Model catalog

GPT-5OpenAI

GPT-5 accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5 Chat (latest)OpenAI

GPT-5 Chat (latest) accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5 MiniOpenAI

GPT-5 Mini accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5 NanoOpenAI

GPT-5 Nano accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

Claude Opus 4.1Anthropic

Claude Opus 4.1 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 32,000 tokens.

Claude Opus 4.1 (latest)Anthropic

Claude Opus 4.1 (latest) accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 32,000 tokens.

GPT OSS 20BOpenAI

GPT OSS 20B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

GPT OSS 120BOpenAI

GPT OSS 120B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Command A VisionCohere

Command A Vision accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 8,000 tokens.

Codestral 25.08Mistral

Codestral 25.08 accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 8,192 tokens.

GLM-4.5Zhipu AI

GLM-4.5 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 98,304 tokens.

GLM-4.5-AirZhipu AI

GLM-4.5-Air accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 98,304 tokens.

GLM-4.5-FlashZhipu AI

GLM-4.5-Flash accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 98,304 tokens.

Qwen3 Coder FlashAlibaba

Qwen3 Coder Flash accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 65,536 tokens.

Qwen FlashAlibaba

Qwen Flash accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 32,768 tokens.

Qwen MT PlusAlibaba

Qwen MT Plus accepts text and returns text. The canonical context window is 16,384 tokens. The canonical maximum output is 8,192 tokens.

Qwen3 Coder PlusAlibaba

Qwen3 Coder Plus accepts text and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

Qwen3 235B-A22B Instruct 2507Alibaba

Qwen3 235B-A22B Instruct 2507 accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 16,384 tokens.

Voxtral Mini 3B 2507Mistral

Voxtral Mini 3B 2507 accepts text, audio and returns text. The canonical context window is 32,768 tokens. The canonical maximum output is 32,768 tokens.

Voxtral Small (latest)Mistral

Voxtral Small (latest) accepts text, audio and returns text. The canonical context window is 32,000 tokens. The canonical maximum output is 32,000 tokens.

Voxtral Small 24B 2507Mistral

Voxtral Small 24B 2507 accepts text, audio and returns text. The canonical context window is 32,768 tokens. The canonical maximum output is 32,768 tokens.

Kimi K2 0711Moonshot AI

Kimi K2 0711 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 98,304 tokens.

Kimi K2 InstructMoonshot AI

Kimi K2 Instruct accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

UncensoredCognitivecomputations

Uncensored accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 8,192 tokens.