Model directory
Every model, one endpoint
Compare 36 models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, Moonshot AI and xAI - token prices, context windows and speed - then call any of them without changing your code.
OpenAI
Hardest reasoning · Long context · Structured output
General purpose · Structured output · Long context
Balanced · Cheap · Tool use
Cheapest · Fast · Classification
General purpose · Structured output
Fast · Cheap · Classification
Anthropic
Hardest reasoning · Long-horizon agents · Long context
Agentic coding · Reasoning · Long context
Balanced · Coding · Tool use
Cheapest Claude · Fast · High volume
Reasoning · Long context · Agentic coding
Balanced · Coding · Tool use
Fast · Takes temperature · High volume
Reasoning · Huge context · Multimodal
Fast · Huge context · Multimodal
Very fast · Cheap · Summarization
Huge context · Multimodal
Very fast · Long context · Summarization
Meta
Reasoning · Huge context · Agentic coding
Agentic coding · Huge context · Tool use
Agentic coding · Huge context · Tool use
Coding · Huge context
Mistral
DeepSeek
Moonshot AI
Reasoning · Huge context · Agentic coding
Fast · Reasoning · Agentic coding
Reasoning · Huge context · Agentic coding
Cheap · Long context · Tool use
Agentic coding · Long context · Tool use
Fast · Agentic coding · Tool use