AI Models with Vision

136 multimodal AI models that support image input and visual understanding, ranked by composite score. These models can analyze images, screenshots, diagrams, and documents alongside text prompts.

Vision Models

136

Of All Models

42%

Providers

Avg Score

Vision Model Rankings

All 136 models with vision capability, sorted by composite score. Score is computed from capabilities, pricing, context window, recency, output capacity, and versatility.

#	Model	Provider	Score	Context	Input/1M	Output/1M
1	GPT-5.4 ProOpenAI	OpenAI	90.9	1.1M	$30.00	$180.00
2	GPT-5.2 ProOpenAI	OpenAI	89.9	400K	$21.00	$168.00
3	GPT-5 ProOpenAI	OpenAI	89.9	400K	$15.00	$120.00
4	o3 ProOpenAI	OpenAI	81.1	200K	$20.00	$80.00
5	Claude Opus 4.1Anthropic	Anthropic	80.5	200K	$15.00	$75.00
6	o1-proOpenAI	OpenAI	76.7	200K	$150.00	$600.00
7	Claude Opus 4Anthropic	Anthropic	74.9	200K	$15.00	$75.00
8	o3 Deep ResearchOpenAI	OpenAI	74	200K	$10.00	$40.00
9	GPT-5 ImageOpenAI	OpenAI	72.7	400K	$10.00	$10.00
10	GPT-5 Image MiniOpenAI	OpenAI	70.7	400K	$2.50	$2.00
11	Claude Opus 4.6Anthropic	Anthropic	70.5	1M	$5.00	$25.00
12	Claude Opus 4.5Anthropic	Anthropic	70	200K	$5.00	$25.00
13	GPT-5.4OpenAI	OpenAI	69.7	1.1M	$2.50	$15.00
14	Claude Sonnet 4.5Anthropic	Anthropic	69.1	1M	$3.00	$15.00
15	GPT-5.3-CodexOpenAI	OpenAI	68.4	400K	$1.75	$14.00
16	GPT-5.2OpenAI	OpenAI	68.4	400K	$1.75	$14.00
17	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	68.2	1.0M	$2.00	$12.00
18	Gemini 3.1 Pro PreviewGoogle	Google	68.2	1.0M	$2.00	$12.00
19	Claude Sonnet 4.6Anthropic	Anthropic	68	1M	$3.00	$15.00
20	o1OpenAI	OpenAI	67.7	200K	$15.00	$60.00
21	GPT-5.1OpenAI	OpenAI	67.4	400K	$1.25	$10.00
22	GPT-5.2-CodexOpenAI	OpenAI	66.8	400K	$1.75	$14.00
23	GPT-5.4 MiniOpenAI	OpenAI	66.1	400K	$0.75	$4.50
24	GPT-5OpenAI	OpenAI	66.1	400K	$1.25	$10.00
25	Gemini 3 Flash PreviewGoogle	Google	66	1.0M	$0.50	$3.00
26	o4 Mini Deep ResearchOpenAI	OpenAI	66	200K	$2.00	$8.00
27	GPT-5.1-Codex-MaxOpenAI	OpenAI	65.8	400K	$1.25	$10.00
28	Gemini 3.1 Flash Lite PreviewGoogle	Google	65.6	1.0M	$0.25	$1.50
29	GPT-5.4 NanoOpenAI	OpenAI	65.3	400K	$0.20	$1.25
30	Gemini 2.5 Flash Lite Preview 09-2025Google	Google	65.3	1.0M	$0.10	$0.40
31	Gemini 2.5 ProGoogle	Google	64.9	1.0M	$1.25	$10.00
32	Nemotron Nano 12B 2 VL (free)NVIDIA	NVIDIA	64.1	128K	Free	Free
33	GPT-5 MiniOpenAI	OpenAI	64.1	400K	$0.25	$2.00
34	Grok 4.1 FastxAI	xAI	64	2M	$0.20	$0.50
35	Grok 4 FastxAI	xAI	63.8	2M	$0.20	$0.50
36	Gemini 2.5 Pro Preview 05-06Google	Google	63.8	1.0M	$1.25	$10.00
37	GPT-5 NanoOpenAI	OpenAI	63.7	400K	$0.05	$0.40
38	Gemini 2.5 Flash LiteGoogle	Google	63.5	1.0M	$0.10	$0.40
39	Claude Haiku 4.5Anthropic	Anthropic	63.3	200K	$1.00	$5.00
40	Gemini 2.5 FlashGoogle	Google	63.1	1.0M	$0.30	$2.50
41	Gemini 2.5 Pro Preview 06-05Google	Google	63	1.0M	$1.25	$10.00
