Skip to content
LMC Feed-Models, Papers, Benchmarks. Zero Fluff.Live

模态探索器

按输入和输出模态分析406个AI模型。查看哪些模型接受文本、图像、音频或视频输入以及它们产生什么输出。发现支持视觉的模型、图像生成器和真正的多模态AI。

模型总数

406

输入模态

5

输出模态

4

真正多模态

13

输入模态分布

text45.4%
image27.4%
file16.9%
video6.5%
audio3.8%
LMMarketCap.com

输出模态分布

text92.4%
image4.3%
video2.4%
audio1.0%
LMMarketCap.com

输入模态

模型可以接受哪些类型的数据作为输入。

text
405
image
245
file
151
video
58
audio
34
模态模型数量占比
text
405100%
image
24560%
file
15137%
video
5814%
audio
348%

输出模态

模型可以产生哪些类型的数据作为输出。

text
387
image
18
video
10
audio
4
模态模型数量占比
text
38795%
image
184%
video
102%
audio
41%

模态流 (输入 → 输出)

所有模型中最常见的输入到输出模态组合。

输入模态输出模态数量占比
text
text
14335%
fileimagetext
text
11127%
imagetext
text
4812%
imagetextvideo
text
307%
audiofileimagetextvideo
text
256%
filetext
text
92%
imagetext
video
82%
imagetext
imagetext
61%
text
image
51%
imagetext
image
41%
audioimagetext
text
31%
fileimagetext
imagetext
31%
audioimagetextvideo
text
20%
imagetext
audiotext
20%
audiotext
audiotext
20%
fileimagetextvideo
text
10%
audiofiletext
text
10%
audiofileimagetext
text
10%
image
video
10%
text
video
10%

最通用的模型

按总独特模态数排名，模态支持最多样化的前20个模型。

模型输入模态输出模态总计独特
Gemini 2.5 Flash
audiofileimagetextvideo
text
5
Gemini 2.5 Flash (batch)
audiofileimagetextvideo
text
5
Gemini 2.5 Flash Lite
audiofileimagetextvideo
text
5
Gemini 2.5 Flash Lite (batch)
audiofileimagetextvideo
text
5
Gemini 2.5 Pro
audiofileimagetextvideo
text
5
Gemini 2.5 Pro (batch)
audiofileimagetextvideo
text
5
Gemini 2.5 Pro Preview 05-06
audiofileimagetextvideo
text
5
Gemini 3 Flash Preview
audiofileimagetextvideo
text
5
Gemini 3 Flash Preview (batch)
audiofileimagetextvideo
text
5
Gemini 3.1 Flash Lite
audiofileimagetextvideo
text
5
Gemini 3.1 Flash Lite (batch)
audiofileimagetextvideo
text
5
Gemini 3.1 Flash Lite Preview
audiofileimagetextvideo
text
5
Gemini 3.1 Pro Preview
audiofileimagetextvideo
text
5
Gemini 3.1 Pro Preview (batch)
audiofileimagetextvideo
text
5
Gemini 3.1 Pro Preview Custom Tools
audiofileimagetextvideo
text
5
Gemini 3.5 Flash
audiofileimagetextvideo
text
5
Gemini 3.5 Flash (batch)
audiofileimagetextvideo
text
5
Gemini 3.5 Flash Lite
audiofileimagetextvideo
text
5
Gemini 3.5 Flash Lite (batch)
audiofileimagetextvideo
text
5
Gemini 3.6 Flash
audiofileimagetextvideo
text
5

