Model catalog

Aion-2.0Aion Labs

Aion-2.0 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Qwen3.5 9BAlibaba

Qwen3.5 9B accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Qwen3.5 27BAlibaba

Qwen3.5 27B accepts text, images, video, audio and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Qwen3.5 35B-A3BAlibaba

Qwen3.5 35B-A3B accepts text, images, video, audio and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Qwen3.5 122B-A10BAlibaba

Qwen3.5 122B-A10B accepts text, images, video, audio and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Qwen3.5 FlashAlibaba

Qwen3.5 Flash accepts text, images, video and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 65,536 tokens.

Gemini 3.1 Pro PreviewGoogle

Gemini 3.1 Pro Preview accepts text, images, video, audio, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

Gemini 3.1 Pro Preview Custom ToolsGoogle

Gemini 3.1 Pro Preview Custom Tools accepts text, images, video, audio, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

Trendyol Asure 12BTrendyol

Trendyol Asure 12B accepts text, images and returns text. The canonical context window is 131,072 tokens.

Sarvam 30BSarvam AI

Sarvam 30B accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 128,000 tokens.

Claude Sonnet 4.6Anthropic

Claude Sonnet 4.6 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 64,000 tokens.

Qwen3.5 PlusAlibaba

Qwen3.5 Plus accepts text, images, video and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 65,536 tokens.

Qwen3.5 397B-A17BAlibaba

Qwen3.5 397B-A17B accepts text, images, video, audio and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Seed 2.0 CodeBytedance Seed

Seed 2.0 Code accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 131,072 tokens.

Seed 2.0 LiteBytedance Seed

Seed 2.0 Lite accepts text, images, video and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 32,000 tokens.

Seed 2.0 MiniBytedance Seed

Seed 2.0 Mini accepts text, images, video and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 32,000 tokens.

Seed 2.0 ProBytedance Seed

Seed 2.0 Pro accepts text, images, video and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 128,000 tokens.

MiniMax-M2.5-highspeedMiniMax (minimax.io)

MiniMax-M2.5-highspeed accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

GLM-5Zhipu AI

GLM-5 accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

MiniMax-M2.5MiniMax (minimax.io)

MiniMax-M2.5 accepts text and returns text. The canonical context window is 204,800 tokens. The canonical maximum output is 131,072 tokens.

Seedance 2.0Bytedance Seed

Seedance 2.0 accepts text, images, video, audio and returns video, audio.

Llama Nemotron Embed VL 1B v2Nvidia

Llama Nemotron Embed VL 1B v2 accepts text, images and returns text. The canonical context window is 32,768 tokens. The canonical maximum output is 2,048 tokens.

Claude Opus 4.6Anthropic

Claude Opus 4.6 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-5.3 CodexOpenAI

GPT-5.3 Codex accepts text, images, PDFs and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.