Model catalog

Morph V3 FastMorph

Morph V3 Fast accepts text and returns text. The canonical context window is 81,920 tokens. The canonical maximum output is 38,000 tokens.

Morph V3 LargeMorph

Morph V3 Large accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 131,072 tokens.

Jamba LargeAI21 Labs

Jamba Large accepts text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 4,096 tokens.

ERNIE 4.5 21B A3BBaidu

ERNIE 4.5 21B A3B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,000 tokens.

ERNIE 4.5 VL 424B A47B Baidu

ERNIE 4.5 VL 424B A47B accepts images, text and returns text. The canonical context window is 123,000 tokens. The canonical maximum output is 16,000 tokens.

Mistral Small 3.2Mistral

Mistral Small 3.2 accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 16,384 tokens.

Mistral Small 3.2 24BMistral

Mistral Small 3.2 24B accepts images, text and returns text. The canonical context window is 256,000 tokens. The canonical maximum output is 16,384 tokens.

Gemini 2.5 FlashGoogle

Gemini 2.5 Flash accepts text, images, audio, video, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

Gemini 2.5 Flash-LiteGoogle

Gemini 2.5 Flash-Lite accepts text, images, audio, video, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

Gemini 2.5 ProGoogle

Gemini 2.5 Pro accepts text, images, audio, video, PDFs and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

MiniMax M1 80KMiniMax (minimax.io)

MiniMax M1 80K accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 80,000 tokens.

Magistral SmallMistral

Magistral Small accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

o3-proOpenAI

o3-pro accepts text, images and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 100,000 tokens.

Gemini 2.5 Pro Preview 06-05Google

Gemini 2.5 Pro Preview 06-05 accepts PDFs, images, text, audio and returns text. The canonical context window is 1,048,576 tokens. The canonical maximum output is 65,536 tokens.

Qwen3 Embedding 8BAlibaba

Qwen3 Embedding 8B accepts text and returns text. The canonical context window is 32,768 tokens.

Qwen3 Reranker 8BAlibaba

Qwen3 Reranker 8B accepts text and returns text. The canonical context window is 32,768 tokens.

DeepSeek R1 0528 Qwen3 8BDeepSeek

DeepSeek R1 0528 Qwen3 8B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 32,000 tokens.

DeepSeek R1 0528DeepSeek

DeepSeek R1 0528 accepts text and returns text. The canonical context window is 163,840 tokens. The canonical maximum output is 32,768 tokens.

Claude Opus 4Anthropic

Claude Opus 4 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 32,000 tokens.

Claude Sonnet 4Anthropic

Claude Sonnet 4 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Claude Sonnet 4 (latest)Anthropic

Claude Sonnet 4 (latest) accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Gemini Embedding 001Google

Gemini Embedding 001 accepts text and returns text. The canonical context window is 2,048 tokens. The canonical maximum output is 1 tokens.

Solar Pro 2Upstage

Solar Pro 2 accepts text and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 8,192 tokens.

Mistral Medium 3Mistral

Mistral Medium 3 accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.