Models
Access the best AI models from leading providers through a single API. Compare pricing, capabilities, and performance benchmarks to find the perfect model for your use case.
GPT-4o
Most capable GPT-4 model with vision capabilities
Context
128K
Input
$2.50/1M
Output
$10.00/1M
Speed
GPT-4o Mini
Affordable small model for fast, lightweight tasks
Context
128K
Input
$0.15/1M
Output
$0.60/1M
Speed
Claude 3.5 Sonnet
Best balance of intelligence and speed
Context
200K
Input
$3.00/1M
Output
$15.00/1M
Speed
Claude 3 Haiku
Fastest model for quick, efficient responses
Context
200K
Input
$0.25/1M
Output
$1.25/1M
Speed
DeepSeek Chat
High-quality open-source model for general chat
Context
64K
Input
$0.14/1M
Output
$0.28/1M
Speed
DeepSeek Coder
Specialized coding model with strong performance
Context
64K
Input
$0.14/1M
Output
$0.28/1M
Speed
Mistral Large
Flagship model with top-tier reasoning
Context
128K
Input
$2.00/1M
Output
$6.00/1M
Speed
Mixtral 8x7B
Efficient mixture-of-experts model
Context
32K
Input
$0.24/1M
Output
$0.24/1M
Speed
Llama 3.1 70B
Open-source model with strong capabilities
Context
128K
Input
$0.59/1M
Output
$0.79/1M
Speed
Gemini 1.5 Pro
Multimodal model with massive context window
Context
2M
Input
$1.25/1M
Output
$5.00/1M
Speed
Command R+
Enterprise-grade model for RAG and tool use
Context
128K
Input
$2.50/1M
Output
$10.00/1M
Speed
Llama 3 70B (Groq)
Ultra-fast inference with Groq LPU
Context
8K
Input
$0.59/1M
Output
$0.79/1M
Speed
12+
Models Available
8
Providers
2M
Max Context
99.9%
Uptime