AI Models with Vision

163 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

163

Of All Models

44%

Providers

Avg Score

Vision Model Rankings

All 163 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-5.5 ProOpenAI	OpenAI	90.9	1.1M	$30.00	$180.00
2	GPT-5.4 ProOpenAI	OpenAI	90.9	1.1M	$30.00	$180.00
3	GPT-5.2 ProOpenAI	OpenAI	89.9	400K	$21.00	$168.00
4	Claude Opus 4.6 (Fast)Anthropic	Anthropic	89.2	1M	$30.00	$150.00
5	GPT-5 ProOpenAI	OpenAI	89	400K	$15.00	$120.00
6	o3 ProOpenAI	OpenAI	79.9	200K	$20.00	$80.00
7	Claude Opus 4.1Anthropic	Anthropic	79.3	200K	$15.00	$75.00
8	o1-proOpenAI	OpenAI	75.5	200K	$150.00	$600.00
9	Claude Opus 4Anthropic	Anthropic	73.7	200K	$15.00	$75.00
10	OpenAI GPT Latest~openai	~openai	73.4	1.1M	$5.00	$30.00
11	GPT-5.5OpenAI	OpenAI	73.4	1.1M	$5.00	$30.00
12	o3 Deep ResearchOpenAI	OpenAI	73.2	200K	$10.00	$40.00
13	Google Gemini Pro Latest~google	~google	71.8	1.0M	$2.00	$12.00
14	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	71.8	1.0M	$2.00	$12.00
15	Gemini 3.1 Pro PreviewGoogle	Google	71.8	1.0M	$2.00	$12.00
16	Claude Opus Latest~anthropic	~anthropic	70.5	1M	$5.00	$25.00
17	Claude Opus 4.7Anthropic	Anthropic	70.5	1M	$5.00	$25.00
18	Claude Opus 4.6Anthropic	Anthropic	70.5	1M	$5.00	$25.00
19	GPT-5.4 Image 2OpenAI	OpenAI	70	272K	$8.00	$15.00
20	Claude Opus 4.5Anthropic	Anthropic	70	200K	$5.00	$25.00
21	GPT-5.4OpenAI	OpenAI	69.7	1.1M	$2.50	$15.00
22	Google Gemini Flash Latest~google	~google	69.5	1.0M	$0.50	$3.00
23	Gemini 3 Flash PreviewGoogle	Google	69.5	1.0M	$0.50	$3.00
24	Gemini 3.1 Flash LiteGoogle	Google	69.2	1.0M	$0.25	$1.50
25	Gemini 3.1 Flash Lite PreviewGoogle	Google	69.2	1.0M	$0.25	$1.50
26	GPT Chat LatestOpenAI	OpenAI	68.9	400K	$5.00	$30.00
27	GPT-5.3-CodexOpenAI	OpenAI	68.4	400K	$1.75	$14.00
28	GPT-5 ImageOpenAI	OpenAI	68.4	400K	$10.00	$10.00
29	Anthropic Claude Sonnet Latest~anthropic	~anthropic	68	1M	$3.00	$15.00
30	Claude Sonnet 4.6Anthropic	Anthropic	68	1M	$3.00	$15.00
31	Claude Sonnet 4.5Anthropic	Anthropic	68	1M	$3.00	$15.00
32	Gemini 2.5 Flash Lite Preview 09-2025Google	Google	67.6	1.0M	$0.10	$0.40
33	Gemma 4 26B A4B (free)Google	Google	67.4	262.1K	Free	Free
34	Gemma 4 31B (free)Google	Google	67.4	262.1K	Free	Free
35	Gemini 2.5 ProGoogle	Google	67.3	1.0M	$1.25	$10.00
36	o1OpenAI	OpenAI	66.5	200K	$15.00	$60.00
37	GPT-5 Image MiniOpenAI	OpenAI	66.4	400K	$2.50	$2.00
38	Gemini 2.5 Pro Preview 05-06Google	Google	66.2	1.0M	$1.25	$10.00
39	OpenAI GPT Mini Latest~openai	~openai	66.1	400K	$0.75	$4.50
40	GPT-5.4 MiniOpenAI	OpenAI	66.1	400K	$0.75	$4.50
41	Nemotron 3 Nano Omni (free)NVIDIA	NVIDIA	66	256K	Free	Free
