MiMo-V2.6-Flash
MiMo-V2.6-Flash is an Unknown open-weights model. It is not yet ranked: 1 independent result so far, and the index needs at least five across two categories. At $0.175 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 35 tokens per second puts it in the slowest quarter, with a first token in 3.3 s. Last measured 22 Sept 2026.
- Blended price
- $0.175/M
- $0.140 in · $0.280 out
- Output speed
- 35 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 3.25 s
- Context
- 1.0M
- Full answer
- –
- Cost per run
- –
- Released
- –
- date not published by our sources
- Agents & tools63
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Coding
| Benchmark | not stated | Source |
|---|---|---|
| Code Migrationnot in index | 40.9%#22 | Vals AI |
| Vibe Code Bench v1.1not in index | 79.0%#19 | Vals AI |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| Terminal-Bench 2.1 (Vals) | 76.4%#15 | Vals AI |
| Finance Agent v2not in index | 56.7%#13 | Vals AI |
| Harvey's Legal Agent Benchmarknot in index | 11.3%#8 | Vals AI |
| Legal Research Benchnot in index | 38.0%#26 | Vals AI |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| Excel Modeling Benchmarknot in index | 65.5%#18 | Vals AI |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| Vals Indexnot in index | 59.7#15 | Vals AI |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Xiaomi | 35 tok/s | 3.25 s | $0.140 | $0.280 | 1.0M | fp8 |
| DeepInfra | 10 tok/s | 2.31 s | $0.140 | $0.280 | 1.0M | fp8 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | 11.8 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0018 | – | 20.4 s |
| Code edit | 6,000 / 1,500 | $0.0013 | – | 46.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.0095 | – | 2.0 min |
| Structured extraction | 2,000 / 200 | $0.0003 | – | 9.0 s |
See also
Data as of 23 Sept 2026. Compare with another model.
Cite as: BenchLeader, “MiMo-V2.6-Flash: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/mimo-v2-6-flash, data as of 23 Sept 2026.