Best LLM under $15 per million tokens
- Gemini 4 Argon leads
- 84.0
- budget, per M output
- $15
- models fit
- 111
- lead over #2
- +1.2
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, Google Gemini 4 Argon leads 111 models that qualify, with 84.0 on the overall index, ahead of Anthropic Claude Sonnet 5.5 (82.8) and OpenAI GPT-6.1 Sol (81.4).
| Rank | Model | Overall index | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Gemini 4 Argon Google | 84.0 | 81.0 | $10.00 | |
| 2 | Claude Sonnet 5.5 Anthropic | 82.8 | 87.3 | $10.00 | |
| 3 | GPT-6.1 Sol OpenAI | 81.4 | 82.4 | $10.00 | |
| 4 | GPT-6 Sol OpenAI | 74.6 | 76.0 | $10.00 | |
| 5 | GPT-5.4 OpenAI | 69.6 | 64.4 | $15.00 | |
| 6 | Gemini 3.8 Flash Google | 69.0 | 61.6 | $3.75 | |
| 7 | Qwen3.8 Max (0902) Qwen | 68.9 | 62.4 | $6.00 | |
| 8 | Muse Spark 1.3 Meta | 68.6 | 57.4 | $4.25 | |
| 9 | MiMo-V2.6-Pro Xiaomi | 68.4 | 65.4 | $0.87 | |
| 10 | Gemini 3.6 Flash Google | 68.3 | 62.5 | $3.75 | |
| 11 | GPT-5.6 Terra OpenAI | 68.1 | 63.9 | $12.00 | |
| 12 | GLM 5.3 Z.ai | 67.9 | 70.6 | $4.40 | |
| 13 | Claude Haiku 5.5 Anthropic | 67.6 | 70.7 | $0.50 | |
| 14 | DeepSeek V4.1 Flash 1017 DeepSeek | 67.6 | 70.3 | $0.60 | |
| 15 | Grok 4.6 xAI | 67.4 | 65.7 | $6.00 | |
| 16 | Muse Spark 1.1 Meta | 67.0 | 70.3 | $4.25 | |
| 17 | Grok 4.7 xAI | 66.6 | 66.7 | $6.00 | |
| 18 | Kimi K3 Moonshot AI | 66.5 | 62.3 | $15.00 | |
| 19 | GLM 5.3 Flash Z.ai | 66.0 | 57.7 | $0.50 | |
| 20 | Gemini 3.7 Flash Google | 65.7 | 58.0 | $3.75 |
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 $15 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
- Artificial Analysis (via OpenRouter), fetched
- LMArena WebDev, fetched