Model catalog

GPT-5.2 ProOpenAI

GPT-5.2 Pro accepts text, images and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

AutoGLM Phone 9B MultilingualZhipu AI

AutoGLM Phone 9B Multilingual accepts text, images and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 65,536 tokens.

Devstral 2Mistral

Devstral 2 accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Devstral Small 2Mistral

Devstral Small 2 accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

GLM-4.6VZhipu AI

GLM-4.6V accepts text, images, video and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 32,768 tokens.

GLM-4.6V-FlashZhipu AI

GLM-4.6V-Flash accepts text, images, video and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 32,768 tokens.

Relace SearchRelace

Relace Search accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 128,000 tokens.

Kling 2.6 Pro Image to VideoKling AI

Kling 2.6 Pro Image to Video accepts text, images and returns video.

Kling 2.6 Pro Text to VideoKling AI

Kling 2.6 Pro Text to Video accepts text and returns video.

Kling Image O1Kling AI

Kling Image O1 accepts text, images and returns images.

Kling O1 Video to Video ReferenceKling AI

Kling O1 Video to Video Reference accepts text, video and returns video.

Kling Video O1 Image to VideoKling AI

Kling Video O1 Image to Video accepts text, images and returns video.

Kling Video O1 Reference to VideoKling AI

Kling Video O1 Reference to Video accepts text and returns video.

Kling Video O1 Video to Video EditKling AI

Kling Video O1 Video to Video Edit accepts text, video and returns video.

Devstral 2 (latest)Mistral

Devstral 2 (latest) accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Ministral 3 3BMistral

Ministral 3 3B accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Ministral 3 3B 2512Mistral

Ministral 3 3B 2512 accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 104,857 tokens.

Ministral 3 8BMistral

Ministral 3 8B accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Ministral 3 8B 2512Mistral

Ministral 3 8B 2512 accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 209,715 tokens.

Ministral 3 14BMistral

Ministral 3 14B accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Ministral 3 14B 2512Mistral

Ministral 3 14B 2512 accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 209,715 tokens.

Ministral 14BMistral

Ministral 14B accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Mistral Large 3Mistral

Mistral Large 3 accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Nova 2 LiteAmazon

Nova 2 Lite accepts text, images, video, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 65,536 tokens.