42	GPT-5.1-Codex-MaxOpenAI	OpenAI	65.8	400K	$1.25	$10.00
43	Gemini 2.5 Flash LiteGoogle	Google	65.8	1.0M	$0.10	$0.40
44	Grok 4.1 FastxAI	xAI	65.7	2M	$0.20	$0.50
45	Gemini 2.5 FlashGoogle	Google	65.4	1.0M	$0.30	$2.50
46	GPT-5.4 NanoOpenAI	OpenAI	65.3	400K	$0.20	$1.25
47	Gemini 2.5 Pro Preview 06-05Google	Google	65.3	1.0M	$1.25	$10.00
48	o4 Mini Deep ResearchOpenAI	OpenAI	65.2	200K	$2.00	$8.00
49	Nano Banana Pro (Gemini 3 Pro Image Preview)Google	Google	65.1	65.5K	$2.00	$12.00
50	GPT-5.2OpenAI	OpenAI	64.9	400K	$1.75	$14.00
51	MiMo-V2.5Xiaomi	Xiaomi	64.6	1.0M	$0.40	$2.00
52	Grok 4 FastxAI	xAI	64.2	2M	$0.20	$0.50
53	GPT-5.1OpenAI	OpenAI	63.9	400K	$1.25	$10.00
54	Nemotron Nano 12B 2 VL (free)NVIDIA	NVIDIA	63.8	128K	Free	Free
55	Anthropic Claude Haiku Latest~anthropic	~anthropic	63.3	200K	$1.00	$5.00
56	Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google	Google	63.3	65.5K	$0.50	$3.00
57	GPT-5.2-CodexOpenAI	OpenAI	63.2	400K	$1.75	$14.00
58	GPT-5 MiniOpenAI	OpenAI	62.8	400K	$0.25	$2.00
59	MiMo-V2-OmniXiaomi	Xiaomi	62.6	262.1K	$0.40	$2.00
60	Claude Haiku 4.5Anthropic	Anthropic	62.6	200K	$1.00	$5.00
61	Qwen3.5 Plus 2026-04-20Alibaba	Alibaba	62.4	1M	$0.40	$2.40
62	Qwen3.6 PlusAlibaba	Alibaba	62.3	1M	$0.33	$1.95
63	Qwen3.6 FlashAlibaba	Alibaba	62.2	1M	$0.25	$1.50
64	Lyria 3 Pro PreviewGoogle	Google	62.2	1.0M	Free	Free
65	Lyria 3 Clip PreviewGoogle	Google	62.2	1.0M	Free	Free
66	GPT-5.3 ChatOpenAI	OpenAI	62.2	128K	$1.75	$14.00
67	Qwen3.5 Plus 2026-02-15Alibaba	Alibaba	62.2	1M	$0.26	$1.56
68	GPT-5.1-CodexOpenAI	OpenAI	62.2	400K	$1.25	$10.00
69	Qwen3.5-FlashAlibaba	Alibaba	61.9	1M	$0.07	$0.26
70	Qwen3.6 35B A3BAlibaba	Alibaba	61.7	262.1K	$0.15	$1.00
71	GLM 5V TurboZhipu AI	Zhipu AI	61.7	202.8K	$1.20	$4.00
72	Seed-2.0-LiteByteDance	ByteDance	61.5	262.1K	$0.25	$2.00
73	Qwen3.6 27BAlibaba	Alibaba	61.4	262.1K	$0.32	$3.20
74	GPT-5OpenAI	OpenAI	61.3	400K	$1.25	$10.00
75	GPT-5.1 ChatOpenAI	OpenAI	61.2	128K	$1.25	$10.00
76	Seed-2.0-MiniByteDance	ByteDance	61.1	262.1K	$0.10	$0.40
77	Qwen3.5-122B-A10BAlibaba	Alibaba	61	262.1K	$0.26	$2.08
78	Qwen3.5 397B A17BAlibaba	Alibaba	61	262.1K	$0.39	$2.34
79	Qwen3.5-35B-A3BAlibaba	Alibaba	60.9	262.1K	$0.14	$1.00
80	GPT-5 CodexOpenAI	OpenAI	60.9	400K	$1.25	$10.00
81	Claude Sonnet 4Anthropic	Anthropic	60.9	1M	$3.00	$15.00
82	Qwen3.5-27BAlibaba	Alibaba	60.8	262.1K	$0.20	$1.56
83	Grok 4.20xAI	xAI	60.7	2M	$1.25	$2.50
84	Qwen3.5-9BAlibaba	Alibaba	60.6	262.1K	$0.04	$0.15
85	Nova 2 LiteAmazon	Amazon	60.6	1M	$0.30	$2.50
86	Seed 1.6ByteDance	ByteDance	60.4	262.1K	$0.25	$2.00
87	Sonar Pro SearchPerplexity	Perplexity	60.4	200K	$3.00	$15.00
