All collections

COLLECTION

AI Models with Vision: Multimodal LLMs for Image Understanding

分析图片、文档与图表，并以文本回答视觉问题的多模态模型。

Open in model catalog Compare models

295 models in this collection. Preview models show catalog availability; open a model to check its gateway and provider details.

295 models

Pareto 26.10 Previewunbiased/pareto-26.10-previewContext1.05MInput$0.8/MOutput$3.2/M

OpenAI: GPT-6.1 Sol Proopenai/gpt-6.1-sol-proContext1.05MInput$2/MOutput$10/M

OpenAI: GPT-6.1 Solopenai/gpt-6.1-solContext1.05MInput$2/MOutput$10/M

Anthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5Context1MInput$2/MOutput$10/M

Anthropic: Claude Sonnet 5.5 (batch)anthropic/claude-sonnet-5.5:batchContext1MInput$1/MOutput$5/M

TypeSafe: Jev Routertypesafe/jev-routerContext1MInputVariableOutputVariable

Perceptron: Perceptron Mk1.5perceptron/perceptron-mk1.5Context36.86KInput$0.15/MOutput$1.5/M

Fireworks: Ember-1fireworks/ember-1Context1.05MInput$3/MOutput$15/M

Qwen: Qwen3.8 Max Primeqwen/qwen3.8-max-primeContext1MInput$4/MOutput$12/M

Space Bunny Alphastealth/space-bunny-alphaContext1MInput$0/MOutput$0/M

Cohere: Command A+cohere/command-a-plusContext192KInput$0.3/MOutput$1.5/M

OpenAI: GPT-6 Luna Proopenai/gpt-6-luna-proContext1.05MInput$0.1/MOutput$0.5/M

How models enter this collection

Membership requires declared image input and text output; visual benchmark quality is not inferred.

Membership comes from public reference metadata. CLSSAI callability is checked against its public directory.