Model catalog

Deep Research Max PreviewGoogle

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

Gemini Deep Research PreviewGoogle

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

GPT-5.4 Image 2OpenAI

GPT-5.4 Image 2 accepts images, text, PDFs and returns images, text. The canonical context window is 272,000 tokens. The canonical maximum output is 128,000 tokens.

GPT-Image-2OpenAI

GPT-Image-2 accepts text, images and returns images.

Kimi K2.6Moonshot AI

Kimi K2.6 accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Hy3 previewTencent

Hy3 preview accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 64,000 tokens.

Qwen3.6 Max PreviewAlibaba

Qwen3.6 Max Preview accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

Grok 4.3xAI

Grok 4.3 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 30,000 tokens.

Qwen3.6 35B-A3BAlibaba

Qwen3.6 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.

Claude Opus 4.7Anthropic

Claude Opus 4.7 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

Grok Build 0.1xAI

Grok Build 0.1 accepts text, images, PDFs and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

Gemini 3.1 Flash TTS PreviewGoogle

Gemini 3.1 Flash TTS Preview accepts text and returns audio. The canonical context window is 8,192 tokens. The canonical maximum output is 16,384 tokens.

Gemini Robotics-ER 1.6 PreviewGoogle

Gemini Robotics-ER 1.6 Preview accepts text, images, video, audio and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 65,536 tokens.

Muse Spark 1.1Meta

Muse Spark 1.1 accepts text, images, PDFs, video and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

GLM-5.1Zhipu AI

GLM-5.1 accepts text and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 131,072 tokens.

Grok Imagine Image QualityxAI

Grok Imagine Image Quality accepts text, images and returns images. The canonical context window is 16,000 tokens.

Gemma 4 26B A4B ITGoogle

Gemma 4 26B A4B IT accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Gemma 4 31B ITGoogle

Gemma 4 31B IT accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Gemma 4 E2B ITGoogle

Gemma 4 E2B IT accepts text, images, audio and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

Gemma 4 E4B ITGoogle

Gemma 4 E4B IT accepts text, images, audio and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

Qwen3.6 PlusAlibaba

Qwen3.6 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.

Step 3.5 Flash 2603StepFun (China)

Step 3.5 Flash 2603 accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

GLM-5V-TurboZhipu AI

GLM-5V-Turbo accepts text, images, video, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 131,072 tokens.

Trinity Large ThinkingArcee Ai

Trinity Large Thinking accepts text and returns text. The canonical context window is 524,288 tokens. The canonical maximum output is 262,144 tokens.