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

Modality Explorer

Analyze 406 AI models by their input and output modalities. See which models accept text, images, audio, or video - and what they produce. Discover vision-capable models, image generators, and true multimodal AI.

Total Models

406

Input Modalities

5

Output Modalities

4

True Multimodal

13

Input Modality Distribution

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

Output Modality Distribution

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

Input Modalities

What types of data can models accept as input.

text
405
image
245
file
151
video
58
audio
34
ModalityModel Count% of Total
text
405100%
image
24560%
file
15137%
video
5814%
audio
348%

Output Modalities

What types of data can models produce as output.

text
387
image
18
video
10
audio
4
ModalityModel Count% of Total
text
38795%
image
184%
video
102%
audio
41%

Modality Flow (Input → Output)

The most common input-to-output modality combinations across all models.

Input ModalitiesOutput ModalitiesCount% of Total
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%

Most Versatile Models

Top 20 models with the most diverse modality support, ranked by total unique modalities.

ModelInput ModalitiesOutput ModalitiesTotal Unique
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

Vision-Capable Models

245 models that accept images as input, sorted alphabetically.

ModelFree?Context
Adobe Firefly 3AdobeNo0K
Anthropic Claude Haiku Latest~anthropicNo200K
Anthropic Claude Sonnet Latest~anthropicNo1M
Claude 3 HaikuAnthropicNo200K
Claude Fable 5AnthropicNo1M
Claude Fable 5 (batch)AnthropicNo1M
Claude Fable Latest~anthropicNo1M
Claude Haiku 4.5AnthropicNo200K
Claude Haiku 4.5 (batch)AnthropicNo200K
Claude Opus 4AnthropicNo200K
Claude Opus 4.1AnthropicNo200K
Claude Opus 4.1 (batch)AnthropicNo200K
Claude Opus 4.5AnthropicNo200K
Claude Opus 4.5 (batch)AnthropicNo200K
Claude Opus 4.6AnthropicNo1M
Claude Opus 4.6 (batch)AnthropicNo1M
Claude Opus 4.7AnthropicNo1M
Claude Opus 4.7 (batch)AnthropicNo1M
Claude Opus 4.7 (Fast)AnthropicNo1M
Claude Opus 4.8AnthropicNo1M
Claude Opus 4.8 (batch)AnthropicNo1M
Claude Opus 4.8 (Fast)AnthropicNo1M
Claude Opus 5AnthropicNo1M
Claude Opus 5 (batch)AnthropicNo1M
Claude Opus 5 (Fast)AnthropicNo1M
Claude Opus Latest~anthropicNo1M
Claude Sonnet 4AnthropicNo1M
Claude Sonnet 4.5AnthropicNo1M
Claude Sonnet 4.5 (batch)AnthropicNo1M
Claude Sonnet 4.6AnthropicNo1M
