Access the world's most advanced AI models through a single API. Compare pricing, capabilities, and performance to find the perfect model for your use case.
Anthropic
Fastest Claude model optimized for speed
OpenAI
Fast and cost-effective for simpler tasks
Mistral AI
Balanced model for European markets
Anthropic
Balanced performance and speed for most use cases
Google's advanced multimodal model
OpenAI
Most capable model for complex reasoning and creative tasks
Mistral AI
High-performance model with excellent multilingual support
Anthropic
Powerful model excelling at analysis and creative writing
Model | Provider | Input Price | Output Price | Context | Status |
---|---|---|---|---|---|
Claude 3 Haiku Fastest Claude model optimized for speed | A Anthropic | $0.25 per 1M tokens | $1.25 per 1M tokens | 200K | available |
GPT-3.5 Turbo Fast and cost-effective for simpler tasks | O OpenAI | $0.5 per 1M tokens | $1.5 per 1M tokens | 16K | available |
Mistral Medium Balanced model for European markets | M Mistral AI | $2.7 per 1M tokens | $8.1 per 1M tokens | 32K | limited |
Claude 3 Sonnet Balanced performance and speed for most use cases | A Anthropic | $3 per 1M tokens | $15 per 1M tokens | 200K | available |
Gemini Pro Google's advanced multimodal model | G Google | $3.5 per 1M tokens | $10.5 per 1M tokens | 32K | beta |
GPT-4o Most capable model for complex reasoning and creative tasks | O OpenAI | $5 per 1M tokens | $15 per 1M tokens | 128K | available |
Mistral Large High-performance model with excellent multilingual support | M Mistral AI | $8 per 1M tokens | $24 per 1M tokens | 32K | available |
Claude 3 Opus Powerful model excelling at analysis and creative writing | A Anthropic | $15 per 1M tokens | $75 per 1M tokens | 200K | available |
Only pay for the tokens you actually consume. No monthly fees or hidden costs.
All prices shown are final. What you see is what you pay, with detailed usage tracking.
Usage is tracked and billed in real-time. Monitor costs as you go in your dashboard.
All models are accessible through the same API endpoint. Switch between models with a single parameter change.