支持视觉的模型

245个接受图像输入的模型，按字母顺序排列。

模型免费?上下文
Adobe Firefly 3Adobe否0K
Anthropic Claude Haiku Latest~anthropic否200K
Anthropic Claude Sonnet Latest~anthropic否1M
Claude 3 HaikuAnthropic否200K
Claude Fable 5Anthropic否1M
Claude Fable 5 (batch)Anthropic否1M
Claude Fable Latest~anthropic否1M
Claude Haiku 4.5Anthropic否200K
Claude Haiku 4.5 (batch)Anthropic否200K
Claude Opus 4Anthropic否200K
Claude Opus 4.1Anthropic否200K
Claude Opus 4.1 (batch)Anthropic否200K
Claude Opus 4.5Anthropic否200K
Claude Opus 4.5 (batch)Anthropic否200K
Claude Opus 4.6Anthropic否1M
Claude Opus 4.6 (batch)Anthropic否1M
Claude Opus 4.7Anthropic否1M
Claude Opus 4.7 (batch)Anthropic否1M
Claude Opus 4.7 (Fast)Anthropic否1M
Claude Opus 4.8Anthropic否1M
Claude Opus 4.8 (batch)Anthropic否1M
Claude Opus 4.8 (Fast)Anthropic否1M
Claude Opus 5Anthropic否1M
Claude Opus 5 (batch)Anthropic否1M
Claude Opus 5 (Fast)Anthropic否1M
Claude Opus Latest~anthropic否1M
Claude Sonnet 4Anthropic否1M
Claude Sonnet 4.5Anthropic否1M
Claude Sonnet 4.5 (batch)Anthropic否1M
Claude Sonnet 4.6Anthropic否1M
Claude Sonnet 4.6 (batch)Anthropic否1M
Claude Sonnet 5Anthropic否1M
Claude Sonnet 5 (batch)Anthropic否1M
ERNIE 4.5 VL 424B A47B Baidu否123K
Fugu Ultrasakana否1M
Gemini 2.5 FlashGoogle否1.0M
Gemini 2.5 Flash (batch)Google否1.0M
Gemini 2.5 Flash LiteGoogle否1.0M
Gemini 2.5 Flash Lite (batch)Google否1.0M
Gemini 2.5 ProGoogle否1.0M
Gemini 2.5 Pro (batch)Google否1.0M
Gemini 2.5 Pro Preview 05-06Google否1.0M
Gemini 2.5 Pro Preview 06-05Google否1.0M
Gemini 3 Flash PreviewGoogle否1.0M
Gemini 3 Flash Preview (batch)Google否1.0M
Gemini 3.1 Flash LiteGoogle否1.0M
Gemini 3.1 Flash Lite (batch)Google否1.0M
Gemini 3.1 Flash Lite PreviewGoogle否1.0M
Gemini 3.1 Pro PreviewGoogle否1.0M
Gemini 3.1 Pro Preview (batch)Google否1.0M
Gemini 3.1 Pro Preview Custom ToolsGoogle否1.0M
Gemini 3.5 FlashGoogle否1.0M
Gemini 3.5 Flash (batch)Google否1.0M
Gemini 3.5 Flash LiteGoogle否1.0M
Gemini 3.5 Flash Lite (batch)Google否1.0M
Gemini 3.6 FlashGoogle否1.0M
Gemini 3.6 Flash (batch)Google否1.0M
Gemma 3 12BGoogle否131.1K
Gemma 3 27BGoogle否262.1K
Gemma 3 4BGoogle否131.1K
Gemma 4 26B A4B Google否262.1K
Gemma 4 26B A4B (free)Google是262.1K
Gemma 4 31BGoogle否262.1K
Gemma 4 31B (free)Google是262.1K
GLM 4.5VZhipu AI否65.5K
GLM 4.6VZhipu AI否131.1K
GLM 5V TurboZhipu AI否202.8K
Google Gemini Flash Latest~google否1.0M
Google Gemini Pro Latest~google否1.0M
GPT Chat LatestOpenAI否400K
GPT-4 TurboOpenAI否128K
GPT-4 Turbo (batch)OpenAI否128K
GPT-4.1OpenAI否1.0M
GPT-4.1 (batch)OpenAI否1.0M
GPT-4.1 MiniOpenAI否1.0M
GPT-4.1 Mini (batch)OpenAI否1.0M
GPT-4.1 NanoOpenAI否1.0M
GPT-4.1 Nano (batch)OpenAI否1.0M
GPT-4oOpenAI否128K
GPT-4o (2024-05-13)OpenAI否128K
GPT-4o (2024-08-06)OpenAI否128K
GPT-4o (2024-11-20)OpenAI否128K
GPT-4o (batch)OpenAI否128K
GPT-4o-miniOpenAI否128K
GPT-4o-mini (2024-07-18)OpenAI否128K
GPT-4o-mini (batch)OpenAI否128K
GPT-5OpenAI否400K
GPT-5 (batch)OpenAI否400K
GPT-5 Codex (batch)OpenAI否400K
GPT-5 ImageOpenAI否400K
GPT-5 Image MiniOpenAI否400K
GPT-5 MiniOpenAI否400K
GPT-5 Mini (batch)OpenAI否400K
GPT-5 NanoOpenAI否400K
GPT-5 Nano (batch)OpenAI否400K
GPT-5 ProOpenAI否400K
GPT-5 Pro (batch)OpenAI否400K
GPT-5.1OpenAI否400K
GPT-5.1 (batch)OpenAI否400K
GPT-5.1-CodexOpenAI否400K
GPT-5.1-Codex-MaxOpenAI否400K
GPT-5.1-Codex-MiniOpenAI否400K
GPT-5.2OpenAI否400K
GPT-5.2 (batch)OpenAI否400K
GPT-5.2 ChatOpenAI否128K
GPT-5.2 ProOpenAI否400K
GPT-5.2 Pro (batch)OpenAI否400K
GPT-5.2-CodexOpenAI否400K
GPT-5.3 ChatOpenAI否128K
GPT-5.3-CodexOpenAI否400K
GPT-5.4OpenAI否1.1M
GPT-5.4 (batch)OpenAI否1.1M
GPT-5.4 Image 2OpenAI否272K
GPT-5.4 MiniOpenAI否400K
GPT-5.4 Mini (batch)OpenAI否400K
GPT-5.4 NanoOpenAI否400K
GPT-5.4 Nano (batch)OpenAI否400K
GPT-5.4 ProOpenAI否1.1M
GPT-5.4 Pro (batch)OpenAI否1.1M
GPT-5.5OpenAI否1.1M
GPT-5.5 (batch)OpenAI否1.1M
GPT-5.5 ProOpenAI否1.1M
