AI Models with Vision

128 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

128

Of All Models

43%

Providers

Avg Score

Vision Model Rankings

All 128 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-5.2 ProOpenAI	OpenAI	89.9	400K	$21.00	$168.00
2	GPT-5 ProOpenAI	OpenAI	89.9	400K	$15.00	$120.00
3	o3 ProOpenAI	OpenAI	81.7	200K	$20.00	$80.00
4	Claude Opus 4.1Anthropic	Anthropic	81.1	200K	$15.00	$75.00
5	o1-proOpenAI	OpenAI	77.3	200K	$150.00	$600.00
6	Claude Opus 4Anthropic	Anthropic	75.5	200K	$15.00	$75.00
7	o3 Deep ResearchOpenAI	OpenAI	74	200K	$10.00	$40.00
8	GPT-5 ImageOpenAI	OpenAI	72.7	400K	$10.00	$10.00
9	GPT-5 Image MiniOpenAI	OpenAI	70.7	400K	$2.50	$2.00
10	Claude Opus 4.6Anthropic	Anthropic	70.5	1M	$5.00	$25.00
11	Claude Opus 4.5Anthropic	Anthropic	70	200K	$5.00	$25.00
12	Claude Sonnet 4.5Anthropic	Anthropic	69.1	1M	$3.00	$15.00
13	Qwen3 VL 30B A3B ThinkingAlibaba	Alibaba	68.6	131.1K	Free	Free
14	Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	68.6	131.1K	Free	Free
15	GPT-5.2OpenAI	OpenAI	68.4	400K	$1.75	$14.00
16	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	68.2	1.0M	$2.00	$12.00
17	Gemini 3.1 Pro PreviewGoogle	Google	68.2	1.0M	$2.00	$12.00
18	Gemini 3 Pro PreviewGoogle	Google	68.2	1.0M	$2.00	$12.00
19	Claude Sonnet 4.6Anthropic	Anthropic	68	1M	$3.00	$15.00
20	GPT-5.1OpenAI	OpenAI	67.4	400K	$1.25	$10.00
21	GPT-5.3-CodexOpenAI	OpenAI	66.8	400K	$1.75	$14.00
22	GPT-5.2-CodexOpenAI	OpenAI	66.8	400K	$1.75	$14.00
23	GPT-5OpenAI	OpenAI	66.6	400K	$1.25	$10.00
24	Gemini 3 Flash PreviewGoogle	Google	66	1.0M	$0.50	$3.00
25	o4 Mini Deep ResearchOpenAI	OpenAI	66	200K	$2.00	$8.00
26	GPT-5.1-Codex-MaxOpenAI	OpenAI	65.8	400K	$1.25	$10.00
27	Gemini 3.1 Flash Lite PreviewGoogle	Google	65.6	1.0M	$0.25	$1.50
28	Gemini 2.5 ProGoogle	Google	65.5	1.0M	$1.25	$10.00
29	Gemini 2.5 Flash Lite Preview 09-2025Google	Google	65.3	1.0M	$0.10	$0.40
30	o1OpenAI	OpenAI	64.7	200K	$15.00	$60.00
31	GPT-5 MiniOpenAI	OpenAI	64.6	400K	$0.25	$2.00
32	Gemini 2.5 Pro Preview 05-06Google	Google	64.4	1.0M	$1.25	$10.00
33	GPT-5 NanoOpenAI	OpenAI	64.2	400K	$0.05	$0.40
34	Nemotron Nano 12B 2 VL (free)NVIDIA	NVIDIA	64.1	128K	Free	Free
35	Gemini 2.5 Flash LiteGoogle	Google	64.1	1.0M	$0.10	$0.40
36	Grok 4.1 FastxAI	xAI	64	2M	$0.20	$0.50
37	Grok 4 FastxAI	xAI	64	2M	$0.20	$0.50
38	Gemini 2.5 FlashGoogle	Google	63.6	1.0M	$0.30	$2.50
39	Gemini 2.5 Pro Preview 06-05Google	Google	63.5	1.0M	$1.25	$10.00
40	Claude Haiku 4.5Anthropic	Anthropic	63.3	200K	$1.00	$5.00
41	Claude Sonnet 4Anthropic	Anthropic	62.7	1M	$3.00	$15.00
42	GPT-5.3 ChatOpenAI	OpenAI	62.2	128K	$1.75	$14.00
43	Qwen3.5 Plus 2026-02-15Alibaba	Alibaba	62.2	1M	$0.26	$1.56
44	GPT-5.2 ChatOpenAI	OpenAI	62.2	128K	$1.75	$14.00
