Best cheap LLM (October 2026)
As of 21 Oct 2026, the best cheap LLM (under $2 per million tokens) on independent benchmarks is Gemini 3.8 Flash (high) by Google (index 64.5 at $1.50/M), ahead of MiMo-V2.6-Pro (index 64.2 at $0.55/M) and Gemini 3.7 Flash (high) (index 63.5 at $0.76/M).
The highest-quality models with a blended list price below $2 per million tokens (three input tokens per output token), ranked on the BenchLeader Index.
199 models qualify · data as of 21 Oct 2026 · rebuilt once a day (the run starts at 22:03 UTC)
Gemini 3.8 Flash high#1 here: index 64.5 at $1.50/MBest value
DeepSeek V4 Flash maxmost index points per dollar among the top 15 (61.1 at $0.175/M)Best open weights
MiMo-V2.6-Pro highest-ranked model here you can run yourself (#2)Fastest of the top 15 Gemini 3.6 Flash high214 output tokens per secondHead to head: Gemini 3.8 Flash vs MiMo-V2.6-Pro (#1 vs #2) · Gemini 3.8 Flash vs Gemini 3.7 Flash (#1 vs #3) · MiMo-V2.6-Pro vs Gemini 3.7 Flash (#2 vs #3)
| # | Model | Index | Price $/M | Speed tok/s |
|---|---|---|---|---|
| 1 | Gemini 3.8 FlashhighGoogle | 64.5 | $1.50 | 144 |
| 2 | MiMo-V2.6-ProXiaomi | 64.2 | $0.548 | 50 |
| 3 | Gemini 3.7 FlashhighGoogle | 63.5 | $0.755 | 80 |
| 4 | DeepSeek V4.1 Flash 1017maxDeepSeek | 63.1 | $0.525 | 209 |
| 5 |  GLM 5.3 FlashZhipu AI | 62.8 | $0.238 | 77 |
| 6 | DeepSeek V4 PromaxDeepSeek | 62.7 | $1.98 | 103 |
| 7 | Gemini 3.6 FlashhighGoogle | 62.1 | $1.50 | 214 |
| 8 |  MiniMax-M3.1-FlashMiniMax | 61.9 | $0.262 | 105 |
| 9 |  Claude Haiku 5.5xhighAnthropic | 61.5 | $0.200 | 192 |
| 10 | DeepSeek V4 FlashmaxDeepSeek | 61.1 | $0.175 | 145 |
| 11 |  Step 5 PreviewStepFun | 60.6 | $1.43 | 92 |
| 12 |  Qwen3.8-Flash-NextAlibaba | 60.3 | $0.230 | 52 |
| 13 |  GPT-6 LunamaxOpenAI | 60.1 | $0.200 | 124 |
| 14 | GPT-5.6 LunamaxOpenAI | 59.9 | $0.450 | 134 |
| 15 | MiMo-V2.6-FlashXiaomi | 59.8 | $0.175 | 53 |
Full ranked list (199 models) · Gemini 3.8 Flash vs MiMo-V2.6-Pro · Best for high-volume extraction, with the weighting stated · Methodology · the LLM benchmarks behind this ranking
Best cheap LLM: questions
- What is the best cheap LLM (under $2 per million tokens) in October 2026?
- As of 21 Oct 2026, the best cheap LLM (under $2 per million tokens) on independent benchmarks is Gemini 3.8 Flash (high) by Google (index 64.5 at $1.50/M), ahead of MiMo-V2.6-Pro (index 64.2 at $0.55/M) and Gemini 3.7 Flash (high) (index 63.5 at $0.76/M). BenchLeader reconciles 229 benchmarks from 43 benchmark publishers and rebuilds the ranking once a day (the run starts at 22:03 UTC).
- Which is the best value?
- DeepSeek V4 Flash (max) gives the most BenchLeader Index points per dollar among the top 15 here: 61.1 at $0.175 per million tokens blended, against $1.50 for Gemini 3.8 Flash.
- What is the best open-weights option?
- MiMo-V2.6-Pro by Xiaomi is the highest-ranked open-weights model on this list, at #2.
- How is this ranked?
- The highest-quality models with a blended list price below $2 per million tokens (three input tokens per output token), ranked on the BenchLeader Index. Every score comes from an independent publisher and links to its source on the model page; self-reported launch numbers are excluded.
Cite as: BenchLeader, “Best cheap LLM (October 2026)”, https://www.benchleader.com/best/cheap-llm, data as of 21 Oct 2026.