MiMo-V2.6-Flash
Xiaomi · released Sep 21, 2026
- Type
- Closed
- Input
- $0.14
- Output
- $0.28
- Cached
- $0.003
List price · per 1M tokens · Xiaomi at 1M context · source ↗
Our take
Written Sep 30, 2026MiMo-V2.6-Flash is a hosted-only model from Xiaomi, so using it means choosing a host rather than running it yourself. Its measured results are uneven: it places 17th of 168 on Arena Coding as of 25 Sep 2026, but 72nd of 168 on Arena Creative Writing on the same date.
Reach for it on coding prompts, where it places 17th of 168 on Arena Coding as of 25 Sep 2026, and for work that mixes text, images, audio and video in one request. Long documents go in whole, though reliable recall across all of it is unverified in our data. Skip it if you need to run the model yourself, or if creative writing is the job.
The case for it
- 17th of 168 on Arena Coding as of 25 Sep 2026, a human-preference board rather than a pass/fail coding test, so it reflects which answers people preferred on coding prompts.
- Text, images, audio and video all go into the same request, so a screenshot or a clip does not have to be described in words first.
- The request capacity takes long documents whole, though room to hold them is not a guarantee of accurate recall.
The case against it
- 72nd of 168 on Arena Creative Writing as of 25 Sep 2026, against 17th of 168 on Arena Coding on the same date.
- We list no download for it, so using it means choosing a host, and no licence is supplied, so we say nothing about what you may do with it.
- Seven hosted offers across five companies, so the host you pick is a real decision rather than a formality.
How good is it?
A text model for writing and completing code, with everyday chat and drafting alongside.
- writing and completing codeArena Coding · 17th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)46th of 168 · 1454
CodingWriting and fixing code on its own
Arena Coding17th of 168 · 1525
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing72nd of 168 · 1394
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked between 4 hours and 16 hours ago — each listing carries its own date.
Why this differs from the header. The strip above quotes Xiaomi's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.14 in / $0.28 out
- Context served
- 1.1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| GMICloudbf16Through OpenRouter | $0.13 / $0.27checked 16 hours ago | 1.1M945K max reply | 4 tok/s | No | Yesunknown period | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $0.14 / $0.28checked 4 hours ago | 1M944K max reply through OpenRouter | 34 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Novita AIfp8Direct and through OpenRouter | $0.14 / $0.28checked 4 hours ago | 1M131K max reply through OpenRouter | 34 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Darkbloomfp4Through OpenRouter | $0.070 / $0.28checked 4 hours ago | 1M131K max reply | 16 tok/s | No | Yesunknown period | Unknown |
| OpenRouterOpenRouter's own listing | $0.14 / $0.28checked 4 hours ago | 1.1M | not measured | Unknown | Unknown | Unknown |
| Xiaomifp8Through OpenRouter | $0.14 / $0.28checked 4 hours ago | 1M131K max reply | 41 tok/s | No | Yes30 days | Unknown |
| Venice AIfp8Through OpenRouter | $0.17 / $0.35checked 4 hours ago | 1M131K max reply | 27 tok/s | No | No | Confirmed |
DeepInfra
Novita AIAcross the 7 listings we hold: 6 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 1 does not say. 3 appear in the zero-retention registry we check (2 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| GMICloudbf16Through OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp8Direct and through OpenRouter | ✓ | ✓ | ✓ |
| Novita AIfp8Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Darkbloomfp4Through OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Xiaomifp8Through OpenRouter | ✓ | ✓ | ✓ |
| Venice AIfp8Through OpenRouter | ✓ | ✗ | ✓ |
Tool calling: 7 of 7 listings say yes. JSON output: 6 of 7 listings say yes, 1 says no. Strict schema: 6 of 7 listings say yes, 1 says no.
Models people weigh against MiMo-V2.6-Flash
When we formed this view
Recent changes
What moved
input −50% ($0.080 → $0.040 per 1M tokens), cache read −50% ($0.080 → $0.040 per 1M tokens)What moved
MiMo-V2.6-Flash moved on 2 hosts: DeepInfra's own listing: input −43% ($0.140 → $0.080 per 1M tokens); Relace: input −33% ($0.120 → $0.080 per 1M tokens), cache read +100% ($0.040 → $0.080 per 1M tokens); DeepInfra through OpenRouter: input −0.0% ($0.14 → $0.14 per 1M tokens), output −0.0% ($0.28 → $0.28 per 1M tokens), cache read +4% ($0.0027 → $0.0028 per 1M tokens)What moved
MiMo-V2.6-Flash moved on 2 hosts: Relace: input +71% ($0.070 → $0.120 per 1M tokens), output +814% ($0.14 → $1.28 per 1M tokens), cache read +471% ($0.007 → $0.040 per 1M tokens); DeepInfra through OpenRouter: cache read −4% ($0.0028 → $0.0027 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 7 listings does not say whether it trains on prompts, and 2 answer only through OpenRouter, not for their own listing.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images, audio and video in, text out
- Catalogue slug
- xiaomi-mimo-v2-6-flash