Get started

Voxtral Small 24B 2507

Sold by 2 sellers, timed at 65.1 tok/s, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Mistral/Voxtral Small 24B 2507USD per 1M tokens · as OpenRouter routes it
mistralai/voxtral-small-24b-2507Mistral · base listing · Mistral tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.10per 1M tokens
Output$0.30per 1M tokens
Cached input$0.01per 1M tokens
Context33k32,768 tokens
The other meters · every further rate the list publishes for this id, in the unit it states1 meter
Audio input$100.00per 1M tokens
What the list says · the fields OpenRouter publishes for this id8 fields
AuthorMistral
Listed
Context32,768 tokens
Max output26,214 tokens
Modalitiestext, audio, 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
Parameters24.3B · 24,261,800,960 declared
Model classVoxtralForConditionalGeneration
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 $0.10 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

409 requests · 2 endpoints · 30-minute window
Throughput65.1 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token812msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread52 to 71.5The 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$0.10$0.30$0.01not declared26knot matchednonenonenot matched100%
  2. Mistralmistral/eu$0.11$0.33$0.011not declared26knot matchednonenonenot matched99.48%
  3. Mistralnot matchednot matchednot matchednot matchedno offer52 tok/s23.81.14s135 reqno offer
  4. Mistralnot matchednot matchednot matchednot matchedno offer71.5 tok/s38651ms274 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 61.8 tok/s. The widest median-to-p90 gap is Mistral's, 2.18x.

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 3 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 91.86% on 20 Nov 2026 and Mistral (mistral/zdr) at 94.24% on 20 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 $0.15 per million tokens, 3 in to 1 out: cheaper than 283 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 Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.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 Voxtral Small 24B 2507 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 Voxtral Small 24B 2507 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.