Claude Sonnet 4.6 (batch)AnthropicNo1M
Claude Sonnet 5AnthropicNo1M
Claude Sonnet 5 (batch)AnthropicNo1M
ERNIE 4.5 VL 424B A47B BaiduNo123K
Fugu UltrasakanaNo1M
Gemini 2.5 FlashGoogleNo1.0M
Gemini 2.5 Flash (batch)GoogleNo1.0M
Gemini 2.5 Flash LiteGoogleNo1.0M
Gemini 2.5 Flash Lite (batch)GoogleNo1.0M
Gemini 2.5 ProGoogleNo1.0M
Gemini 2.5 Pro (batch)GoogleNo1.0M
Gemini 2.5 Pro Preview 05-06GoogleNo1.0M
Gemini 2.5 Pro Preview 06-05GoogleNo1.0M
Gemini 3 Flash PreviewGoogleNo1.0M
Gemini 3 Flash Preview (batch)GoogleNo1.0M
Gemini 3.1 Flash LiteGoogleNo1.0M
Gemini 3.1 Flash Lite (batch)GoogleNo1.0M
Gemini 3.1 Flash Lite PreviewGoogleNo1.0M
Gemini 3.1 Pro PreviewGoogleNo1.0M
Gemini 3.1 Pro Preview (batch)GoogleNo1.0M
Gemini 3.1 Pro Preview Custom ToolsGoogleNo1.0M
Gemini 3.5 FlashGoogleNo1.0M
Gemini 3.5 Flash (batch)GoogleNo1.0M
Gemini 3.5 Flash LiteGoogleNo1.0M
Gemini 3.5 Flash Lite (batch)GoogleNo1.0M
Gemini 3.6 FlashGoogleNo1.0M
Gemini 3.6 Flash (batch)GoogleNo1.0M
Gemma 3 12BGoogleNo131.1K
Gemma 3 27BGoogleNo262.1K
Gemma 3 4BGoogleNo131.1K
Gemma 4 26B A4B GoogleNo262.1K
Gemma 4 26B A4B (free)GoogleYes262.1K
Gemma 4 31BGoogleNo262.1K
Gemma 4 31B (free)GoogleYes262.1K
GLM 4.5VZhipu AINo65.5K
GLM 4.6VZhipu AINo131.1K
GLM 5V TurboZhipu AINo202.8K
Google Gemini Flash Latest~googleNo1.0M
Google Gemini Pro Latest~googleNo1.0M
GPT Chat LatestOpenAINo400K
GPT-4 TurboOpenAINo128K
GPT-4 Turbo (batch)OpenAINo128K
GPT-4.1OpenAINo1.0M
GPT-4.1 (batch)OpenAINo1.0M
GPT-4.1 MiniOpenAINo1.0M
GPT-4.1 Mini (batch)OpenAINo1.0M
GPT-4.1 NanoOpenAINo1.0M
GPT-4.1 Nano (batch)OpenAINo1.0M
GPT-4oOpenAINo128K
GPT-4o (2024-05-13)OpenAINo128K
GPT-4o (2024-08-06)OpenAINo128K
GPT-4o (2024-11-20)OpenAINo128K
GPT-4o (batch)OpenAINo128K
GPT-4o-miniOpenAINo128K
GPT-4o-mini (2024-07-18)OpenAINo128K
GPT-4o-mini (batch)OpenAINo128K
GPT-5OpenAINo400K
GPT-5 (batch)OpenAINo400K
GPT-5 Codex (batch)OpenAINo400K
GPT-5 ImageOpenAINo400K
GPT-5 Image MiniOpenAINo400K
GPT-5 MiniOpenAINo400K
GPT-5 Mini (batch)OpenAINo400K
GPT-5 NanoOpenAINo400K
GPT-5 Nano (batch)OpenAINo400K
GPT-5 ProOpenAINo400K
GPT-5 Pro (batch)OpenAINo400K
GPT-5.1OpenAINo400K
GPT-5.1 (batch)OpenAINo400K
GPT-5.1-CodexOpenAINo400K
GPT-5.1-Codex-MaxOpenAINo400K
GPT-5.1-Codex-MiniOpenAINo400K
GPT-5.2OpenAINo400K
GPT-5.2 (batch)OpenAINo400K
GPT-5.2 ChatOpenAINo128K
GPT-5.2 ProOpenAINo400K
GPT-5.2 Pro (batch)OpenAINo400K
GPT-5.2-CodexOpenAINo400K
GPT-5.3 ChatOpenAINo128K
GPT-5.3-CodexOpenAINo400K
GPT-5.4OpenAINo1.1M
GPT-5.4 (batch)OpenAINo1.1M
