Model catalog

Gemini Flash-Lite LatestGoogle

Gemini Flash-Lite 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.

Laguna S 2.1Poolside

Laguna S 2.1 accepts text and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 32,768 tokens.

Macaron V1 TallMindlab

Macaron V1 Tall accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Macaron V1 VentiMindlab

Macaron V1 Venti accepts text and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

Qwen3.8 Max PreviewAlibaba

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

Kimi K3Moonshot AI

Kimi K3 accepts text, images, video and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 131,072 tokens.

InklingThinking Machines

Inkling accepts text, images, audio and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 1,048,576 tokens.

Qwen3.7 FlashAlibaba

Qwen3.7 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.

GPT-5.6 LunaOpenAI

GPT-5.6 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-5.6 SolOpenAI

GPT-5.6 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.

GPT-5.6 TerraOpenAI

GPT-5.6 Terra accepts text, images, PDFs and returns text. The canonical context window is 1,050,000 tokens. The canonical maximum output is 128,000 tokens.

Grok 4.5xAI

Grok 4.5 accepts text, images and returns text. The canonical context window is 500,000 tokens. The canonical maximum output is 500,000 tokens.

Aion-3.0Aion Labs

Aion-3.0 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

Aion-3.0-MiniAion Labs

Aion-3.0-Mini accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,768 tokens.

GPT-Realtime-2.1OpenAI

GPT-Realtime-2.1 accepts text, audio, images and returns text, audio. The canonical context window is 128,000 tokens. The canonical maximum output is 32,000 tokens.

Hy3Tencent

Hy3 accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 128,000 tokens.

Laguna XS 2.1Poolside

Laguna XS 2.1 accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Claude Sonnet 5Anthropic

Claude Sonnet 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.

Gemini Omni Flash PreviewGoogle

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

LongCat-2.0Meituan

LongCat-2.0 accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

Nano Banana 2 LiteGoogle

Nano Banana 2 Lite accepts text, images and returns text, images. The canonical context window is 65,536 tokens. The canonical maximum output is 4,096 tokens.

Seed 2.1 ProBytedance Seed

Seed 2.1 Pro accepts text, images, video and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

Seed 2.1 TurboBytedance Seed

Seed 2.1 Turbo accepts text, images, video and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.

Seed CharacterBytedance Seed

Seed Character accepts text, images, video and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 256,000 tokens.