20 Cheapest Gemini Alternatives
Non-Google models with image input, ranked by blended price. · verified 2026-11-17
#1 is DeepSeek OCR 2 at $0.03 input and $0.03 output per million tokens.
// ranking
| # | model | lab | in $/1M | out $/1M | ctx |
|---|---|---|---|---|---|
| 1 | DeepSeek OCR 2 | DeepSeek | $0.03 | $0.03 | 8.2K |
| 2 | Qwen3.7 Flash | Alibaba (Qwen) | $0.03 | $0.13 | 1M |
| 3 | AutoGLM Phone 9B Multilingual | Z.AI (Zhipu) | $0.035 | $0.138 | 65.5K |
| 4 | Qwen-VL OCR | Alibaba (Qwen) | $0.07 | $0.16 | 34.1K |
| 5 | Ministral 3 3B | Mistral | $0.10 | $0.10 | 131.1K |
| 6 | Qwen3.5 9B | Alibaba (Qwen) | $0.10 | $0.15 | 262.1K |
| 7 | GPT-5 Nano | OpenAI | $0.05 | $0.40 | 400K |
| 8 | Llama 4 Scout 17B | Meta | $0.10 | $0.30 | 327.7K |
| 9 | Ministral 3 8B | Mistral | $0.15 | $0.15 | 262.1K |
| 10 | Mistral Small 3.1 24B | Mistral | $0.10 | $0.30 | 128K |
| 11 | Qwen3.5 Flash | Alibaba (Qwen) | $0.10 | $0.40 | 1M |
| 12 | Llama Guard 4 12B | Meta | $0.18 | $0.18 | 163.8K |
| 13 | Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | 1M |
| 14 | Muse Ember | Meta | $0.10 | $0.50 | 1.05M |
| 15 | Ministral 3 14B | Mistral | $0.20 | $0.20 | 262.1K |
| 16 | GPT-6 Luna | OpenAI | $0.10 | $0.50 | 1.05M |
| 17 | Llama 3.2 11B Vision Instruct | Meta | $0.0485 | $0.676 | 128K |
| 18 | Qwen3.8 Flash | Alibaba (Qwen) | $0.15 | $0.47 | 1M |
| 19 | Qwen3.8 Omni Flash | Alibaba (Qwen) | $0.15 | $0.47 | 1M |
| 20 | GLM-5.3-Flash | Z.AI (Zhipu) | $0.15 | $0.50 | 1M |
// how this ranking works
Non-Google models with image input, ranked by blended price. Only active models with a published price and context window are included. Prices are base-tier list prices in USD per million tokens; the blended price weights input and output 3:1, a typical mix for chat and RAG workloads. The data comes from models.dev and is refreshed every day, so this ranking changes as soon as a provider changes its prices.