Cheapest good LLM for general-purpose work
- Claude Haiku 5.5 leads
- $0.50
- models qualify
- 11
Output $/Mtok · 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, Anthropic Claude Haiku 5.5 is the cheapest model at or above the median Vals Index result, at $0.50 per million output tokens, ahead of DeepSeek V4.1 Flash 1017 ($0.60) and Xiaomi MiMo-V2.6-Pro ($0.87).
The full best LLM for general use ranking combines this benchmark with others.
| Rank | Model | Output $/Mtok | Coding evidence | Vals Index | Coding index |
|---|---|---|---|---|---|
| 1 | Claude Haiku 5.5 Anthropic | $0.50 | 58.7% | 70.7 | |
| 2 | DeepSeek V4.1 Flash 1017 DeepSeek | $0.60 | 61.3% | 70.3 | |
| 3 | MiMo-V2.6-Pro Xiaomi | $0.87 | 57.8% | 65.4 | |
| 4 | GLM 5.3 Z.ai | $4.40 | 59.7% | 70.6 | |
| 5 | Grok 4.7 xAI | $6.00 | 58.6% | 66.7 | |
| 6 | Claude Sonnet 5.5 Anthropic | $10.00 | 70.8% | 87.3 | |
| 7 | Gemini 4 Argon Google | $10.00 | 69.2% | 81.0 | |
| 8 | GPT-6.1 Sol OpenAI | $10.00 | 63.9% | 82.4 | |
| 9 | Claude Opus 5.5 Anthropic | $20.00 | 70.2% | 88.8 | |
| 10 | Muse Wonder Meta | $20.00 | 64.9% | 71.9 | |
| 11 | GPT-6 Astra OpenAI | $50.00 | 65.0% | 85.1 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models whose Vals Index result is at or above 57.8%, the median of every model on that board, ordered by output price, cheapest first. Free listings are left out: they are a tariff, not a price.
- OpenRouter, fetched
- Vals Index, fetched , board updated October 21, 2026