Model catalog

Qwen3-VL PlusAlibaba

Qwen3-VL Plus accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Qwen3 Omni 30B A3B ThinkingAlibaba

Qwen3 Omni 30B A3B Thinking accepts text, images, video, audio and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 16,384 tokens.

Magistral Small 1.2Mistral

Magistral Small 1.2 accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

GPT-5-CodexOpenAI

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

Kimi K2 Instruct 0905Moonshot AI

Kimi K2 Instruct 0905 accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 98,304 tokens.

Qwen3 Max PreviewAlibaba

Qwen3 Max Preview accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Apertus 8BSwiss Ai

Apertus 8B accepts text and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 8,192 tokens.

Apertus 70BSwiss Ai

Apertus 70B accepts text and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 8,192 tokens.

x-AI/Grok-Code-Fast 1xAI

x-AI/Grok-Code-Fast 1 accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 10,000 tokens.

Sarvam 105BSarvam AI

Sarvam 105B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Qwen3-Next 80B-A3B (Thinking)Alibaba

Qwen3-Next 80B-A3B (Thinking) accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Qwen3-Next 80B-A3B InstructAlibaba

Qwen3-Next 80B-A3B Instruct accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Command A TranslateCohere

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

Seed 1.6 FlashBytedance Seed

Seed 1.6 Flash accepts text, images and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 32,000 tokens.

Hermes 4 405BNousresearch

Hermes 4 405B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 117,964 tokens.

Nano BananaGoogle

Nano Banana accepts text, images and returns text, images. The canonical context window is 32,768 tokens. The canonical maximum output is 32,768 tokens.

Command A ReasoningCohere

Command A Reasoning accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 32,000 tokens.

DeepSeek-V3.1DeepSeek

DeepSeek-V3.1 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

DeepSeek V3.1DeepSeek

DeepSeek V3.1 accepts text and returns text. The canonical context window is 163,840 tokens. The canonical maximum output is 32,768 tokens.

Nemotron Nano 9B v2Nvidia

Nemotron Nano 9B v2 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Seed 1.6 VisionBytedance Seed

Seed 1.6 Vision accepts text, images and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 32,000 tokens.

Baichuan M2 32BBaichuan

Baichuan M2 32B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Mistral Medium 3.1Mistral

Mistral Medium 3.1 accepts text, images, PDFs and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 104,857 tokens.

GLM-4.5VZhipu AI

GLM-4.5V accepts text, images, video and returns text. The canonical context window is 64,000 tokens. The canonical maximum output is 16,384 tokens.