xiaomi
Xiaomi: MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
xiaomi/mimo-v2.6-flash is Xiaomi's MiMo-V2.6-Flash, listed on OpenRouter as a sparse Mixture-of-Experts model with 309B total parameters and 15B activated per token, hybrid attention, and a roughly 1M-token context window. The catalog and the linked XiaomiMiMo/MiMo-V2.6-Flash-RL model card describe omnimodal input (text, image, video, audio) with text output, optional reasoning, MIT licensing, and training centered on large-scale reinforcement learning for coding and agentic tasks. Published benchmark results are vendor-reported and not independently confirmed.[1][2]
Strengths
- Omnimodal inputs (text, image, video, audio) with text output, per the catalog and model card.[1][2]
- Roughly 1M-token context window, documented for long repositories, tool traces, and multi-session agent runs.[1][2]
- Agentic orientation: tool calling, parallel tool calls, structured outputs, and optional reasoning are supported; the card describes RL training for coding and agent tasks.[1][2]
Limitations
- Benchmark results come from Xiaomi's own model card; independent measurement is thin (the catalog shows only a third-party intelligence index, with coding and agentic indices absent), so workload validation is needed.[1][2]
- The documentation covers the MiMo-V2.6-Flash-RL checkpoint; its details may not map exactly onto the served xiaomi/mimo-v2.6-flash endpoint.[1][2]
- Knowledge cutoff is not disclosed, and self-hosting follows a documented multi-GPU recipe (tensor and data parallelism), so local deployment is heavyweight.[1][2]
Where to use it
Sources
- [1] OpenRouter catalog · Xiaomi: MiMo-V2.6-FlashSources checked: Nov 13, 2026
- [2] Model documentation · Xiaomi: MiMo-V2.6-FlashSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
Specifications
- Model ID
- xiaomi/mimo-v2.6-flash
- Canonical ID
- xiaomi/mimo-v2.6-flash-20260921
- Creator
- xiaomi
- Added to OpenRouter
- 21.09.2026
- Context length
- 1,050,000
- Modality
- text+image+audio+video->text
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.140 / out $0.280
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | BB — next 30% of the cohort | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 26.7 | BB — next 30% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Darkbloomfp4 | 1,048,576 | $0.100 | $0.280 | — | — | 94.74% |
| GMICloudbf16 | 1,050,000 | $0.112 | $0.224 | — | — | 100% |
| Coherefp8 | 1,048,576 | $0.140 | $0.280 | — | — | 100% |
| DeepInfrafp8 | 1,048,576 | $0.140 | $0.280 | — | — | 0% |
| Xiaomifp8 | 1,048,576 | $0.140 | $0.280 | — | — | 100% |
| Tenstorrentfp8 | 1,048,576 | $0.165 | $0.330 | — | — | 100% |
| Venicefp8 | 1,000,000 | $0.175 | $0.350 | — | — | 86.67% |
| Makorafp8 | 1,048,576 | $0.180 | $0.360 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.