Cheapest good LLM for overall intelligence
- Ling 3.0 Flash leads
- $0.063
- models qualify
- 107
Output $/Mtok · read October 21
Cheapest output, $ per million tokens
- Mistral Nemo $0.03
- Gemma 3 4B $0.05
- S Llama 3 8B Lunaris $0.05
- Ling 3.0 Flash $0.063
- Mistral Small 3 $0.08
- Llama 3.1 8B Instruct $0.08
- gpt-oss-20b $0.09
- N Nex-N2.5-Mini $0.10
As of October 21, 2026, inclusionAI Ling 3.0 Flash is the cheapest model at or above the median AA Intelligence Index result, at $0.063 per million output tokens, ahead of inclusionAI Ling 3.0 Flash VL ($0.18) and DeepSeek V4 Flash 0423 ($0.182).
This list narrows the best LLM for overall intelligence ranking.
| Rank | Model | Output $/Mtok | Coding evidence | AA Intelligence Index | Coding index |
|---|---|---|---|---|---|
| 1 | Ling 3.0 Flash inclusionAI | $0.063 | 20.1 | Not benchmarked | |
| 2 | Ling 3.0 Flash VL inclusionAI | $0.18 | 24.6 | Not benchmarked | |
| 3 | DeepSeek V4 Flash 0423 DeepSeek | $0.182 | 24.4 | 54.6 | |
| 4 | Solar Mini 4 Upstage | $0.20 | 24.1 | Not benchmarked | |
| 5 | Ling 3.1 Flash inclusionAI | $0.225 | 41.1 | Not benchmarked | |
| 6 | MiMo-V2.5 Xiaomi | $0.238 | 21.8 | 34.0 | |
| 7 | MiMo-V2.6-Flash Xiaomi | $0.28 | 37.9 | 61.9 | |
| 8 | DeepSeek V3.2 DeepSeek | $0.42 | 21.5 | 54.4 | |
| 9 | Claude Haiku 5.5 Anthropic | $0.50 | 43.4 | 75.9 | |
| 10 | GLM 5.3 Flash Z.ai | $0.50 | 41.8 | 71.0 | |
| 11 | GPT-6 Luna OpenAI | $0.50 | 38.1 | 71.4 | |
| 12 | Nemotron 3.5 Super VL NVIDIA | $0.50 | 26.5 | 65.5 | |
| 13 | DeepSeek V4.1 Flash DeepSeek | $0.525 | 24.7 | 77.2 | |
| 14 | DeepSeek V4.1 Flash 1017 DeepSeek | $0.60 | 39.5 | 83.3 | |
| 15 | Solar Pro 4 Upstage | $0.60 | 28.2 | 24.4 | |
| 16 | Hy3 preview Tencent | $0.60 | 25.3 | 22.4 | |
| 17 | MiMo-V2.5-Pro Xiaomi | $0.609 | 26.0 | 40.0 | |
| 18 | DeepSeek V4 Flash Vision Exp DeepSeek | $0.6468 | 34.8 | 37.6 | |
| 19 | MiMo-V2.6-Pro Xiaomi | $0.87 | 46.3 | 72.6 | |
| 20 | MiniMax M2.5 MiniMax | $0.95 | 22.8 | 59.4 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models whose AA Intelligence Index result is at or above 18.5, 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
- Artificial Analysis (via OpenRouter), fetched