Get started

MiMo-V2.6-Flash

Sold by 7 sellers, timed at 30.7 tok/s, and scored 26.7 on the Intelligence Index.

retrieved sha256 · 0bb53a77713f

Models/Xiaomi/MiMo-V2.6-FlashUSD per 1M tokens · as OpenRouter routes it
xiaomi/mimo-v2.6-flashXiaomi · base listing · Other tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.14per 1M tokens
Output$0.28per 1M tokens
Cached input$0.0028per 1M tokens
Context1.05M1,050,000 tokens
What Vitna read · the provider's own pricing page, kept as a dated recordin / out per 1M tokens
Novita AIopen weights$0.14 / $0.28confirmed 22 Nov 2026

The same weights, served by one provider at its own list price, read from novita.ai. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.

What the list says · the fields OpenRouter publishes for this id10 fields
AuthorXiaomi
Listed
Canonical idxiaomi/mimo-v2.6-flash-20260921
Context1,050,000 tokens
Max output131,072 tokens
Modalitiestext, image, video, audio → text
TokenizerOther
Reasoningoptional
Moderationnot moderated by OpenRouter
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licencemit
Parameters311B · 310,756,322,688 declared
Model classMiMoV2ForCausalLM
Downloadnot gated
Published

What sellers charge

7 sellers · 2x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.10 at Darkbloom to $0.20 at Makora. 1 seller undercuts the $0.14 listed; 3 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

127,010 requests · 7 endpoints · 30-minute window
Throughput30.7 tok/sMedian output rate, weighted across the 7 endpoints serving it by the requests each answered.the speed board
First token3.31sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread23 to 57The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

7 priced · 7 timed · cheapest first
  1. Darkbloomdarkbloom/fp4$0.10$0.28$0.0028fp429k31 tok/s153.4s343 req92.92%
  2. Coherecohere/fp8 · listed$0.14$0.28$0.003fp8131k46 tok/s91.15s20,944 req99.93%
  3. DeepInfradeepinfra/fp8 · listed$0.14$0.28$0.0028fp8944k31 tok/s87.91s1,583 req93.75%
  4. Xiaomixiaomi/fp8 · listed$0.14$0.28$0.0028fp8131k23 tok/s114.02s89,181 req100%
  5. Tenstorrenttenstorrent/fp8$0.165$0.33$0.004fp8131k27 tok/s152.28s99 req99.72%
  6. Venicevenice/fp8$0.175$0.35$0.00375fp8131k26 tok/s611.5s681 req95.06%
  7. Makoramakora/fp8$0.20$0.40$0.015fp8131k57 tok/s101.11s14,179 req99.93%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 3 of the 7 timed routes are slower than it, and the middle route runs at 31 tok/s. The widest median-to-p90 gap is Makora's, 5.7x.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 8 of the 12 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: DeepInfra at 2.36% on 13 Nov 2026, Venice at 9.72% on 26 Oct 2026, GMICloud at 23.71% on 20 Nov 2026, Tenstorrent at 55.68% on 7 Nov 2026, and 4 more. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

20 parameters · 7 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. structured_outputsevery seller
  5. temperatureevery seller
  6. tool_choiceevery seller
  7. toolsevery seller
  8. top_pevery seller
  9. frequency_penalty6 of 7not Tenstorrent
  10. presence_penalty6 of 7not Tenstorrent
  11. response_format6 of 7not Venice
  12. stop6 of 7not Tenstorrent
  13. top_k6 of 7not Xiaomi
  14. repetition_penalty4 of 7not Tenstorrent, Venice, and Xiaomi
  15. seed4 of 7not Tenstorrent, Venice, and Xiaomi
  16. logprobs3 of 7only Cohere, Makora, and Tenstorrent
  17. top_logprobs3 of 7only Cohere, Makora, and Tenstorrent
  18. logit_bias1 of 7only DeepInfra
  19. min_p1 of 7only DeepInfra
  20. parallel_tool_calls1 of 7only Cohere

8 of these 20 are accepted by every one of the 7 sellers that publish a list; the other 12 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.175 per million tokens, 3 in to 1 out: cheaper than 276 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board
Intelligence Index26.7Position 33 of 58, above 43% of the models scored.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard

Not ranked in any Design Arena category.

Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed MiMo-V2.6-Flash on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for MiMo-V2.6-Flash under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.