Get started

Mistral Large 3 2512

Sold by 2 sellers, timed at 75.3 tok/s, scored 20.1 on the Coding Index, and on 8 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Mistral/Mistral Large 3 2512USD per 1M tokens · as OpenRouter routes it
mistralai/mistral-large-2512Mistral · base listing · Mistral tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.50per 1M tokens
Output$1.50per 1M tokens
Cached input$0.05per 1M tokens
Context262k262,144 tokens
What the list says · the fields OpenRouter publishes for this id8 fields
AuthorMistral
Listed
Context262,144 tokens
Max output209,715 tokens
Modalitiestext, image, file → text
TokenizerMistral
Moderationnot moderated by OpenRouter
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licenceapache-2.0
Parametersno safetensors count
Model classnot stated
Downloadnot gated
Published

What sellers charge

2 sellers · 1.1x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.50 at Mistral to $0.55 at Mistral. The $0.50 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

3,839 requests · 2 endpoints · 30-minute window
Throughput75.3 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token578msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread73 to 77The 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

2 priced · 2 timed · cheapest first
  1. Mistralmistral/zdr · listed$0.50$1.50$0.05not declared210knot matchednonenonenot matched99.58%
  2. Mistralmistral/eu$0.55$1.65$0.055not declared210knot matchednonenonenot matched99.36%
  3. Mistralnot matchednot matchednot matchednot matchedno offer77 tok/s52532ms2,200 reqno offer
  4. Mistralnot matchednot matchednot matchednot matchedno offer73 tok/s50640ms1,639 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 75 tok/s. The widest median-to-p90 gap is Mistral's, 1.48x.

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 . 2 of the 2 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Mistral (mistral/eu) at 97.22% on 17 Nov 2026 and Mistral (mistral/zdr) at 97.43% on 17 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
  1. frequency_penaltyevery seller
  2. max_tokensevery seller
  3. presence_penaltyevery seller
  4. response_formatevery seller
  5. seedevery seller
  6. stopevery seller
  7. structured_outputsevery seller
  8. temperatureevery seller
  9. tool_choiceevery seller
  10. toolsevery seller
  11. 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 models

Blended $0.75 per million tokens, 3 in to 1 out: cheaper than 176 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

Each 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.

Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Index20.1Position 100 of 118, above 15% of the models scored.the coding leaderboard
Agentic Index1.0Position 82 of 94, above 12% of the models scored.the agentic leaderboard
  1. 3D scenes · Models1079 Elowin rate 46.9% · source rank 99the board, 113 ranked
  2. ASCII art · Models1053 Elowin rate 40.3% · source rank 72the board, 67 ranked
  3. Code · Models1130 Elowin rate 47.6% · source rank 98the board, 120 ranked
  4. Data visualisation · Models1133 Elowin rate 45.7% · source rank 88the board, 110 ranked
  5. Game development · Models1069 Elowin rate 41.5% · source rank 110the board, 120 ranked
  6. SVG · Models982 Elowin rate 38.0% · source rank 95the board, 83 ranked
  7. UI components · Models1090 Elowin rate 43.0% · source rank 103the board, 116 ranked
  8. Websites · Models1153 Elowin rate 49.5% · source rank 96the board, 126 ranked
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 Mistral Large 3 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 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Mistral Large 3 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.

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.