Model directory

Every model, one endpoint

Compare 20 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.

Seven providers' catalogues, one OpenAI-compatible endpoint - every entry with list-price costs, context window and measured speed.

Compare models head-to-head Quickstart

OpenAI

GPT-5.1OpenAI

$1.25 in$10 out400K ctx

General purpose · Structured output

GPT-5 miniOpenAI

$0.25 in$2 out400K ctx

Fast · Cheap · Classification

Anthropic

Claude Opus 5Anthropic

$5 in$25 out1M ctx

Reasoning · Long context · Agentic coding

Claude Sonnet 5Anthropic

$2 in$10 out1M ctx

Balanced · Coding · Tool use

Claude Haiku 4.5Anthropic

$1 in$5 out200K ctx

Fast · Cheap · High volume

Google

Gemini 2.5 ProGoogle

$1.25 in$10 out1.048576M ctx

Huge context · Multimodal

Gemini 2.5 FlashGoogle

$0.3 in$2.5 out1.048576M ctx

Very fast · Long context · Summarization

Mistral

Mistral LargeMistral

$0.5 in$1.5 out262K ctx

European hosting · Function calling

Mistral SmallMistral

$0.15 in$0.6 out262K ctx

Low cost · Low latency

DeepSeek

DeepSeek V4 ProDeepSeek

$0.66 in$1.98 out1M ctx

Reasoning · Huge context · Very cheap

DeepSeek V4 FlashDeepSeek

$0.22 in$0.66 out1M ctx

Cheapest · Huge context · Tool use

Moonshot AI

Kimi K3Moonshot AI

$3 in$15 out1.048576M ctx

Reasoning · Huge context · Agentic coding

Kimi K2.6Moonshot AI

$0.95 in$4 out262K ctx

Cheap · Long context · Tool use

Kimi K2.7 CodeMoonshot AI

$0.95 in$4 out262K ctx

Agentic coding · Long context · Tool use

Kimi K2.7 Code HighspeedMoonshot AI

$1.9 in$8 out262K ctx

Fast · Agentic coding · Tool use

xAI

Grok 4.6xAI

$2 in$6 out500K ctx

Agentic coding · Reasoning · Long context

Grok 4.3xAI

$1.25 in$2.5 out1M ctx

Huge context · Cheap · Reasoning

Grok Build 0.1xAI

$1 in$2 out256K ctx

Agentic coding · Cheap · Tool use