42	MiMo-V2-OmniXiaomi	Xiaomi	62.6	262.1K	$0.40	$2.00
43	GPT-5.3 ChatOpenAI	OpenAI	62.2	128K	$1.75	$14.00
44	Qwen3.5 Plus 2026-02-15Alibaba	Alibaba	62.2	1M	$0.26	$1.56
45	GPT-5.2 ChatOpenAI	OpenAI	62.2	128K	$1.75	$14.00
46	GPT-5.1-CodexOpenAI	OpenAI	62.2	400K	$1.25	$10.00
47	GPT-5 CodexOpenAI	OpenAI	62.1	400K	$1.25	$10.00
48	Qwen3.5-FlashAlibaba	Alibaba	61.9	1M	$0.07	$0.26
49	o3OpenAI	OpenAI	61.6	200K	$2.00	$8.00
50	Seed-2.0-LiteByteDance	ByteDance	61.5	262.1K	$0.25	$2.00
51	Nano Banana Pro (Gemini 3 Pro Image Preview)Google	Google	61.5	65.5K	$2.00	$12.00
52	GPT-5.1 ChatOpenAI	OpenAI	61.2	128K	$1.25	$10.00
53	Seed-2.0-MiniByteDance	ByteDance	61.1	262.1K	$0.10	$0.40
54	Qwen3.5-122B-A10BAlibaba	Alibaba	61	262.1K	$0.26	$2.08
55	Qwen3.5 397B A17BAlibaba	Alibaba	61	262.1K	$0.39	$2.34
56	Qwen3.5-35B-A3BAlibaba	Alibaba	60.8	262.1K	$0.16	$1.30
57	Qwen3.5-27BAlibaba	Alibaba	60.8	262.1K	$0.20	$1.56
58	Sonar Pro SearchPerplexity	Perplexity	60.7	200K	$3.00	$15.00
59	o4 Mini HighOpenAI	OpenAI	60.7	200K	$1.10	$4.40
60	o4 MiniOpenAI	OpenAI	60.7	200K	$1.10	$4.40
61	Nova 2 LiteAmazon	Amazon	60.6	1M	$0.30	$2.50
62	Qwen3.5-9BAlibaba	Alibaba	60.5	256K	$0.05	$0.15
63	Seed 1.6ByteDance	ByteDance	60.4	262.1K	$0.25	$2.00
64	Claude Sonnet 4Anthropic	Anthropic	60.4	200K	$3.00	$15.00
65	Seed 1.6 FlashByteDance	ByteDance	60	262.1K	$0.07	$0.30
66	GPT-5.1-Codex-MiniOpenAI	OpenAI	60	400K	$0.25	$2.00
67	Grok 4.20 BetaxAI	xAI	59.9	2M	$2.00	$6.00
68	Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google	Google	59.8	65.5K	$0.50	$3.00
69	Kimi K2.5Moonshot AI	Moonshot AI	59.3	262.1K	$0.45	$2.20
70	GPT-4.1OpenAI	OpenAI	58.9	1.0M	$2.00	$8.00
71	Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	58.1	131.1K	$0.26	$2.60
72	Claude 3.7 SonnetAnthropic	Anthropic	58.1	200K	$3.00	$15.00
73	Claude 3.7 Sonnet (thinking)Anthropic	Anthropic	58.1	200K	$3.00	$15.00
74	Qwen3 VL 30B A3B ThinkingAlibaba	Alibaba	58	131.1K	$0.13	$1.56
75	Qwen3 VL 8B ThinkingAlibaba	Alibaba	57.9	131.1K	$0.12	$1.36
76	Grok 4xAI	xAI	57.9	256K	$3.00	$15.00
77	GPT-4.1 MiniOpenAI	OpenAI	57.3	1.0M	$0.40	$1.60
78	GPT-4.1 NanoOpenAI	OpenAI	57	1.0M	$0.10	$0.40
79	Grok 4.20 Multi-Agent BetaxAI	xAI	56.4	2M	$2.00	$6.00
80	GPT-5 ChatOpenAI	OpenAI	56.3	128K	$1.25	$10.00
81	Nova Premier 1.0Amazon	Amazon	55.6	1M	$2.50	$12.50
82	Nano Banana (Gemini 2.5 Flash Image)Google	Google	54.9	32.8K	$0.30	$2.50
83	Gemini 2.0 Flash LiteGoogle	Google	54.4	1.0M	$0.07	$0.30
84	Qwen3 VL 32B InstructAlibaba	Alibaba	54.1	131.1K	$0.10	$0.42
85	Qwen3 VL 8B InstructAlibaba	Alibaba	54.1	131.1K	$0.08	$0.50
86	Qwen3 VL 30B A3B InstructAlibaba	Alibaba	54.1	131.1K	$0.13	$0.52
87	Gemini 2.0 FlashGoogle	Google	53.9	1.0M	$0.10	$0.40
88	Reka Edgereka	reka	53.1	16.4K	$0.20	$0.20
89	Mistral Small 4Mistral AI	Mistral AI	52.9	262.1K	$0.15	$0.60