88	o3OpenAI	OpenAI	60.4	200K	$2.00	$8.00
89	GPT-5.1-Codex-MiniOpenAI	OpenAI	60.2	400K	$0.25	$2.00
90	Seed 1.6 FlashByteDance	ByteDance	60	262.1K	$0.07	$0.30
91	Gemma 4 31BGoogle	Google	59.5	262.1K	$0.13	$0.38
92	o4 Mini HighOpenAI	OpenAI	59.5	200K	$1.10	$4.40
93	o4 MiniOpenAI	OpenAI	59.5	200K	$1.10	$4.40
94	Kimi K2.5Moonshot AI	Moonshot AI	59.3	262.1K	$0.44	$2.00
95	GPT-5.2 ChatOpenAI	OpenAI	59.1	128K	$1.75	$14.00
96	MoonshotAI Kimi Latest~moonshotai	~moonshotai	58.7	262.1K	$0.75	$3.50
97	Kimi K2.6Moonshot AI	Moonshot AI	58.7	262.1K	$0.75	$3.50
98	Grok 4.3xAI	xAI	58.3	1M	$1.25	$2.50
99	Grok 4xAI	xAI	58.3	256K	$3.00	$15.00
100	Grok 4.20 Multi-AgentxAI	xAI	58	2M	$2.00	$6.00
101	Nano Banana (Gemini 2.5 Flash Image)Google	Google	57.5	32.8K	$0.30	$2.50
102	Qwen3 VL 8B ThinkingAlibaba	Alibaba	57.2	131.1K	$0.12	$1.36
103	Qianfan-OCR-Fast (free)Baidu	Baidu	57.1	65.5K	Free	Free
104	Qwen3 VL 30B A3B ThinkingAlibaba	Alibaba	57	131.1K	$0.13	$1.56
105	Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	56.9	131.1K	$0.26	$2.60
106	Claude 3.7 SonnetAnthropic	Anthropic	56.8	200K	$3.00	$15.00
107	Claude 3.7 Sonnet (thinking)Anthropic	Anthropic	56.8	200K	$3.00	$15.00
108	Gemini 2.0 Flash LiteGoogle	Google	56.7	1.0M	$0.07	$0.30
109	Gemini 2.0 FlashGoogle	Google	56.2	1M	$0.10	$0.40
110	GPT-4.1 MiniOpenAI	OpenAI	56	1.0M	$0.40	$1.60
111	GLM 4.6VZhipu AI	Zhipu AI	55.7	131.1K	$0.30	$0.90
112	GPT-4.1 NanoOpenAI	OpenAI	55.7	1.0M	$0.10	$0.40
113	Nova Premier 1.0Amazon	Amazon	55.3	1M	$2.50	$12.50
114	GPT-5 ChatOpenAI	OpenAI	55	128K	$1.25	$10.00
115	Mistral Medium 3.5Mistral AI	Mistral AI	54.6	262.1K	$1.50	$7.50
116	Gemma 4 26B A4B Google	Google	54.5	262.1K	$0.06	$0.33
117	Qwen3 VL 32B InstructAlibaba	Alibaba	53.6	131.1K	$0.10	$0.42
118	Qwen3 VL 8B InstructAlibaba	Alibaba	53.4	131.1K	$0.08	$0.50
119	Qwen3 VL 30B A3B InstructAlibaba	Alibaba	53.2	131.1K	$0.13	$0.52
120	Qwen3 VL 235B A22B InstructAlibaba	Alibaba	53.1	262.1K	$0.20	$0.88
121	Reka Edgerekaai	rekaai	53	16.4K	$0.10	$0.10
122	Mistral Small 4Mistral AI	Mistral AI	52.9	262.1K	$0.15	$0.60
123	GPT-5 NanoOpenAI	OpenAI	52.4	400K	$0.05	$0.40
124	GLM 4.5VZhipu AI	Zhipu AI	50.7	65.5K	$0.60	$1.80
125	Mistral Large 3 2512Mistral AI	Mistral AI	49.6	262.1K	$0.50	$1.50
126	Mistral Small 3.2 24BMistral AI	Mistral AI	49.6	128K	$0.07	$0.20
127	Ministral 3 14B 2512Mistral AI	Mistral AI	49.2	262.1K	$0.20	$0.20
128	Ministral 3 8B 2512Mistral AI	Mistral AI	49.2	262.1K	$0.15	$0.15
129	ERNIE 4.5 VL 28B A3BBaidu	Baidu	49.1	30K	$0.14	$0.56
130	Ministral 3 3B 2512Mistral AI	Mistral AI	48.5	131.1K	$0.10	$0.10
131	GPT-4.1OpenAI	OpenAI	48.5	1.0M	$2.00	$8.00
