Model catalog

DeepSeek V4.1 Flash 1017DeepSeek

DeepSeek V4.1 Flash 1017 accepts text, images and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 384,000 tokens.

Muse Spark OpenMeta

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

Nemotron 3.5 Super VL 120B A12BNvidia

Nemotron 3.5 Super VL 120B A12B accepts text, images, video and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 8,192 tokens.

Jev 1.14Typesafe

Jev 1.14 accepts text and returns text. The canonical context window is 64,000 tokens.

Gemini 4 ArgonGoogle

Gemini 4 Argon 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.

Muse WonderMeta

Muse Wonder 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.

Claude Haiku 5.5Anthropic

Claude Haiku 5.5 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

Drex 2.0Nace Ai

Drex 2.0 accepts text and returns text. The canonical context window is 131,072 tokens.

Mistral Large 4Mistral

Mistral Large 4 accepts text, images and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 262,144 tokens.

Nano Banana 2.1Google

Nano Banana 2.1 accepts text, images, video and returns text, images. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Beam 1.0 501B A23BReflection

Beam 1.0 501B A23B accepts text and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

Grok Imagine Video 1.5 LitexAI

Grok Imagine Video 1.5 Lite accepts text, images and returns video. The canonical context window is 1,024 tokens.

GPT-6.1 SolOpenAI

GPT-6.1 Sol accepts text, images, PDFs and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

Ling 3.1 FlashInclusionai

Ling 3.1 Flash accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Liquid d1Liquid

Liquid d1 accepts text and returns text. The canonical context window is 65,536 tokens.

Claude Sonnet 5.5Anthropic

Claude Sonnet 5.5 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

Drex 1.5Nace Ai

Drex 1.5 accepts text and returns text. The canonical context window is 139,264 tokens.

LongCat-2.5-PreviewMeituan

LongCat-2.5-Preview accepts text, images and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Qwen 3.8 Max PrimeAlibaba

Qwen 3.8 Max Prime accepts text, images, video and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Claude Opus 5.5Anthropic

Claude Opus 5.5 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

Ember-1Fireworks

Ember-1 accepts text, images and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

GPT-6 LunaOpenAI

GPT-6 Luna accepts text, images, PDFs and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-6 SolOpenAI

GPT-6 Sol accepts text, images, PDFs and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

MiMo-V2.6-FlashXiaomi

MiMo-V2.6-Flash accepts text, images, audio, video and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.