Model catalog

MiMo-V2.6-ProXiaomi

MiMo-V2.6-Pro 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.

Grok 4.7xAI

Grok 4.7 accepts text, images, PDFs and returns text. The canonical context window is 500,000 tokens. The canonical maximum output is 500,000 tokens.

MiMo-V2.6-Pro-UltraSpeedXiaomi

MiMo-V2.6-Pro-UltraSpeed 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.

Viv FastVivgrid

Viv Fast accepts text, images and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 256,000 tokens.

ParetoUnbiased

Pareto accepts text, images and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 131,072 tokens.

Qwen3.8 Omni FlashAlibaba

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

Arrow 2Quiverai

Arrow 2 accepts text, images and returns text, images. The canonical context window is 131,072 tokens. The canonical maximum output is 65,536 tokens.

Arrow 2 TelosQuiverai

Arrow 2 Telos accepts text, images and returns text, images. The canonical context window is 1,050,000 tokens. The canonical maximum output is 65,536 tokens.

Step 5 PreviewStepFun (China)

Step 5 Preview accepts text, images, video and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 1,000,000 tokens.

JevTypesafe

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

Schematron V2 SmallInference Net

Schematron V2 Small accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

Schematron V2 TurboInference Net

Schematron V2 Turbo accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 8,192 tokens.

Fugu MaxSakana AI

Fugu Max accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

Fugu Ultra v2Sakana AI

Fugu Ultra v2 accepts text, images, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 128,000 tokens.

DeepSeek V4.1 Flash (2026-09-10)DeepSeek

DeepSeek V4.1 Flash (2026-09-10) accepts text, images and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 384,000 tokens.

Ling 3.0 Flash VLInclusionai

Ling 3.0 Flash VL accepts text, images, video and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

GPT Image 2.5 FlareOpenAI

GPT Image 2.5 Flare accepts text, images and returns images.

GPT Image 2.5 SunburstOpenAI

GPT Image 2.5 Sunburst accepts text, images and returns images.

Mercury 2.5Inception

Mercury 2.5 accepts text and returns text. The canonical context window is 260,000 tokens. The canonical maximum output is 65,536 tokens.

MiniCPM5-2BOpenbmb

MiniCPM5-2B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

GPT-6 AstraOpenAI

GPT-6 Astra 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 Astra (Fast)OpenAI

GPT-6 Astra (Fast) 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 3.0 Flash SanteInclusionai

Ling 3.0 Flash Sante accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 32,768 tokens.

Gemini 3.8 FlashGoogle

Gemini 3.8 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.