90	Gemma 3 27B (free)Google	Google	51.5	131.1K	Free	Free
91	Llama 4 MaverickMeta	Meta	51	1.0M	$0.15	$0.60
92	Mistral Small 3.1 24B (free)Mistral AI	Mistral AI	50.7	128K	Free	Free
93	ERNIE 4.5 VL 28B A3BBaidu	Baidu	50.4	30K	$0.14	$0.56
94	Nemotron Nano 12B 2 VLNVIDIA	NVIDIA	50.3	131.1K	$0.20	$0.60
95	Gemma 3 4B (free)Google	Google	50.1	32.8K	Free	Free
96	Llama 4 ScoutMeta	Meta	49.8	327.7K	$0.08	$0.30
97	Claude 3.5 SonnetAnthropic	Anthropic	49.7	200K	$6.00	$30.00
98	Mistral Large 3 2512Mistral AI	Mistral AI	49.6	262.1K	$0.50	$1.50
99	Qwen3 VL 235B A22B InstructAlibaba	Alibaba	49.3	262.1K	$0.20	$0.88
100	Ministral 3 14B 2512Mistral AI	Mistral AI	49.2	262.1K	$0.20	$0.20
101	Ministral 3 8B 2512Mistral AI	Mistral AI	49.2	262.1K	$0.15	$0.15
102	GPT-4o (2024-11-20)OpenAI	OpenAI	49.2	128K	$2.50	$10.00
103	Ministral 3 3B 2512Mistral AI	Mistral AI	48.5	131.1K	$0.10	$0.10
104	Sonar ProPerplexity	Perplexity	48	200K	$3.00	$15.00
105	Qwen VL MaxAlibaba	Alibaba	48	131.1K	$0.52	$2.08
106	Mistral Medium 3.1Mistral AI	Mistral AI	47.8	131.1K	$0.40	$2.00
107	ERNIE 4.5 VL 424B A47B Baidu	Baidu	47.7	123K	$0.42	$1.25
108	GPT-4o (extended)OpenAI	OpenAI	46.9	128K	$6.00	$18.00
109	Gemma 3 12B (free)Google	Google	46.5	32.8K	Free	Free
110	GPT-4o (2024-08-06)OpenAI	OpenAI	46.3	128K	$2.50	$10.00
111	Mistral Small 3.1 24BMistral AI	Mistral AI	46.2	131.1K	$0.03	$0.11
112	Mistral Small 3.2 24BMistral AI	Mistral AI	45.8	128K	$0.07	$0.20
113	Claude 3.5 HaikuAnthropic	Anthropic	45.5	200K	$0.80	$4.00
114	GPT-4 TurboOpenAI	OpenAI	45.3	128K	$10.00	$30.00
115	Mistral Medium 3Mistral AI	Mistral AI	45.1	131.1K	$0.40	$2.00
116	Sonar Reasoning ProPerplexity	Perplexity	44.9	128K	$2.00	$8.00
117	MiniMax-01MiniMax	MiniMax	44.7	1.0M	$0.20	$1.10
118	Gemma 3 27BGoogle	Google	44.5	131.1K	$0.08	$0.16
119	GPT-4o (2024-05-13)OpenAI	OpenAI	44.2	128K	$5.00	$15.00
120	GPT-4oOpenAI	OpenAI	43.9	128K	$2.50	$10.00
121	Spotlightarcee-ai	arcee-ai	43.5	131.1K	$0.18	$0.18
122	GPT-4o-mini (2024-07-18)OpenAI	OpenAI	43.4	128K	$0.15	$0.60
123	GPT-4o-miniOpenAI	OpenAI	43.4	128K	$0.15	$0.60
124	UI-TARS 7B ByteDance	ByteDance	43.1	128K	$0.10	$0.20
125	Qwen VL PlusAlibaba	Alibaba	43.1	131.1K	$0.14	$0.41
126	Qwen2.5 VL 72B InstructAlibaba	Alibaba	42.7	32.8K	$0.80	$0.80
127	Nova Pro 1.0Amazon	Amazon	42.7	300K	$0.80	$3.20
128	Nova Lite 1.0Amazon	Amazon	41.9	300K	$0.06	$0.24
129	Pixtral Large 2411Mistral AI	Mistral AI	41.5	131.1K	$2.00	$6.00
130	Llama Guard 4 12BMeta	Meta	41.1	163.8K	$0.18	$0.18
131	Qwen2.5 VL 32B InstructAlibaba	Alibaba	39.9	128K	$0.20	$0.60
132	Llama 3.2 11B Vision InstructMeta	Meta	39.9	131.1K	$0.05	$0.05
133	Gemma 3 4BGoogle	Google	39.5	131.1K	$0.04	$0.08
134	Gemma 3 12BGoogle	Google	39.5	131.1K	$0.04	$0.13
135	SonarPerplexity	Perplexity	38.5	127.1K	$1.00	$1.00
136	Claude 3 HaikuAnthropic	Anthropic	34.7	200K	$0.25	$1.25

