20 Cheapest Reasoning Models
Models with built-in reasoning, ranked by blended price. · verified 2026-10-11
#1 is Gemma 4 E2B IT at $0.04 input and $0.08 output per million tokens.
// ranking
| # | model | lab | in $/1M | out $/1M | ctx |
|---|---|---|---|---|---|
| 1 | Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | |
| 2 | Qwen3.7 Flash | Alibaba (Qwen) | $0.03 | $0.13 | 1M |
| 3 | DeepSeek R1 0528 Qwen3 8B | DeepSeek | $0.06 | $0.09 | 128K |
| 4 | Qwen Turbo | Alibaba (Qwen) | $0.05 | $0.20 | 1M |
| 5 | DeepSeek V4 Flash 0731 | DeepSeek | $0.06 | $0.18 | 1.05M |
| 6 | GPT OSS 120B | OpenAI | $0.05 | $0.25 | 131.1K |
| 7 | GPT OSS Safeguard 20B | OpenAI | $0.07 | $0.20 | 128K |
| 8 | Qwen3.5 9B | Alibaba (Qwen) | $0.10 | $0.15 | 262.1K |
| 9 | DeepSeek V4 Flash | DeepSeek | $0.09 | $0.18 | 1.05M |
| 10 | Qwen3 30B A3b fp8 | Alibaba (Qwen) | $0.0509 | $0.335 | 32.8K |
| 11 | gpt-oss-20b | OpenAI | $0.07 | $0.30 | 131.1K |
| 12 | Qwen Flash | Alibaba (Qwen) | $0.05 | $0.40 | 1M |
| 13 | Gemma 4 26B A4B IT | $0.07 | $0.34 | 262.1K | |
| 14 | GPT-5 Nano | OpenAI | $0.05 | $0.40 | 400K |
| 15 | GLM-4.7-Flash | Z.AI (Zhipu) | $0.0605 | $0.40 | 131.1K |
| 16 | GLM-4.7-FlashX | Z.AI (Zhipu) | $0.07 | $0.40 | 200K |
| 17 | Qwen3.5 Flash | Alibaba (Qwen) | $0.10 | $0.40 | 1M |
| 18 | Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | |
| 19 | Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | 1M |
| 20 | GPT-6 Luna | OpenAI | $0.10 | $0.50 | 1.05M |