Model catalog

o4-miniOpenAI

o4-mini accepts text, images and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 100,000 tokens.

Llama 3.1 Nemotron 70B InstructNvidia

Llama 3.1 Nemotron 70B Instruct accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 8,192 tokens.

GPT-4.1OpenAI

GPT-4.1 accepts text, images, PDFs and returns text. The canonical context window is 1,047,576 tokens. The canonical maximum output is 32,768 tokens.

GPT-4.1 miniOpenAI

GPT-4.1 mini accepts text, images, PDFs and returns text. The canonical context window is 1,047,576 tokens. The canonical maximum output is 32,768 tokens.

Llama 3.3 Nemotron Super 49B v1Nvidia

Llama 3.3 Nemotron Super 49B v1 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 131,072 tokens.

Qwen3 32BAlibaba

Qwen3 32B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 16,384 tokens.

Qwen3 235B-A22BAlibaba

Qwen3 235B-A22B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 16,384 tokens.

Qwen3-Coder 480B-A35B InstructAlibaba

Qwen3-Coder 480B-A35B Instruct accepts text and returns text. The canonical context window is 262,144 tokens. The canonical maximum output is 65,536 tokens.

DeepSeek V3 0324DeepSeek

DeepSeek V3 0324 accepts text and returns text. The canonical context window is 163,840 tokens. The canonical maximum output is 147,456 tokens.

DeepSeek V3 0324DeepSeek

DeepSeek V3 0324 accepts text and returns text. The canonical context window is 163,840 tokens. The canonical maximum output is 163,840 tokens.

o1-proOpenAI

o1-pro accepts text, images and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 100,000 tokens.

Mistral Small 3.1 24BMistral

Mistral Small 3.1 24B accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 16,384 tokens.

QwQ 32BAlibaba

QwQ 32B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

QwQ PlusAlibaba

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

Claude Sonnet 3.7Anthropic

Claude Sonnet 3.7 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 64,000 tokens.

Aion-RP 1.0 (8B)Aion Labs

Aion-RP 1.0 (8B) accepts text and returns text. The canonical context window is 32,768 tokens. The canonical maximum output is 29,491 tokens.

DeepSeek-R1DeepSeek

DeepSeek-R1 accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 32,768 tokens.

MiniMax Text 01 (MiniMax)MiniMax (minimax.io)

MiniMax Text 01 (MiniMax) accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 131,072 tokens.

DeepSeek-V3DeepSeek

DeepSeek-V3 accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

o3-miniOpenAI

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

Llama 3.3 Euryale 70BSao10k

Llama 3.3 Euryale 70B accepts text and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 16,384 tokens.

Phi-4-miniMicrosoft

Phi-4-mini accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

Llama-3.3-70B-InstructMeta

Llama-3.3-70B-Instruct accepts text and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

Nova Pro 1.0Amazon

Nova Pro 1.0 accepts text, images and returns text. The canonical context window is 300,000 tokens. The canonical maximum output is 5,120 tokens.