125","completion":"0.0000025","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 a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","pricing":{"prompt":"0.00000125","completion":"0.0000025","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":null,"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text","tokenizer":null,"supports_vision":false,"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-Code-Fast-1 from xAI is a high-performance, cost-efficient model designed for agentic coding. It offers visible reasoning traces, strong steerability, and supports a 256k context window.","pricing":{"prompt":"0.000000202","completion":"0.0000015152","image":null,"request":null},"metadata_source":"poe","metadata_status":"known"},{"id":"grok-4","object":"model","created":1749028256,"owned_by":"xai","endpoint":"/v1/chat/completions","token_multiplier":10,"premium":false,"context_window":256000,"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 is xAI's latest and most intelligent language model. It features state-of-the-art capabilities in coding, reasoning, and answering questions. It excels at handling complex and multi-step tasks. Reasoning traces are not available via the xAI API.","pricing":{"prompt":"0.0000030303","completion":"0.0000151515","image":null,"request":null},"metadata_source":"poe","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":"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","file"],"output_modalities":["text"],"modality":"text+file->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","file"],"output_modalities":["text"],"modality":"text+file->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":"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":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-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":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-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":"mistral-medium-3-5","object":"model","created":1749028256,"owned_by":"mistral","endpoint":"/v1/chat/completions","token_multiplier":8,"premium":false,"context_window":262144,"max_output_tokens":null,"input_modalities":["text","image","file"],"output_modalities":["text"],"modality":"text+image+file->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 Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","pricing":{"prompt":"0.0000015","completion":"0.0000075","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"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":8,"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","file"],"output_modalities":["text"],"modality":"text+image+file->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","file"],"output_modalities":["text"],"modality":"text+image+file->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":"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-plus","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","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":"c4ai-aya-expanse-32b","object":"model","created":1749028256,"owned_by":"cohere","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":"c4ai-aya-vision-32b","object":"model","created":1749028256,"owned_by":"cohere","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":"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":"0.00000013","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":"0.00000003","completion":"0.00000017","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"kimi-k3","object":"model","created":1749028256,"owned_by":"moonshotai","endpoint":"/v1/chat/completions","token_multiplier":6.5,"premium":false,"context_window":1048576,"max_output_tokens":null,"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":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","pricing":{"prompt":"0.000003","completion":"0.000015","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"kimi-k2.7-code","object":"model","created":1749028256,"owned_by":"moonshotai","endpoint":"/v1/chat/completions","token_multiplier":3,"premium":false,"context_window":262144,"max_output_tokens":262144,"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":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","pricing":{"prompt":"0.00000067","completion":"0.0000034","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":262144,"max_output_tokens":262144,"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":"0.00000095","completion":"0.000004","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"mimo-v2.5","object":"model","created":1749028256,"owned_by":"xiaomi","endpoint":"/v1/chat/completions","token_multiplier":1.2,"premium":false,"context_window":1050000,"max_output_tokens":131072,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"modality":"text+image+audio+video->text","tokenizer":"Other","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":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","pricing":{"prompt":"0.00000014","completion":"0.00000028","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"mimo-v2.5-pro","object":"model","created":1749028256,"owned_by":"xiaomi","endpoint":"/v1/chat/completions","token_multiplier":1.5,"premium":false,"context_window":1050000,"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":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","pricing":{"prompt":"0.000000435","completion":"0.00000087","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"minimax-m3","object":"model","created":1749028256,"owned_by":"minimax","endpoint":"/v1/chat/completions","token_multiplier":2,"premium":false,"context_window":1048576,"max_output_tokens":512000,"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":true,"supports_audio_input":false,"supports_image_output":false,"supports_streaming":true,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","pricing":{"prompt":"0.0000003","completion":"0.0000012","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":204800,"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-M2.7 