MiMo-V2.6-Pro
Sold by 4 sellers, timed at 37.7 tok/s, scored 29.9 on the Intelligence Index, and on 8 Design Arena boards.
retrieved sha256 · 0bb53a77713f
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 sellers charge
4 sellers · 6.82x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.387 at DeepInfra to $2.64 at PrimaLabs. 1 seller undercuts the $0.435 listed; 1 is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
31,213 requests · 4 endpoints · 30-minute windowOpenRouter'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
4 priced · 4 timed · cheapest first- DeepInfradeepinfra/fp8 · 10% off$0.387$0.783$0.00324fp8944k40 tok/s18734ms12,918 req100%
- StreamLakestreamlake · listed$0.435$0.87$0.0036not declared128k26 tok/s133.03s1,041 req99.08%
- Xiaomixiaomi/fp8 · listed$0.435$0.87$0.0036fp8131k28 tok/s193.82s16,409 req100%
- PrimaLabsprimalabs/fp8$2.64$5.28$0.024fp8944k204 tok/s82903ms845 req99.71%
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: 2 of the 4 timed routes are slower than it, and the middle route runs at 34 tok/s. The widest median-to-p90 gap is PrimaLabs's, 2.48x.
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 . 5 of the 7 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: StreamLake at 36.17% on 23 Oct 2026, GMICloud at 87.82% on 10 Nov 2026, PrimaLabs (primalabs/fp8) at 95.75% on 12 Nov 2026, Novita at 97.29% on 23 Oct 2026, and 1 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
19 parameters · 4 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- response_formatevery seller
- stopevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_pevery seller
- frequency_penalty3 of 4not StreamLake
- presence_penalty3 of 4not StreamLake
- structured_outputs3 of 4not StreamLake
- seed2 of 4not StreamLake and Xiaomi
- logit_bias1 of 4not PrimaLabs, StreamLake, and Xiaomi
- logprobs1 of 4not DeepInfra, StreamLake, and Xiaomi
- min_p1 of 4not PrimaLabs, StreamLake, and Xiaomi
- repetition_penalty1 of 4not PrimaLabs, StreamLake, and Xiaomi
- top_k1 of 4not PrimaLabs, StreamLake, and Xiaomi
- top_logprobs1 of 4not DeepInfra, StreamLake, and Xiaomi
9 of these 19 are accepted by every one of the 4 sellers that publish a list; the other 10 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 modelsBlended $0.544 per million tokens, 3 in to 1 out: cheaper than 204 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 boardEach mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.
- Web apps · Agents1272 Elowin rate 58.2% · source rank 10the board, 47 ranked
- 3D scenes · Models1320 Elowin rate 57.7% · source rank 16the board, 113 ranked
- Code · Models1315 Elowin rate 53.5% · source rank 14the board, 120 ranked
- Data visualisation · Models1336 Elowin rate 58.9% · source rank 7the board, 110 ranked
- Game development · Models1312 Elowin rate 53.5% · source rank 16the board, 120 ranked
- SVG · Models1290 Elowin rate 54.2% · source rank 12the board, 83 ranked
- UI components · Models1333 Elowin rate 58.3% · source rank 12the board, 116 ranked
- Websites · Models1310 Elowin rate 51.9% · source rank 11the board, 126 ranked
Epoch AI has not placed MiMo-V2.6-Pro 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 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for MiMo-V2.6-Pro 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.
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.
