Model catalog

Nano Banana ProGoogle

Nano Banana Pro accepts text, images and returns text, images. The canonical context window is 65,536 tokens. The canonical maximum output is 32,768 tokens.

Qwen3.7 MaxAlibaba

Qwen3.7 Max accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 65,536 tokens.

Command A PlusCohere

Command A Plus accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 64,000 tokens.

Gemini 3.5 FlashGoogle

Gemini 3.5 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.

Perceptron Mk1Perceptron

Perceptron Mk1 accepts text, images, video and returns text. The canonical context window is 32,768 tokens. The canonical maximum output is 8,192 tokens.

Gemini 3.1 Flash LiteGoogle

Gemini 3.1 Flash Lite 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.

GPT Realtime WhisperOpenAI

GPT Realtime Whisper accepts audio and returns text. The canonical context window is 16,000 tokens. The canonical maximum output is 2,000 tokens.

CoBuddyBaidu

CoBuddy accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 65,536 tokens.

GPT-5.5 InstantOpenAI

GPT-5.5 Instant accepts text, images, PDFs and returns text. The canonical context window is 400,000 tokens. The canonical maximum output is 128,000 tokens.

Mistral Medium 3.5Mistral

Mistral Medium 3.5 accepts text, images, PDFs and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 209,715 tokens.

Mistral Medium (latest)Mistral

Mistral Medium (latest) accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Mistral Medium 3.5Mistral

Mistral Medium 3.5 accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 262,144 tokens.

Nemotron 3 Nano Omni 30B A3B ReasoningNvidia

Nemotron 3 Nano Omni 30B A3B Reasoning accepts text, images, video, audio and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 65,536 tokens.

Qwen3.6 FlashAlibaba

Qwen3.6 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.

DeepSeek V4 FlashDeepSeek

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

DeepSeek V4 ProDeepSeek

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

DeepSeek V4 Flash 0423DeepSeek

DeepSeek V4 Flash 0423 accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 384,000 tokens.

DeepSeek V4 Pro 0423DeepSeek

DeepSeek V4 Pro 0423 accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 384,000 tokens.

GPT-5.5OpenAI

GPT-5.5 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-5.5 ProOpenAI

GPT-5.5 Pro accepts text, images, PDFs and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

Gemini Embedding 2Google

Gemini Embedding 2 accepts text, images, audio, video, PDFs and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 3,072 tokens.

MiMo-V2.5Xiaomi

MiMo-V2.5 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.

MiMo-V2.5-ProXiaomi

MiMo-V2.5-Pro accepts text and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

Qwen3.6 27BAlibaba

Qwen3.6 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.