GPT-5.4 Image 2OpenAINo272K
GPT-5.4 MiniOpenAINo400K
GPT-5.4 Mini (batch)OpenAINo400K
GPT-5.4 NanoOpenAINo400K
GPT-5.4 Nano (batch)OpenAINo400K
GPT-5.4 ProOpenAINo1.1M
GPT-5.4 Pro (batch)OpenAINo1.1M
GPT-5.5OpenAINo1.1M
GPT-5.5 (batch)OpenAINo1.1M
GPT-5.5 ProOpenAINo1.1M
GPT-5.5 Pro (batch)OpenAINo1.1M
GPT-5.6 LunaOpenAINo1.1M
GPT-5.6 Luna (batch)OpenAINo1.1M
GPT-5.6 Luna ProOpenAINo1.1M
GPT-5.6 Luna Pro (batch)OpenAINo1.1M
GPT-5.6 SolOpenAINo1.1M
GPT-5.6 Sol (batch)OpenAINo1.1M
GPT-5.6 Sol ProOpenAINo1.1M
GPT-5.6 Sol Pro (batch)OpenAINo1.1M
GPT-5.6 TerraOpenAINo1.1M
GPT-5.6 Terra (batch)OpenAINo1.1M
GPT-5.6 Terra ProOpenAINo1.1M
GPT-5.6 Terra Pro (batch)OpenAINo1.1M
Grok 4.20xAINo2M
Grok 4.20 Multi-AgentxAINo2M
Grok 4.3xAINo1M
Grok 4.5xAINo500K
Grok Build 0.1xAINo256K
Grok Latest~x-aiNo500K
InklingthinkingmachinesNo1.0M
Inkling (batch)thinkingmachinesNo524.3K
Inkling SmallthinkingmachinesNo524.3K
Kimi K2.5Moonshot AINo262.1K
Kimi K2.6Moonshot AINo262.1K
Kimi K2.7 CodeMoonshot AINo262.1K
Kimi K2.7 Code (batch)Moonshot AINo262.1K
Kimi K3Moonshot AINo1.0M
Kling 1.6KuaishouNo0K
Leonardo PhoenixLeonardo AINo0K
Llama 4 MaverickMetaNo1.0M
Llama 4 ScoutMetaNo1.3M
Llama Guard 4 12BMetaNo1.0M
LTX-Video 2LightricksYes0K
Luma Dream MachineLuma AINo0K
Lyria 3 Clip PreviewGoogleYes1.0M
Lyria 3 Pro PreviewGoogleYes1.0M
Midjourney v6.1MidjourneyNo0K
MiMo-V2.5XiaomiNo1.1M
MiniMax M3MiniMaxNo1.0M
MiniMax M3 (batch)MiniMaxNo524.3K
MiniMax Video-01MiniMaxNo0K
MiniMax-01MiniMaxNo1.0M
Ministral 3 14B 2512Mistral AINo262.1K
Ministral 3 3B 2512Mistral AINo131.1K
Ministral 3 8B 2512Mistral AINo262.1K
Mistral Large 3 2512Mistral AINo262.1K
Mistral Medium 3Mistral AINo131.1K
Mistral Medium 3.1Mistral AINo131.1K
Mistral Medium 3.5Mistral AINo262.1K
Mistral Small 3.1 24BMistral AINo128K
Mistral Small 3.2 24BMistral AINo256K
Mistral Small 4Mistral AINo262.1K
MoonshotAI Kimi Latest~moonshotaiNo1.0M
Muse Spark 1.1metaNo1.0M
Muse Spark 1.2metaNo1.0M
Nano Banana (Gemini 2.5 Flash Image)GoogleNo32.8K
Nano Banana 2 (Gemini 3.1 Flash Image Preview)GoogleNo65.5K
Nano Banana 2 (Gemini 3.1 Flash Image)GoogleNo131.1K
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)GoogleNo65.5K
Nano Banana Pro (Gemini 3 Pro Image Preview)GoogleNo65.5K
Nano Banana Pro (Gemini 3 Pro Image)GoogleNo131.1K
Nemotron 3 Nano Omni (free)NVIDIAYes256K
Nemotron 3.5 Content Safety (free)NVIDIAYes128K
Nemotron Nano 12B 2 VL (free)NVIDIAYes128K
Nova 2 LiteAmazonNo1M
Nova Lite 1.0AmazonNo300K
Nova Premier 1.0AmazonNo1M
