Get started

Mistral Medium 3.5

Sold by 2 sellers, timed at 102 tok/s, and scored 4.6 on the Intelligence Index.

retrieved sha256 · 0bb53a77713f

Models/Mistral/Mistral Medium 3.5USD per 1M tokens · as OpenRouter routes it
mistralai/mistral-medium-3-5Mistral · base listing · Mistral tokenizer
listed until 2027-01-31
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$1.50per 1M tokens
Output$7.50per 1M tokens
Cached inputnot listedper 1M tokens
Context262k262,144 tokens
What the list says · the fields OpenRouter publishes for this id12 fields
AuthorMistral
Listed
Canonical idmistralai/mistral-medium-3.5-20260430
Context262,144 tokens
Max output209,715 tokens
Modalitiestext, image, file → text
TokenizerMistral
Reasoningoptional · effort high, none, high by default
Moderationnot moderated by OpenRouter
Listed until2027-01-31
Other listingbatch variant
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licenceother
Parameters128B · 127,704,210,176 declared
Model classMistral3ForConditionalGeneration
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 $1.50 at Mistral to $1.65 at Mistral. The $1.50 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

911 requests · 2 endpoints · 30-minute window
Throughput102 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token422msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread97 to 105The 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$1.50$7.50not listednot declared210knot matchednonenonenot matched99.91%
  2. Mistralmistral/eu$1.65$8.25not listednot declared210knot matchednonenonenot matched99.84%
  3. Mistralnot matchednot matchednot matchednot matchedno offer97 tok/s45361ms350 reqno offer
  4. Mistralnot matchednot matchednot matchednot matchedno offer105 tok/s53460ms561 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 101 tok/s. The widest median-to-p90 gap is Mistral's, 2.16x.

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

14 parameters · 2 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. presence_penaltyevery seller
  5. reasoningevery seller
  6. reasoning_effortevery seller
  7. response_formatevery seller
  8. seedevery seller
  9. stopevery seller
  10. structured_outputsevery seller
  11. temperatureevery seller
  12. tool_choiceevery seller
  13. toolsevery seller
  14. top_pevery seller

All 14 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 $3.00 per million tokens, 3 in to 1 out: cheaper than 81 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 Index4.6Position 54 of 58, above 7% of the models scored.the intelligence leaderboard
Coding Index46.9Position 62 of 118, above 47% of the models scored.the coding leaderboard
Agentic Index7.0Position 62 of 94, above 34% of the models scored.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
Index141.6138.3 to 144.7
Position115 of 258above 56% of the models placed
Results behind it6benchmark results
As Epoch names itMistral Medium 3.5released 28 Apr 2026

Position 115 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Mistral Medium 3.5 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.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.