132	Llama 4 ScoutMeta	Meta	48.5	327.7K	$0.08	$0.30
133	GPT-4o (2024-11-20)OpenAI	OpenAI	47.9	128K	$2.50	$10.00
134	Gemma 3 12BGoogle	Google	46.9	131.1K	$0.04	$0.13
135	Gemma 3 27BGoogle	Google	46.9	131.1K	$0.08	$0.16
136	Sonar ProPerplexity	Perplexity	46.8	200K	$3.00	$15.00
137	Qwen VL MaxAlibaba	Alibaba	46.8	131.1K	$0.52	$2.08
138	Mistral Medium 3.1Mistral AI	Mistral AI	46.5	131.1K	$0.40	$2.00
139	ERNIE 4.5 VL 424B A47B Baidu	Baidu	46.5	123K	$0.42	$1.25
140	Llama 4 MaverickMeta	Meta	46.2	1.0M	$0.15	$0.60
141	GPT-4o (2024-08-06)OpenAI	OpenAI	45	128K	$2.50	$10.00
142	GPT-4 TurboOpenAI	OpenAI	45	128K	$10.00	$30.00
143	Llama Guard 4 12BMeta	Meta	44.9	163.8K	$0.18	$0.18
144	Claude 3.5 HaikuAnthropic	Anthropic	44.3	200K	$0.80	$4.00
145	Mistral Medium 3Mistral AI	Mistral AI	43.8	131.1K	$0.40	$2.00
146	Sonar Reasoning ProPerplexity	Perplexity	43.6	128K	$2.00	$8.00
147	MiniMax-01MiniMax	MiniMax	43.5	1.0M	$0.20	$1.10
148	Gemma 3 4BGoogle	Google	43.3	131.1K	$0.04	$0.08
149	GPT-4o (2024-05-13)OpenAI	OpenAI	43	128K	$5.00	$15.00
150	GPT-4oOpenAI	OpenAI	42.7	128K	$2.50	$10.00
151	Spotlightarcee-ai	arcee-ai	42.2	131.1K	$0.18	$0.18
152	GPT-4o-mini (2024-07-18)OpenAI	OpenAI	42.2	128K	$0.15	$0.60
153	GPT-4o-miniOpenAI	OpenAI	42.2	128K	$0.15	$0.60
154	Qwen VL PlusAlibaba	Alibaba	41.9	131.1K	$0.14	$0.41
155	UI-TARS 7B ByteDance	ByteDance	41.8	128K	$0.10	$0.20
156	Nova Pro 1.0Amazon	Amazon	41.5	300K	$0.80	$3.20
157	Nova Lite 1.0Amazon	Amazon	40.7	300K	$0.06	$0.24
158	Pixtral Large 2411Mistral AI	Mistral AI	40.2	131.1K	$2.00	$6.00
159	Llama 3.2 11B Vision InstructMeta	Meta	38.7	131.1K	$0.24	$0.24
160	SonarPerplexity	Perplexity	37.3	127.1K	$1.00	$1.00
161	Qwen2.5 VL 72B InstructAlibaba	Alibaba	35.9	32K	$0.25	$0.75
162	Mistral Small 3.1 24BMistral AI	Mistral AI	34.9	128K	$0.35	$0.56
163	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 163 vision models break down by other features.

Function Calling

83%

136 of 163 vision models

JSON Mode

85%

139 of 163 vision models

Streaming

100%

163 of 163 vision models

Reasoning

67%

109 of 163 vision models

Web Search

44%

72 of 163 vision models

Image Output

6 of 163 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-5.5 Pro OpenAI
GPT-5.4 Pro OpenAI
GPT-5.2 Pro OpenAI
Claude Opus 4.6 (Fast) Anthropic
GPT-5 Pro OpenAI
o3 Pro OpenAI
Claude Opus 4.1 Anthropic
o1-pro OpenAI
Claude Opus 4 Anthropic
OpenAI GPT Latest ~openai
GPT-5.5 OpenAI
o3 Deep Research OpenAI
Google Gemini Pro Latest ~google
Gemini 3.1 Pro Preview Custom Tools Google
Gemini 3.1 Pro Preview Google

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.