20 Cheapest LLM APIs
The lowest blended price per million tokens across every tracked model. · verified 2026-10-11
#1 is Llama 3.2 1B Instruct at $0.02 input and $0.02 output per million tokens.
// ranking
| # | model | lab | in $/1M | out $/1M | ctx |
|---|---|---|---|---|---|
| 1 | Llama 3.2 1B Instruct | Meta | $0.02 | $0.02 | 131K |
| 2 | Llama-3.1-8B-Instruct | Meta | $0.02 | $0.05 | 16.4K |
| 3 | DeepSeek OCR 2 | DeepSeek | $0.03 | $0.03 | 8.2K |
| 4 | Qwen3-ASR Flash | Alibaba (Qwen) | $0.035 | $0.035 | 53.2K |
| 5 | Voxtral Mini 3B 2507 | Mistral | $0.04 | $0.04 | 32.8K |
| 6 | Gemma 3 4B IT | $0.04 | $0.08 | 131.1K | |
| 7 | Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | |
| 8 | Qwen3.7 Flash | Alibaba (Qwen) | $0.03 | $0.13 | 1M |
| 9 | AutoGLM Phone 9B Multilingual | Z.AI (Zhipu) | $0.035 | $0.138 | 65.5K |
| 10 | Gemma 3 12B IT | $0.05 | $0.10 | 131.1K | |
| 11 | Command R7B | Cohere | $0.0375 | $0.15 | 128K |
| 12 | Command R7B Arabic | Cohere | $0.0375 | $0.15 | 128K |
| 13 | DeepSeek R1 0528 Qwen3 8B | DeepSeek | $0.06 | $0.09 | 128K |
| 14 | Llama 3.2 1B Instruct | Meta | $0.027 | $0.201 | 60K |
| 15 | Qwen Turbo | Alibaba (Qwen) | $0.05 | $0.20 | 1M |
| 16 | DeepSeek V4 Flash 0731 | DeepSeek | $0.06 | $0.18 | 1.05M |
| 17 | Qwen-VL OCR | Alibaba (Qwen) | $0.07 | $0.16 | 34.1K |
| 18 | Gemma 3 27B IT | $0.08 | $0.16 | 131.1K | |
| 19 | Ministral 3 3B | Mistral | $0.10 | $0.10 | 131.1K |
| 20 | GPT OSS 120B | OpenAI | $0.05 | $0.25 | 131.1K |