What Else Can Vision Models Do?

Vision-capable models often support additional capabilities. Here is how the 136 vision models break down by other features.

Function Calling

80%

109 of 136 vision models

JSON Mode

85%

115 of 136 vision models

Streaming

100%

136 of 136 vision models

Reasoning

57%

78 of 136 vision models

Web Search

36%

49 of 136 vision models

Image Output

5 of 136 vision models

Top Providers of Vision Models

Which providers offer the most AI models with image understanding capabilities.

OpenAI

vision models

Google

vision models

Alibaba

vision models

Anthropic

vision models

Mistral AI

vision models

xAI

vision models

ByteDance

vision models

Amazon

vision models

Top Vision Models - Full Capability Breakdown

Detailed capability matrix for the top 15 vision models by composite score.

Model	Function Calling	JSON Mode	Streaming	Reasoning	Web Search	Image Output
GPT-5.4 Pro OpenAI
GPT-5.2 Pro OpenAI
GPT-5 Pro OpenAI
o3 Pro OpenAI
Claude Opus 4.1 Anthropic
o1-pro OpenAI
Claude Opus 4 Anthropic
o3 Deep Research OpenAI
GPT-5 Image OpenAI
GPT-5 Image Mini OpenAI
Claude Opus 4.6 Anthropic
Claude Opus 4.5 Anthropic
GPT-5.4 OpenAI
Claude Sonnet 4.5 Anthropic
GPT-5.3-Codex OpenAI

Supported

Not supported

What Are Vision / Multimodal AI Models?

Vision-capable AI models (also called multimodal models) can process both text and images as input. Instead of being limited to text-only prompts, these models can understand photos, screenshots, charts, diagrams, handwritten notes, and other visual content.

How Vision Input Works

You send an image (as a URL or base64-encoded data) alongside your text prompt via the API. The model processes both together, allowing it to answer questions about the image, describe its contents, extract text (OCR), analyze charts, or reason about visual information.

Common Use Cases for Vision Models

Document analysis and OCR, screenshot-to-code generation, chart and graph interpretation, medical image analysis, accessibility (image descriptions), visual QA for customer support, UI/UX review, diagram-to-code conversion, and real-time visual understanding in agentic workflows.

Vision vs. Image Output

Vision (image input) and image output are distinct capabilities. Vision means the model can see and understand images you send to it. Image output means the model can generate new images. Some models support both, but many vision models are text-output only - they analyze images but respond with text.

Pricing Considerations

Image tokens typically cost more than text tokens. A single high-resolution image can consume thousands of tokens. Most providers charge for image input based on the image dimensions and detail level. Check each model's specific pricing for image token costs.

Explore More Model Comparisons

Dive deeper into model capabilities, rankings, and head-to-head comparisons to find the right vision model for your use case.

LLM Leaderboard|Capability Matrix|Compare Models

Frequently Asked Questions

Vision AI models (multimodal LLMs) can understand and analyze images alongside text. They accept image inputs and can describe photos, extract text from screenshots, analyze charts, and answer questions about visual content.

The top vision models include GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash. Rankings change frequently as models improve — check our leaderboard for the latest scores.

Not all of them. Vision capabilities refer to understanding images (input). Some models like DALL-E and Stable Diffusion specialize in generating images (output). A few models like GPT-4o can both understand and generate images.