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 2026-10-28 12:57 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 | Qwen2 VL 7B Instruct | Nebius | $0.02 | $0.06 | — | 131K |
| 8 | Paddleocr Vl | Novita AI | $0.02 | $0.02 | — | 16K |
| 9 | Deepseek Ocr | Novita AI | $0.03 | $0.03 | — | 8K |
| 10 | Deepseek Ocr 2 | Novita AI | $0.03 | $0.03 | — | 8K |
| 11 | Autoglm Phone 9b Multilingual | Novita AI | $0.035 | $0.138 | — | 66K |
| 12 | Llama 3.2 11b Vision Instruct | Cloudflare Workers AI | $0.049 | $0.676 | — | 128K |
| 13 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 14 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 15 | GPT 5 Nano | Azure OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 16 | Gemma 3 12b It | Novita AI | $0.05 | $0.1 | — | 131K |
| 17 | GPT 5 Nano | Azure OpenAI | $0.055 | $0.44 | $0.0055 | 272K |
| 18 | Nemotron 3 Nano Omni | Nebius | $0.06 | $0.24 | — | 262K |
| 19 | Gemma 4 26B A4B It | DeepInfra | $0.07 | $0.34 | — | 262K |
| 20 | Amazon.nova Lite V1:0 | Amazon Bedrock | $0.072 | $0.288 | $0.018 | 300K |
| 21 | Qwen3 Vl 8b Instruct | Novita AI | $0.08 | $0.5 | — | 131K |
| 22 | Gemma 4 31B It Turbo | DeepInfra | $0.09 | $0.34 | $0.05 | 262K |
| 23 | Claude Haiku 5 5 | Anthropic | $0.1 | $0.5 | $0.01 | 1M |
| 24 | Gemini 2.5 Flash Lite | Google Gemini | $0.1 | $0.4 | $0.01 | 1.0M |
| 25 | Muse Spark 1.2 Contributor | Meta | $0.1 | $0.2 | $0.002 | 1.0M |
| 26 | Muse Spark 1.3 Contributor | Meta | $0.1 | $0.2 | $0.002 | 1.0M |
| 27 | Ministral 3b 2512 | Mistral AI | $0.1 | $0.1 | $0.01 | 131K |
| 28 | Ministral 3b | Mistral AI | $0.1 | $0.1 | $0.01 | 131K |
| 29 | Ministral 3 3b 2512 | Mistral AI | $0.1 | $0.1 | $0.01 | 131K |
| 30 | GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 31 | GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 32 | GPT 6 Luna | OpenAI | $0.1 | $0.5 | $0.01 | 922K |
| 33 | GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 34 | GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | $0.025 | 1.0M |
| 35 | GPT 6 Luna | Azure OpenAI | $0.1 | $0.5 | $0.01 | 922K |
| 36 | GPT 6 Luna | Azure OpenAI | $0.1 | $0.5 | $0.01 | 922K |
| 37 | Claude Haiku 5 5 | Amazon Bedrock | $0.1 | $0.5 | $0.01 | 1M |
| 38 | Qwen3.6 35B A3B | DeepInfra | $0.1 | $0.95 | — | 262K |
| 39 | Seed 2.0 Mini | DeepInfra | $0.1 | $0.4 | $0.02 | 256K |
| 40 | Qwen3.5 9B | DeepInfra | $0.1 | $0.15 | — | 262K |
| 41 | Gemma 3 27b It | Nebius | $0.1 | $0.3 | — | 110K |
| 42 | Cosmos3 Super Reasoner | Nebius | $0.1 | $0.3 | — | 262K |
| 43 | Gemma 3 27b It | Novita AI | $0.119 | $0.2 | — | 98K |
| 44 | Anthropic.claude Haiku 5 5 | Amazon Bedrock | $0.12 | $0.6 | $0.012 | 1M |
| 45 | Gemma 4 31B It | DeepInfra | $0.13 | $0.38 | — | 262K |
| 46 | Qwen2 VL 72B Instruct | Nebius | $0.13 | $0.4 | — | 131K |
| 47 | Gemma 4 26b A4b It | Novita AI | $0.13 | $0.4 | — | 262K |
| 48 | Model Router | Azure OpenAI | $0.14 | free | — | 200K |
| 49 | Qwen3.5 35B A3B | DeepInfra | $0.14 | $1 | $0.05 | 262K |
| 50 | DeepSeek V4.1 Flash | DeepInfra | $0.14 | $0.42 | $0.0042 | 1.0M |
| 51 | DeepSeek V4.1 Flash 1017 | DeepInfra | $0.14 | $0.42 | $0.0042 | 1.0M |
| 52 | Ernie 4.5 Vl 28b A3b | Novita AI | $0.14 | $0.56 | — | 30K |
| 53 | Gemma 4 31b It | Novita AI | $0.14 | $0.4 | — | 262K |
| 54 | Qwen3.8 Flash | Alibaba DashScope | $0.15 | $0.47 | $0.016 | 992K |
| 55 | Qwen3.8 Omni Flash | Alibaba DashScope | $0.15 | $0.47 | $0.016 | 992K |
| 56 | Zai Glm 5 3 Flash | Mistral AI | $0.15 | $0.5 | $0.03 | 1.0M |
| 57 | Magistral Small | Mistral AI | $0.15 | $0.6 | $0.015 | 262K |
| 58 | Mistral Small | Mistral AI | $0.15 | $0.6 | $0.015 | 262K |
| 59 | Ministral 3 8b 2512 | Mistral AI | $0.15 | $0.15 | $0.015 | 262K |
| 60 | Ministral 8b 2512 | Mistral AI | $0.15 | $0.15 | $0.015 | 262K |
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.