The best platform to
instantly access every AI model

One endpoint, one API key. connect to the world's leading language models without juggling providers.

Route to any model

One unified API key. Switch between providers without changing your integration.

OpenAIgpt-5-212ms
Anthropicclaude-opus-4-618ms
Geminigemini-3.1-pro9ms

Drop-in OpenAI replacement

Already using the OpenAI SDK? Point your base URL at Navy and every model becomes available instantly.

Request
NavyNavyAI
OpenAIgpt-5-2
Anthropicclaude-opus-4-6
Geminigemini-3.1-pro
DeepSeekdeepseek-v3.2

Live usage & latency

Track token spend, response times, and model performance across every provider in one dashboard.

Token usage
Last 7d
By model
OpenAI2.4M tokens today
Model health
OpenAI
gpt-5-211ms
Anthropic
claude-opus-4-619ms
Gemini
gemini-3.1-pro8ms

Every major provider

All the models you need, all through one key.

OpenAIOpenAI
AnthropicAnthropic
GeminiGoogle
MistralMistral
CohereCohere
+40 more

Simple pricing

Pay for what you use. No surprises.

How token usage works

Your daily allowance is consumed differently depending on the model type.

Chat & Text

  • Billed per input + output token
  • Multiplier varies by model

Image Generation

  • 5,000 base tokens per image
  • Multiplier varies by model

Audio Processing

  • 5,000 base tokens per request
  • Multiplier varies by model

Frequently asked questions

Everything you need to know before getting started.

How does the daily token allowance work?
Can I upgrade my plan anytime?
Can I downgrade my plan?
What payment methods do you accept?
Is there a free trial for paid plans?
What happens if I exceed my daily limit?
Do you offer refunds?