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-5.2","object":"model","created":1749028256,"owned_by":"z-ai","endpoint":"/v1/chat/completions","token_multiplier":4,"premium":false,"context_window":1048576,"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 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","pricing":{"prompt":"0.00000063","completion":"0.00000198","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":204800,"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":"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":"0.0000014","completion":"0.0000044","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"qwen3.6-27b","object":"model","created":1749028256,"owned_by":"alibaba","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":262144,"max_output_tokens":262144,"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":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","pricing":{"prompt":"0.0000006","completion":"0.0000036","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":262144,"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":"0.0000005","completion":"0.0000036","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":"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":"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-v4-flash-venice","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":1048576,"max_output_tokens":393216,"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-v3.2-venice","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":163840,"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":"0.000000269","completion":"0.0000004","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":204800,"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":"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":"0.00000095","completion":"0.00000255","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":204800,"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":"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":"0.0000014","completion":"0.0000044","image":null,"request":null},"metadata_source":"openrouter","metadata_status":"known"},{"id":"glm-5.2-venice","object":"model","created":1749028256,"owned_by":"venice","endpoint":"/v1/chat/completions","token_multiplier":1,"premium":false,"context_window":1048576,"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 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","pricing":{"prompt":"0.00000063","completion":"0.00000198","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":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 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":"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":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.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":"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-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":"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":"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":"gemini-omni","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/images/generations","token_multiplier":200,"premium":true,"required_plan":"Ultra","context_window":1048576,"max_output_tokens":null,"input_modalities":["text","image","video"],"output_modalities":["video"],"modality":"text+image+video->video","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":null,"description":"Google's Gemini Omni Flash is a high-quality, cost-efficient model where Gemini's multimodal reasoning meets video generation and conversational editing. It generates and refines videos from flexible inputs—text alone, images with text, video with text, or multiple images with text—and lets you edit results using natural language. Drawing on Gemini's real-world knowledge of history, biology and narrative logic, it produces compelling videos with synchronized text and on-screen action, while multimodal referencing helps maintain control and consistency across your scene.","pricing":{"prompt":"0.0000015152","completion":"0.0000090909","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-3.1-flash-tts-preview","object":"model","created":1749028256,"owned_by":"google","endpoint":"/v1/audio/speech","token_multiplier":50,"premium":false,"context_window":null,"max_output_tokens":null,"input_modalities":["text"],"output_modalities":["audio"],"modality":"text->audio","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":"Gemini 3.1 Flash TTS is Google’s most controllable text-to-speech model yet, designed to turn text into natural-sounding audio with precise control over style, tone, pace, and delivery. It uses new Audio Tags to make voices feel more expressive and customizable for narration, assistants, and other voice experiences.\n\nNotes:\n- Text and style prompt limited to 4,000 bytes each (8,000 bytes combined)\n- Max output duration: approximately 10 minutes\n- Multi-speaker requires SpeakerName: text format (example: Alice: Hi! Bob: Hello, must be on new lines)\n- The model auto-detects the input language. The Language setting is a hint to help choose the right voice/accent, the model may override it if the text is in a different language.\n\nExpressive Audio Tags:\n- Use inline in your text to control delivery\n- Emotion/tone: [whispers], [shouts], [laughs], [cries], [sighs], [gasps], [groans], [scoffs], [sarcasm], [deadpan], [cheerful], [sad], [angry], [fearful], [surprised], [disgusted], [confused], [nervous], [bored], [excited], [relieved], [hopeful], [proud], [shy], [sincere], [playful], [serious], [tender], [dramatic], [monotone], [warm], [cold]\n- Pace/speed: [slow], [fast], [extremely fast], [extremely slow], [normal pace]\n- Pauses: [short pause], [long pause], [pause], [breath]\n- Emphasis/delivery: [emphasis], [softly], [loudly], [high pitch], [low pitch], [rising tone], [falling tone]\n- Example: \"[whispers] I have a secret. [normal pace] But first, let me explain.\"\n\nThis bot supports optional parameters for additional customization.","pricing":{"prompt":null,"completion":null,"image":null,"request":null},"metadata_source":"poe","metadata_status":"known"}]}