45	GPT-5.1-CodexOpenAI	OpenAI	62.2	400K	$1.25	$10.00
46	GPT-5 CodexOpenAI	OpenAI	62.2	400K	$1.25	$10.00
47	o3OpenAI	OpenAI	62.2	200K	$2.00	$8.00
48	Qwen3.5-FlashAlibaba	Alibaba	61.9	1M	$0.10	$0.40
49	Nano Banana Pro (Gemini 3 Pro Image Preview)Google	Google	61.5	65.5K	$2.00	$12.00
50	o4 Mini HighOpenAI	OpenAI	61.3	200K	$1.10	$4.40
51	o4 MiniOpenAI	OpenAI	61.3	200K	$1.10	$4.40
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	Nova 2 LiteAmazon	Amazon	60.6	1M	$0.30	$2.50
60	Seed 1.6ByteDance	ByteDance	60.4	262.1K	$0.25	$2.00
61	Seed 1.6 FlashByteDance	ByteDance	60	262.1K	$0.07	$0.30
62	GPT-5.1-Codex-MiniOpenAI	OpenAI	60	400K	$0.25	$2.00
63	Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google	Google	59.8	65.5K	$0.50	$3.00
64	GPT-4.1OpenAI	OpenAI	59.4	1.0M	$2.00	$8.00
65	Kimi K2.5Moonshot AI	Moonshot AI	59.3	262.1K	$0.45	$2.20
66	Claude 3.7 SonnetAnthropic	Anthropic	58.6	200K	$3.00	$15.00
67	Claude 3.7 Sonnet (thinking)Anthropic	Anthropic	58.6	200K	$3.00	$15.00
68	Grok 4xAI	xAI	58.5	256K	$3.00	$15.00
69	Qwen3 VL 8B ThinkingAlibaba	Alibaba	57.9	131.1K	$0.12	$1.36
70	GPT-4.1 MiniOpenAI	OpenAI	57.8	1.0M	$0.40	$1.60
71	GPT-4.1 NanoOpenAI	OpenAI	57.5	1.0M	$0.10	$0.40
72	GPT-5 ChatOpenAI	OpenAI	56.8	128K	$1.25	$10.00
73	Nova Premier 1.0Amazon	Amazon	55.6	1M	$2.50	$12.50
74	Gemma 3 27B (free)Google	Google	55.6	131.1K	Free	Free
75	Gemini 2.0 Flash LiteGoogle	Google	55	1.0M	$0.07	$0.30
76	Nano Banana (Gemini 2.5 Flash Image)Google	Google	54.9	32.8K	$0.30	$2.50
77	Gemini 2.0 FlashGoogle	Google	54.4	1.0M	$0.10	$0.40
78	Qwen3 VL 32B InstructAlibaba	Alibaba	54.1	131.1K	$0.10	$0.42
79	Qwen3 VL 8B InstructAlibaba	Alibaba	54.1	131.1K	$0.08	$0.50
80	Qwen3 VL 30B A3B InstructAlibaba	Alibaba	54.1	131.1K	$0.13	$0.52
81	Mistral Small 3.2 24BMistral AI	Mistral AI	52.9	131.1K	$0.06	$0.18
82	Llama 4 MaverickMeta	Meta	51.6	1.0M	$0.15	$0.60
83	Mistral Small 3.1 24B (free)Mistral AI	Mistral AI	51.2	128K	Free	Free
84	ERNIE 4.5 VL 28B A3BBaidu	Baidu	50.9	30K	$0.14	$0.56
85	Gemma 3 4B (free)Google	Google	50.7	32.8K	Free	Free
86	Nemotron Nano 12B 2 VLNVIDIA	NVIDIA	50.3	131.1K	$0.20	$0.60
87	Llama 4 ScoutMeta	Meta	50.3	327.7K	$0.08	$0.30
88	Claude 3.5 SonnetAnthropic	Anthropic	50.3	200K	$6.00	$30.00
89	GPT-4o (2024-11-20)OpenAI	OpenAI	49.7	128K	$2.50	$10.00
90	Mistral Large 3 2512Mistral AI	Mistral AI	49.6	262.1K	$0.50	$1.50
91	Gemma 3 27BGoogle	Google	49.6	128K	$0.04	$0.15
92	Qwen3 VL 235B A22B InstructAlibaba	Alibaba	49.4	262.1K	$0.20	$0.88
93	Ministral 3 14B 2512Mistral AI	Mistral AI	49.2	262.1K	$0.20	$0.20
94	Ministral 3 8B 2512Mistral AI	Mistral AI	49.2	262.1K	$0.15	$0.15
95	Qwen VL MaxAlibaba	Alibaba	48.9	131.1K	$0.80	$3.20
96	Sonar ProPerplexity	Perplexity	48.6	200K	$3.00	$15.00
