20 Cheapest Models With a 1M-Token Context
Models with at least one million tokens of context, ranked by blended price. · verified 2026-10-11
#1 is Qwen3.7 Flash at $0.03 input and $0.13 output per million tokens.
// ranking
| # | model | lab | in $/1M | out $/1M | ctx |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Flash | Alibaba (Qwen) | $0.03 | $0.13 | 1M |
| 2 | Qwen Turbo | Alibaba (Qwen) | $0.05 | $0.20 | 1M |
| 3 | DeepSeek V4 Flash 0731 | DeepSeek | $0.06 | $0.18 | 1.05M |
| 4 | DeepSeek V4 Flash | DeepSeek | $0.09 | $0.18 | 1.05M |
| 5 | Qwen Flash | Alibaba (Qwen) | $0.05 | $0.40 | 1M |
| 6 | Qwen3.5 Flash | Alibaba (Qwen) | $0.10 | $0.40 | 1M |
| 7 | Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | |
| 8 | Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | 1M |
| 9 | GPT-6 Luna | OpenAI | $0.10 | $0.50 | 1.05M |
| 10 | Qwen3.8 Flash | Alibaba (Qwen) | $0.15 | $0.47 | 1M |
| 11 | Qwen3.8 Omni Flash | Alibaba (Qwen) | $0.15 | $0.47 | 1M |
| 12 | GLM-5.3-Flash | Z.AI (Zhipu) | $0.15 | $0.50 | 1M |
| 13 | Llama 4 Maverick 17B Instruct | Meta | $0.27 | $0.85 | 1.05M |
| 14 | Qwen3.6 Flash | Alibaba (Qwen) | $0.1875 | $1.125 | 1M |
| 15 | GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | 1.05M |
| 16 | MiniMax-M3 | MiniMax | $0.30 | $1.20 | 1M |
| 17 | Gemini 3.1 Flash Lite | $0.25 | $1.50 | 1.05M | |
| 18 | Qwen Plus | Alibaba (Qwen) | $0.40 | $1.20 | 1M |
| 19 | Qwen3 Coder Flash | Alibaba (Qwen) | $0.30 | $1.50 | 1M |
| 20 | DeepSeek V4 Flash Vision Exp | DeepSeek | $0.44 | $1.32 | 1.05M |