Best LLM under $1 per million tokens
- MiMo-V2.6-Pro leads
- 68.4
- budget, per M output
- $1
- models fit
- 35
- lead over #2
- +0.8
Overall index · read October 22
Cheapest output, $ per million tokens
- S Llama 3 8B Lunaris $0.05
- Gemma 3 4B $0.075
- Mistral Small 3 $0.08
- Llama 3.1 8B Instruct $0.08
- N Nex-N2.5-Mini $0.10
- Reka Edge $0.10
- Ministral 3 3B 2512 $0.10
- Granite 4.0 Micro $0.112
As of October 22, 2026, Xiaomi MiMo-V2.6-Pro leads 35 models that qualify, with 68.4 on the overall index, ahead of Anthropic Claude Haiku 5.5 (67.6) and DeepSeek V4.1 Flash 1017 (67.6).
| Rank | Model | Overall index | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | MiMo-V2.6-Pro Xiaomi | 68.4 | 65.4 | $0.87 | |
| 2 | Claude Haiku 5.5 Anthropic | 67.6 | 70.7 | $0.50 | |
| 3 | DeepSeek V4.1 Flash 1017 DeepSeek | 67.6 | 70.3 | $0.60 | |
| 4 | GLM 5.3 Flash Z.ai | 66.0 | 57.7 | $0.50 | |
| 5 | DeepSeek V4.1 Flash DeepSeek | 62.4 | 62.5 | $0.84 | |
| 6 | MiMo-V2.6-Flash Xiaomi | 60.8 | 54.7 | $0.28 | |
| 7 | GPT-6 Luna OpenAI | 59.7 | 57.3 | $0.50 | |
| 8 | DeepSeek V4 Flash 0731 DeepSeek | 55.2 | 51.8 | $0.396 | |
| 9 | Gemma 4 26B A4B Google | 54.7 | Not enough data | $0.60 | |
| 10 | MiMo-V2.5 Xiaomi | 50.7 | 50.0 | $0.336 | |
| 11 | Qwen3.5-Flash Qwen | 50.1 | 41.1 | $0.26 | |
| 12 | gpt-oss-120b OpenAI | 50.0 | Not enough data | $0.50 | |
| 13 | Qwen3.6 35B A3B Qwen | 45.0 | Not benchmarked | $1.00 | |
| 14 | Gemma 4 31B Google | 42.1 | 39.0 | $0.40 | |
| 15 | GLM 4.7 Flash Z.ai | 42.1 | Not benchmarked | $0.40 | |
| 16 | 41.5 | Not benchmarked | $0.30 | ||
| 17 | Qwen3 32B Qwen | 40.8 | Not benchmarked | $0.40 | |
| 18 | MiMo-V2.5-Pro Xiaomi | 39.3 | 31.6 | $0.9152 | |
| 19 | gpt-oss-20b OpenAI | 38.5 | Not benchmarked | $0.15 | |
| 20 | Qwen3 30B A3B Qwen | 38.2 | Not benchmarked | $0.50 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models with a paid output price of $1 or less per million tokens on OpenRouter, ordered by the LLMBenchmark Index, highest first. The index is our own 0 to 100 composite of our five skill indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.
- OpenRouter, fetched
- LMArena WebDev, fetched
- Artificial Analysis (via OpenRouter), fetched