Cheapest vision models
Models that accept images, sorted by input cost. Useful for OCR, screenshot QA and document extraction at scale.
Current leader: Gemini Exp 1114 (Google Gemini). Refreshed 2026-09-13 13:40 UTC.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 3 27b It | Google Gemini | free | free | — | 131K |
| 4 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 5 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 6 | Learnlm 1.5 Pro Experimental | Google Gemini | free | free | — | 33K |
| 7 | Anthropic.claude Mythos Preview | Amazon Bedrock | free | free | — | 1M |
| 8 | Auto | OpenRouter | free | free | — | 2M |
| 9 | Free | OpenRouter | free | free | — | 200K |
| 10 | Nemotron 3.5 Content Safety:free | OpenRouter | free | free | — | 128K |
| 11 | Minimax M3:free | OpenRouter | free | free | — | 1.0M |
| 12 | Nemotron 3 Nano Omni 30b A3b Reasoning:free | OpenRouter | free | free | — | 256K |
| 13 | Gemma 4 26b A4b It:free | OpenRouter | free | free | — | 262K |
| 14 | Gemma 4 31b It:free | OpenRouter | free | free | — | 262K |
| 15 | Qwen2 VL 7B Instruct | Nebius | $0.02 | $0.06 | — | 131K |
| 16 | Paddleocr Vl | Novita AI | $0.02 | $0.02 | — | 16K |
| 17 | Deepseek Ocr | Novita AI | $0.03 | $0.03 | — | 8K |
| 18 | Deepseek Ocr 2 | Novita AI | $0.03 | $0.03 | — | 8K |
| 19 | Qwen3.7 Flash | OpenRouter | $0.03 | $0.13 | $0.006 | 1M |
| 20 | Autoglm Phone 9b Multilingual | Novita AI | $0.035 | $0.138 | — | 66K |
| 21 | Gemma 4 26b A4b It | OpenRouter | $0.042 | $0.22 | — | 262K |
| 22 | Llama 3.2 11b Vision Instruct | Cloudflare Workers AI | $0.049 | $0.676 | — | 128K |
| 23 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 24 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 25 | GPT 5 Nano | Azure OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 26 | Gemma 3 12b It | Novita AI | $0.05 | $0.1 | — | 131K |
| 27 | Gemma 3 4b It | OpenRouter | $0.05 | $0.1 | — | 131K |
| 28 | Gemma 3 12b It | OpenRouter | $0.05 | $0.15 | — | 131K |
| 29 | GPT 5 Nano | Azure OpenAI | $0.055 | $0.44 | $0.0055 | 272K |
| 30 | Mistral Small 3 2 2506 | Mistral AI | $0.06 | $0.18 | — | 131K |
| 31 | Nemotron 3 Nano Omni | Nebius | $0.06 | $0.24 | — | 262K |
| 32 | Glm 4.7 Flash | OpenRouter | $0.06 | $0.4 | $0.01 | 200K |
| 33 | Qwen3.5 Flash 02 23 | OpenRouter | $0.065 | $0.26 | — | 1M |
| 34 | Gemma 4 26B A4B It | DeepInfra | $0.07 | $0.34 | — | 262K |
| 35 | Amazon.nova Lite V1:0 | Amazon Bedrock | $0.072 | $0.288 | — | 300K |
| 36 | Gemini 2.0 Flash Lite | Google Gemini | $0.075 | $0.3 | $0.019 | 1.0M |
| 37 | Gemini 2.0 Flash Lite 001 | Google Gemini | $0.075 | $0.3 | $0.019 | 1.0M |
| 38 | Qwen3 Vl 8b Instruct | Novita AI | $0.08 | $0.5 | — | 131K |
| 39 | Gemma 3 27b It | OpenRouter | $0.08 | $0.45 | $0.04 | 131K |
| 40 | Gemma 4 31B It Turbo | DeepInfra | $0.09 | $0.34 | $0.05 | 262K |
| 41 | Gemma 4 31b It | OpenRouter | $0.09 | $0.34 | $0.05 | 262K |
| 42 | Gemini 2.0 Flash | Google Gemini | $0.1 | $0.4 | $0.025 | 1.0M |
| 43 | Gemini 2.0 Flash 001 | Google Gemini | $0.1 | $0.4 | $0.025 | 1.0M |
| 44 | Gemini 2.5 Flash Lite | Google Gemini | $0.1 | $0.4 | $0.01 | 1.0M |
| 45 | Gemini 2.5 Flash Lite Preview 09 2025 | Google Gemini | $0.1 | $0.4 | $0.01 | 1.0M |
| 46 | Gemini Flash Lite | Google Gemini | $0.1 | $0.4 | $0.01 | 1.0M |
| 47 | Gemini 2.5 Flash Lite Preview 06 17 | Google Gemini | $0.1 | $0.4 | $0.01 | 1.0M |
| 48 | Muse Spark 1.2 Contributor | Meta | $0.1 | $0.2 | $0.002 | 1.0M |
| 49 | Muse Spark 1.3 Contributor | Meta | $0.1 | $0.2 | $0.002 | 1.0M |
| 50 | Ministral 3b 2512 | Mistral AI | $0.1 | $0.1 | $0.01 | 131K |
| 51 | Ministral 3b | Mistral AI | $0.1 | $0.1 | $0.01 | 131K |
| 52 | Ministral 3 3b 2512 | Mistral AI | $0.1 | $0.1 | $0.01 | 131K |
| 53 | GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 54 | GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 55 | GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 56 | GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 57 | Qwen3.6 35B A3B | DeepInfra | $0.1 | $0.95 | — | 262K |
| 58 | Seed 2.0 Mini | DeepInfra | $0.1 | $0.4 | $0.02 | 256K |
| 59 | Qwen3.5 9B | DeepInfra | $0.1 | $0.15 | — | 262K |
| 60 | Gemma 3 27b It | Nebius | $0.1 | $0.3 | — | 110K |
Other use cases
Frequently asked
› Which vision model is cheapest per token?
Gemini Exp 1114 from Google Gemini currently leads this list, at $0/1M input tokens. Rankings are recomputed from the raw dataset on every refresh, so they track price cuts automatically.
› How are these rankings calculated?
Each use case applies a capability filter (context size, vision, tool calling, cache pricing) and then ranks the surviving models by the blended cost that profile actually pays. See the methodology page for the exact formulas.
› Is the cheapest model always the right choice?
No. Check the capability flags and context window, and benchmark quality on your own data — the cheapest model that fails your evals costs more than the second cheapest that passes them.