Model catalog

Vision SmallVispark

Vision Small accepts text, images, audio, video, PDFs and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 65,536 tokens.

GPT-4oOpenAI

GPT-4o accepts text, images, PDFs and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 16,384 tokens.

GPT-4o (2024-05-13)OpenAI

GPT-4o (2024-05-13) accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

Hermes 2 Pro Llama 3 8BNousresearch

Hermes 2 Pro Llama 3 8B accepts text and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 8,192 tokens.

Mixtral 8x22B InstructMistral

Mixtral 8x22B Instruct accepts text, PDFs and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 52,428 tokens.

WizardLM 2 8x22BMicrosoft

WizardLM 2 8x22B accepts text and returns text. The canonical context window is 65,536 tokens. The canonical maximum output is 8,000 tokens.

Qwen-VL MaxAlibaba

Qwen-VL Max accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

Qwen MaxAlibaba

Qwen Max accepts text and returns text. The canonical context window is 32,768 tokens. The canonical maximum output is 8,192 tokens.

BGE Reranker V2 M3Baai

BGE Reranker V2 M3 accepts text and returns text. The canonical context window is 8,192 tokens.

Claude Haiku 3Anthropic

Claude Haiku 3 accepts text, images, PDFs and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 4,096 tokens.

Mistral LargeMistral

Mistral Large accepts text, PDFs and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 102,400 tokens.

BGE M3Baai

BGE M3 accepts text and returns text. The canonical context window is 8,192 tokens.

Qwen-VL PlusAlibaba

Qwen-VL Plus accepts text, images and returns text. The canonical context window is 131,072 tokens. The canonical maximum output is 8,192 tokens.

Qwen PlusAlibaba

Qwen Plus accepts text and returns text. The canonical context window is 1,000,000 tokens. The canonical maximum output is 32,768 tokens.

SonarPerplexity

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

Sonar ProPerplexity

Sonar Pro accepts text, images and returns text. The canonical context window is 200,000 tokens. The canonical maximum output is 8,192 tokens.

Sonar Reasoning ProPerplexity

Sonar Reasoning Pro accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

Mistral EmbedMistral

Mistral Embed accepts text and returns text. The canonical context window is 8,000 tokens. The canonical maximum output is 3,072 tokens.

GPT-4OpenAI

GPT-4 accepts text and returns text. The canonical context window is 8,192 tokens. The canonical maximum output is 8,192 tokens.

GPT-4 TurboOpenAI

GPT-4 Turbo accepts text, images and returns text. The canonical context window is 128,000 tokens. The canonical maximum output is 4,096 tokens.

MythoMax L2 13BGryphe

MythoMax L2 13B accepts text and returns text. The canonical context window is 4,096 tokens. The canonical maximum output is 3,200 tokens.

Weaver (alpha)Mancer

Weaver (alpha) accepts text and returns text. The canonical context window is 8,000 tokens. The canonical maximum output is 6,000 tokens.

ReMM SLERP 13BUndi95

ReMM SLERP 13B accepts text and returns text. The canonical context window is 6,144 tokens. The canonical maximum output is 5,529 tokens.

GPT-3.5-turboOpenAI

GPT-3.5-turbo accepts text and returns text. The canonical context window is 16,385 tokens. The canonical maximum output is 4,096 tokens.