Nova Pro 1.0AmazonNo300K
o1OpenAINo200K
o1 (batch)OpenAINo200K
o1-proOpenAINo200K
o1-pro (batch)OpenAINo200K
o3OpenAINo200K
o3 (batch)OpenAINo200K
o3 ProOpenAINo200K
o3 Pro (batch)OpenAINo200K
o4 MiniOpenAINo200K
o4 Mini (batch)OpenAINo200K
o4 Mini HighOpenAINo200K
o4 Mini High (batch)OpenAINo200K
OpenAI GPT Latest~openaiNo1.1M
OpenAI GPT Mini Latest~openaiNo400K
Perceptron Mk1perceptronNo32.8K
Pika 2.0PikaNo0K
Qwen2.5 VL 72B InstructAlibabaNo128K
Qwen3 VL 235B A22B InstructAlibabaNo262.1K
Qwen3 VL 235B A22B ThinkingAlibabaNo131.1K
Qwen3 VL 30B A3B InstructAlibabaNo262.1K
Qwen3 VL 30B A3B ThinkingAlibabaNo262.1K
Qwen3 VL 32B InstructAlibabaNo131.1K
Qwen3 VL 8B InstructAlibabaNo262.1K
Qwen3 VL 8B ThinkingAlibabaNo131.1K
Qwen3.5 397B A17BAlibabaNo262.1K
Qwen3.5 Plus 2026-02-15AlibabaNo1M
Qwen3.5 Plus 2026-04-20AlibabaNo1M
Qwen3.5-122B-A10BAlibabaNo262.1K
Qwen3.5-27BAlibabaNo262.1K
Qwen3.5-35B-A3BAlibabaNo262.1K
Qwen3.5-9BAlibabaNo262.1K
Qwen3.5-FlashAlibabaNo1M
Qwen3.6 27BAlibabaNo262.1K
Qwen3.6 35B A3BAlibabaNo262.1K
Qwen3.6 FlashAlibabaNo1M
Qwen3.6 PlusAlibabaNo1M
Qwen3.7 FlashAlibabaNo1M
Qwen3.7 PlusAlibabaNo1M
Qwen3.8 MaxAlibabaNo1M
Reka EdgerekaaiNo16.4K
Runway Gen-3 AlphaRunwayNo0K
Seed 1.6ByteDanceNo262.1K
Seed 1.6 FlashByteDanceNo262.1K
Seed-2.0-LiteByteDanceNo262.1K
Seed-2.0-MiniByteDanceNo262.1K
SonarPerplexityNo127.1K
Sonar ProPerplexityNo200K
Sonar Pro SearchPerplexityNo200K
Sonar Reasoning ProPerplexityNo128K
SoraOpenAINo0K
Stable Diffusion 3.5Stability AINo0K
Stable Video DiffusionStability AINo0K
Step 3.7 FlashStepFunNo262.1K
UI-TARS 7B ByteDanceNo128K
Veo 2GoogleNo0K

Image Generators

18 models that can produce images as output.

ModelFree?
Adobe Firefly 3AdobeNo
DALL-E 3OpenAINo
FLUX.1 ProBlack Forest LabsNo
GPT-5 ImageOpenAINo
GPT-5 Image MiniOpenAINo
GPT-5.4 Image 2OpenAINo
Ideogram 2.0IdeogramNo
Imagen 3GoogleNo
Leonardo PhoenixLeonardo AINo
Midjourney v6.1MidjourneyNo
Nano Banana (Gemini 2.5 Flash Image)GoogleNo
Nano Banana 2 (Gemini 3.1 Flash Image Preview)GoogleNo
Nano Banana 2 (Gemini 3.1 Flash Image)GoogleNo
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)GoogleNo
Nano Banana Pro (Gemini 3 Pro Image Preview)GoogleNo
Nano Banana Pro (Gemini 3 Pro Image)GoogleNo
Recraft V3RecraftNo
Stable Diffusion 3.5Stability AINo

Explore More

Dive deeper into multimodal AI, vision models, or browse all explorers.

All ExplorersMultimodal AI ModelsAI Models with Vision
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