Ministral 3 3B 2512
Sold by 2 sellers, timed at 167 tok/s, scored 4.8 on the Coding Index, and on 4 Design Arena boards.
retrieved sha256 · 0bb53a77713f
The maker's own list price, read from docs.mistral.ai. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.
What sellers charge
2 sellers · 1.1x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.10 at Mistral to $0.11 at Mistral. The $0.10 listed is the cheapest on offer; 1 seller is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
47,942 requests · 2 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
2 priced · 2 timed · cheapest first- Mistralmistral/zdr · listed$0.10$0.10$0.01not declared105knot matchednonenonenot matched99.93%
- Mistralmistral/eu$0.11$0.11$0.011not declared105knot matchednonenonenot matched99.93%
- Mistralnot matchednot matchednot matchednot matchedno offer153 tok/s98349ms3,113 reqno offer
- Mistralnot matchednot matchednot matchednot matchedno offer168 tok/s101399ms44,829 reqno offer
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: 1 of the 2 timed routes are slower than it, and the middle route runs at 161 tok/s. The widest median-to-p90 gap is Mistral's, 1.66x.
Mistral publishes 2 offers and had 2 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.
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 . Every one of the 3 sellers with a reading was at 99% or better on each of the 23 days held, 23 Oct 2026 to 21 Nov 2026. 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
11 parameters · 2 sellers- frequency_penaltyevery seller
- max_tokensevery seller
- presence_penaltyevery seller
- response_formatevery seller
- seedevery seller
- stopevery seller
- structured_outputsevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_pevery seller
All 11 are accepted by every one of the 2 sellers that publish a list. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.
Price position
342 priced modelsBlended $0.10 per million tokens, 3 in to 1 out: cheaper than 312 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.
- 3D scenes · Models943 Elowin rate 35.9% · source rank 129the board, 113 ranked
- Code · Models998 Elowin rate 37.3% · source rank 130the board, 120 ranked
- Game development · Models937 Elowin rate 33.0% · source rank 138the board, 120 ranked
- Websites · Models1019 Elowin rate 38.2% · source rank 134the board, 126 ranked
Epoch AI has not placed Ministral 3 3B 2512 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 Ministral 3 3B 2512 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.