GPT-5.5 Pro (batch)OpenAI否1.1M
GPT-5.6 LunaOpenAI否1.1M
GPT-5.6 Luna (batch)OpenAI否1.1M
GPT-5.6 Luna ProOpenAI否1.1M
GPT-5.6 Luna Pro (batch)OpenAI否1.1M
GPT-5.6 SolOpenAI否1.1M
GPT-5.6 Sol (batch)OpenAI否1.1M
GPT-5.6 Sol ProOpenAI否1.1M
GPT-5.6 Sol Pro (batch)OpenAI否1.1M
GPT-5.6 TerraOpenAI否1.1M
GPT-5.6 Terra (batch)OpenAI否1.1M
GPT-5.6 Terra ProOpenAI否1.1M
GPT-5.6 Terra Pro (batch)OpenAI否1.1M
Grok 4.20xAI否2M
Grok 4.20 Multi-AgentxAI否2M
Grok 4.3xAI否1M
Grok 4.5xAI否500K
Grok Build 0.1xAI否256K
Grok Latest~x-ai否500K
Inklingthinkingmachines否1.0M
Inkling (batch)thinkingmachines否524.3K
Inkling Smallthinkingmachines否524.3K
Kimi K2.5Moonshot AI否262.1K
Kimi K2.6Moonshot AI否262.1K
Kimi K2.7 CodeMoonshot AI否262.1K
Kimi K2.7 Code (batch)Moonshot AI否262.1K
Kimi K3Moonshot AI否1.0M
Kling 1.6Kuaishou否0K
Leonardo PhoenixLeonardo AI否0K
Llama 4 MaverickMeta否1.0M
Llama 4 ScoutMeta否1.3M
Llama Guard 4 12BMeta否1.0M
LTX-Video 2Lightricks是0K
Luma Dream MachineLuma AI否0K
Lyria 3 Clip PreviewGoogle是1.0M
Lyria 3 Pro PreviewGoogle是1.0M
Midjourney v6.1Midjourney否0K
MiMo-V2.5Xiaomi否1.1M
MiniMax M3MiniMax否1.0M
MiniMax M3 (batch)MiniMax否524.3K
MiniMax Video-01MiniMax否0K
MiniMax-01MiniMax否1.0M
Ministral 3 14B 2512Mistral AI否262.1K
Ministral 3 3B 2512Mistral AI否131.1K
Ministral 3 8B 2512Mistral AI否262.1K
Mistral Large 3 2512Mistral AI否262.1K
Mistral Medium 3Mistral AI否131.1K
Mistral Medium 3.1Mistral AI否131.1K
Mistral Medium 3.5Mistral AI否262.1K
Mistral Small 3.1 24BMistral AI否128K
Mistral Small 3.2 24BMistral AI否256K
Mistral Small 4Mistral AI否262.1K
MoonshotAI Kimi Latest~moonshotai否1.0M
Muse Spark 1.1meta否1.0M
Muse Spark 1.2meta否1.0M
Nano Banana (Gemini 2.5 Flash Image)Google否32.8K
Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google否65.5K
Nano Banana 2 (Gemini 3.1 Flash Image)Google否131.1K
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google否65.5K
Nano Banana Pro (Gemini 3 Pro Image Preview)Google否65.5K
Nano Banana Pro (Gemini 3 Pro Image)Google否131.1K
Nemotron 3 Nano Omni (free)NVIDIA是256K
Nemotron 3.5 Content Safety (free)NVIDIA是128K
Nemotron Nano 12B 2 VL (free)NVIDIA是128K
Nova 2 LiteAmazon否1M
Nova Lite 1.0Amazon否300K
Nova Premier 1.0Amazon否1M
Nova Pro 1.0Amazon否300K
o1OpenAI否200K
o1 (batch)OpenAI否200K
o1-proOpenAI否200K
o1-pro (batch)OpenAI否200K
o3OpenAI否200K
o3 (batch)OpenAI否200K
o3 ProOpenAI否200K
o3 Pro (batch)OpenAI否200K
o4 MiniOpenAI否200K
o4 Mini (batch)OpenAI否200K
o4 Mini HighOpenAI否200K
o4 Mini High (batch)OpenAI否200K
OpenAI GPT Latest~openai否1.1M
OpenAI GPT Mini Latest~openai否400K
Perceptron Mk1perceptron否32.8K
Pika 2.0Pika否0K
Qwen2.5 VL 72B InstructAlibaba否128K
Qwen3 VL 235B A22B InstructAlibaba否262.1K
Qwen3 VL 235B A22B ThinkingAlibaba否131.1K
Qwen3 VL 30B A3B InstructAlibaba否262.1K
Qwen3 VL 30B A3B ThinkingAlibaba否262.1K
Qwen3 VL 32B InstructAlibaba否131.1K
Qwen3 VL 8B InstructAlibaba否262.1K
Qwen3 VL 8B ThinkingAlibaba否131.1K
Qwen3.5 397B A17BAlibaba否262.1K
Qwen3.5 Plus 2026-02-15Alibaba否1M
Qwen3.5 Plus 2026-04-20Alibaba否1M
Qwen3.5-122B-A10BAlibaba否262.1K
Qwen3.5-27BAlibaba否262.1K
Qwen3.5-35B-A3BAlibaba否262.1K
Qwen3.5-9BAlibaba否262.1K
Qwen3.5-FlashAlibaba否1M
Qwen3.6 27BAlibaba否262.1K
Qwen3.6 35B A3BAlibaba否262.1K
Qwen3.6 FlashAlibaba否1M
Qwen3.6 PlusAlibaba否1M
Qwen3.7 FlashAlibaba否1M
Qwen3.7 PlusAlibaba否1M
Qwen3.8 MaxAlibaba否1M
Reka Edgerekaai否16.4K
Runway Gen-3 AlphaRunway否0K
Seed 1.6ByteDance否262.1K
Seed 1.6 FlashByteDance否262.1K
Seed-2.0-LiteByteDance否262.1K
Seed-2.0-MiniByteDance否262.1K
SonarPerplexity否127.1K
Sonar ProPerplexity否200K
Sonar Pro SearchPerplexity否200K
Sonar Reasoning ProPerplexity否128K
SoraOpenAI否0K
Stable Diffusion 3.5Stability AI否0K
Stable Video DiffusionStability AI否0K
Step 3.7 FlashStepFun否262.1K
UI-TARS 7B ByteDance否128K
Veo 2Google否0K

