Model catalog

Muse Spark 1.3Meta

Muse Spark 1.3 accepts text, images, video, PDFs, audio and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

Qwen3.8 Max 0902Alibaba

Qwen3.8 Max 0902 accepts text, images, video, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Claude Fable 5.1Anthropic

Claude Fable 5.1 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

Granite 4.2 8BIbm

Granite 4.2 8B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 117,964 tokens.

Hy4 previewTencent

Hy4 preview accepts text and returns text. The canonical context window is 1,024,000 tokens. The canonical maximum output is 64,000 tokens.

Gemini Omni 1.1 FlashGoogle

Gemini Omni 1.1 Flash accepts text, images, video and returns video. The canonical context window is 1,048,576 tokens. The canonical maximum output is 57,920 tokens.

Ling 3.0 Flash FinInclusionai

Ling 3.0 Flash Fin accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Qwen3.8 Flash NextAlibaba

Qwen3.8 Flash Next accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 131,072 tokens.

Gemini 3.5 Transcribe LiveGoogle

Gemini 3.5 Transcribe Live accepts audio and returns text.

GLM-5.3-FlashZhipu AI

GLM-5.3-Flash accepts text, images, video, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Qwen3.8 FlashAlibaba

Qwen3.8 Flash accepts text, images, video and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Apodex 1.1 MiniApodex

Apodex 1.1 Mini accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

DeepSeek V4 Flash Vision ExpDeepSeek

DeepSeek V4 Flash Vision Exp accepts text, images and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 384,000 tokens.

Hy-MT2-1.8BTencent

Hy-MT2-1.8B accepts text and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 4,096 tokens.

Hy-MT2-30B-A3BTencent

Hy-MT2-30B-A3B accepts text and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 4,096 tokens.

Hy-MT2-7BTencent

Hy-MT2-7B accepts text and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 4,096 tokens.

Ornith 1.5 35B A3BDeepreinforce

Ornith 1.5 35B A3B accepts text, images and returns text. The canonical context window is 262,144 tokens.

GLM-5.3Zhipu AI

GLM-5.3 accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Qwen3.8 27BAlibaba

Qwen3.8 27B accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Gemini 3.7 FlashGoogle

Gemini 3.7 Flash 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 Flash LatestGoogle

Gemini Flash Latest 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.

Kling 3.0 Omni 720p Image to VideoKling AI

Kling 3.0 Omni 720p Image to Video accepts text, images and returns video.

Kling 3.0 Omni 720p Text to VideoKling AI

Kling 3.0 Omni 720p Text to Video accepts text and returns video.

Kling 3.0 Omni 1080p Image to VideoKling AI

Kling 3.0 Omni 1080p Image to Video accepts text, images and returns video.