97	Ministral 3 3B 2512Mistral AI	Mistral AI	48.5	131.1K	$0.10	$0.10
98	Mistral Medium 3.1Mistral AI	Mistral AI	48.3	131.1K	$0.40	$2.00
99	ERNIE 4.5 VL 424B A47B Baidu	Baidu	48.3	123K	$0.42	$1.25
100	GPT-4o (extended)OpenAI	OpenAI	47.5	128K	$6.00	$18.00
101	Molmo2 8BAllen AI	Allen AI	47.3	36.9K	$0.20	$0.20
102	Gemma 3 12B (free)Google	Google	47.1	32.8K	Free	Free
103	GPT-4o (2024-08-06)OpenAI	OpenAI	46.8	128K	$2.50	$10.00
104	Claude 3.5 HaikuAnthropic	Anthropic	46.1	200K	$0.80	$4.00
105	GPT-4 TurboOpenAI	OpenAI	45.9	128K	$10.00	$30.00
106	Mistral Medium 3Mistral AI	Mistral AI	45.6	131.1K	$0.40	$2.00
107	Sonar Reasoning ProPerplexity	Perplexity	45.4	128K	$2.00	$8.00
108	MiniMax-01MiniMax	MiniMax	45.3	1.0M	$0.20	$1.10
109	GPT-4o (2024-05-13)OpenAI	OpenAI	44.8	128K	$5.00	$15.00
110	GPT-4oOpenAI	OpenAI	44.5	128K	$2.50	$10.00
111	Spotlightarcee-ai	arcee-ai	44	131.1K	$0.18	$0.18
112	GPT-4o-mini (2024-07-18)OpenAI	OpenAI	44	128K	$0.15	$0.60
113	GPT-4o-miniOpenAI	OpenAI	44	128K	$0.15	$0.60
114	Qwen VL PlusAlibaba	Alibaba	43.7	131.1K	$0.14	$0.41
115	UI-TARS 7B ByteDance	ByteDance	43.6	128K	$0.10	$0.20
116	Qwen2.5 VL 72B InstructAlibaba	Alibaba	43.3	32.8K	$0.80	$0.80
117	Nova Pro 1.0Amazon	Amazon	43.2	300K	$0.80	$3.20
118	Nova Lite 1.0Amazon	Amazon	42.5	300K	$0.06	$0.24
119	Pixtral Large 2411Mistral AI	Mistral AI	42	131.1K	$2.00	$6.00
120	Llama Guard 4 12BMeta	Meta	41.6	163.8K	$0.18	$0.18
121	Qwen2.5 VL 32B InstructAlibaba	Alibaba	40.5	128K	$0.20	$0.60
122	Llama 3.2 11B Vision InstructMeta	Meta	40.5	131.1K	$0.05	$0.05
123	Gemma 3 4BGoogle	Google	40.1	131.1K	$0.04	$0.08
124	Gemma 3 12BGoogle	Google	40.1	131.1K	$0.04	$0.13
125	SonarPerplexity	Perplexity	39.1	127.1K	$1.00	$1.00
126	Mistral Small 3.1 24BMistral AI	Mistral AI	36.7	128K	$0.35	$0.56
127	Claude 3 HaikuAnthropic	Anthropic	34.9	200K	$0.25	$1.25
128	Qwen2.5-VL 7B InstructAlibaba	Alibaba	29.7	32.8K	$0.20	$0.20

What Else Can Vision Models Do?

Vision-capable models often support additional capabilities. Here is how the 128 vision models break down by other features.

Function Calling

80%

102 of 128 vision models

JSON Mode

81%

104 of 128 vision models

Streaming

100%

128 of 128 vision models

Reasoning

53%

68 of 128 vision models

Web Search

35%

45 of 128 vision models

Image Output

5 of 128 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

ByteDance

vision models

Amazon

vision models

Perplexity

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-5.2 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
Claude Sonnet 4.5 Anthropic
Qwen3 VL 30B A3B Thinking Alibaba
Qwen3 VL 235B A22B Thinking Alibaba
GPT-5.2 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.

Full Leaderboard|Capability Matrix|Compare Models