图像生成器

18个可以生成图像输出的模型。

模型免费?
Adobe Firefly 3Adobe否
DALL-E 3OpenAI否
FLUX.1 ProBlack Forest Labs否
GPT-5 ImageOpenAI否
GPT-5 Image MiniOpenAI否
GPT-5.4 Image 2OpenAI否
Ideogram 2.0Ideogram否
Imagen 3Google否
Leonardo PhoenixLeonardo AI否
Midjourney v6.1Midjourney否
Nano Banana (Gemini 2.5 Flash Image)Google否
Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google否
Nano Banana 2 (Gemini 3.1 Flash Image)Google否
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google否
Nano Banana Pro (Gemini 3 Pro Image Preview)Google否
Nano Banana Pro (Gemini 3 Pro Image)Google否
Recraft V3Recraft否
Stable Diffusion 3.5Stability AI否

探索更多

深入了解多模态AI、视觉模型或浏览所有探索器。

全部探索器多模态AI模型支持视觉的AI模型
Frequently Asked Questions

Modalities refer to the types of data an AI model can process as input or generate as output. Common input modalities include text, images, and audio. Output modalities include text generation, image creation, code, and structured data like JSON.

A multimodal AI model can process and generate multiple types of data - for example, accepting both text and images as input. Models like GPT-4o, Claude 3.5, and Gemini 2.0 are multimodal, supporting text, image, and sometimes audio inputs.

Our tracker shows that a growing majority of new AI models support vision (image) input. Most top-tier models from OpenAI, Anthropic, Google, and Meta now accept image inputs alongside text, making vision a near-standard capability.

AI Model Modality Explorer - Input & Output Analysis | LM Market Cap