LLM Perks

Free vision models

Models that accept images as input: Gemini, Gemma, Llama 4, Qwen-VL, Nemotron Omni, and more.

37 models9 providersup to 10.5M contextbest: Gemini 3.8 FlashUpdated:
Read more

Image support depends on the provider: some routers expose a multimodal model in text-only mode.

Size
37 found
# Model ↕ AA Index ↕ GPQA ↕ Context ↕ Size ↕ Free at ↕
1
Gemini 3.8 Flash
Google
VisionReasoningCodingTool use
40.9 95% 1M Mid-size Google AI Studio
2
Gemini 3.6 Flash
Google
VisionReasoningCodingTool use
34.0 93% 1M Mid-size UnoRouter
3
Gemma 4 31B
Google DeepMind · 31B
VisionTool useOpen weights
19.0 86% 262K Mid-size OpenRouter, Together AI, NVIDIA Build, UnoRouter
4
Gemini 3.5 Flash Lite
Google
VisionReasoningCoding
22.2 84% 1M Small UnoRouter
5
Gemma 4 26B A4B
Google DeepMind · 26B · 4B
VisionTool useOpen weights
16.7 79% 262K Mid-size OpenRouter, Together AI, Cloudflare Workers AI, UnoRouter
6
Gemini 3.1 Flash Lite
Google
VisionReasoningCoding
15.6 82% 1M Small UnoRouter
7
Gemma 4 12B
Google DeepMind · 12B
VisionTool useOpen weights
14.2 75% 262K Mid-size Together AI, UnoRouter
8
Llama 4 Maverick Instruct Fp4
Meta · 400B · 17B
VisionTool useOpen weights
— — 1M Frontier Together AI
9
Nemotron 3 Nano Omni
NVIDIA · 30B · 3B
VisionReasoningTool useOpen weights
10.3 47% 262K Mid-size +1OpenRouter, Together AI, NVIDIA Build, TokenRouter, UnoRouter
10
Qwen3 VL 235B
Alibaba Cloud · 235B · 22B
VisionReasoningTool useOpen weights
13.4 77% 262K Frontier Together AI
11
Nemotron 3.5 Super VL
NVIDIA
VisionReasoningTool useOpen weights
— — 1M Mid-size OpenRouter, UnoRouter, OpenCode Zen
12
Nemotron 3.5 Super VL 120B
NVIDIA · 120B · 12B
VisionReasoningTool useOpen weights
— — — Frontier NVIDIA Build
13
Qwen2.5 VL 72B
Alibaba Cloud · 72B · New
VisionTool useOpen weights
— — 32K Frontier UnoRouter
14
Llama 4 Scout
Meta · 109B · 17B
VisionTool useOpen weights
8.1 59% 10.5M Frontier Together AI, Cloudflare Workers AI, UnoRouter
15
Gemma 4 26B IT Chimerax
Google DeepMind · 26B · 4B
VisionTool useOpen weights
— — 262K Mid-size UnoRouter
16
Gemma 4 26B IT Darksoul
Google DeepMind · 26B · 4B
VisionTool useOpen weights
— — 262K Mid-size UnoRouter
17
Gemma 4 26B IT Luminous
Google DeepMind · 26B · 4B
VisionTool useOpen weights
— — 262K Mid-size UnoRouter
18
Gemma 4 26B IT Meromero
Google DeepMind · 26B · 4B
VisionTool useOpen weights
— — 262K Mid-size UnoRouter
19
Gemma 4 26B IT Moonlight
Google DeepMind · 26B · 4B
VisionTool useOpen weights
— — 262K Mid-size UnoRouter
20
Llama 3.2 11B Vision
Meta · 11B
VisionTool useOpen weights
5.4 22% 131K Mid-size Together AI, Cloudflare Workers AI, NVIDIA Build, UnoRouter
21
C4ai Aya Vision 32B
Cohere · 32B
VisionTool use
— — 16K Mid-size Cohere
22
Gemma 4 E4b
Google DeepMind
VisionOpen weights
8.9 58% 131K Small Together AI
23
GPT-4o
OpenAI
VisionTool use
8.4 54% 128K Frontier UnoRouter
24
Llama 3.2 90B Vision
Meta · 90B
VisionTool useOpen weights
6.4 43% 16K Frontier Together AI, NVIDIA Build
25
Gemma 4 E2b
Google DeepMind
VisionOpen weights
7.8 43% 131K Small Together AI
26
Gemma 3 4B
Google DeepMind · 4B
VisionOpen weights
4.8 29% 66K Small Together AI, NVIDIA Build
27
Command A Vision 07 2025
Cohere · 111B · Legacy
Vision
— — 128K Frontier Cohere
28
clef-omni
Vision
— — 66K Small Cloudflare Workers AI
29
Cosmos Reason2 8B
NVIDIA · 8B
VisionReasoning
— — — Small NVIDIA Build
30
Qwen2.5 VL 7B
Alibaba Cloud · 7B
VisionOpen weights
— — 33K Small UnoRouter
31
Gemma 3 27B
Google DeepMind · 27B
VisionTool useOpen weights
4.9 43% 66K Mid-size Together AI
32
Gemma 3 12B
Google DeepMind · 12B
VisionTool useOpen weights
3.8 35% 128K Mid-size NVIDIA Build
33
Neva 22B
NVIDIA · 22B · Legacy
Vision
— — — Mid-size NVIDIA Build
34
Fuyu 8B
Adept · 8B · Legacy
Vision
— — — Small NVIDIA Build
35
Kosmos 2
Microsoft · Legacy
Vision
— — — Small NVIDIA Build
36
Phi 3 Vision 128K
Microsoft · 4.2B · Legacy
VisionOpen weights
— — 131K Small NVIDIA Build
37
Vila
NVIDIA · Legacy
Vision
— — — Small NVIDIA Build

Benchmarks: Artificial Analysis (September 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.

FAQ

What is the best free model for vision (image input)?

Gemini 3.8 Flash currently leads — free at Google AI Studio. Next come Gemini 3.6 Flash, Gemma 4 31B, Gemini 3.5 Flash Lite.

See also