Mistral Small 3.2 24B
Sold by 5 sellers, timed at 51.2 tok/s, on 5 Design Arena boards, and not scored by Artificial Analysis.
retrieved sha256 · 0bb53a77713f
The same weights served by 2 providers, each at its own list price. OpenRouter's rate is its routed rate across whichever of them it uses, and it need not match any one of them.
What sellers charge
5 sellers · 1.88x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.06 at DeepInfra to $0.1125 at DeepInfra. 4 sellers undercut the $0.10 listed; 1 is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
24,028 requests · 5 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
5 priced · 5 timed · cheapest first- DeepInfradeepinfra/fp8/flex$0.06$0.16not listedfp8102knot matchednonenonenot matched100%
- DeepInfradeepinfra/fp8$0.075$0.20not listedfp816knot matchednonenonenot matched99.78%
- Parasailparasail/bf16$0.09$0.30$0.05bf1633k13 tok/s10663ms878 req94.15%
- Venicevenice/fp8$0.09375$0.25not listedfp816k46 tok/s22629ms7,832 req94.32%
- DeepInfradeepinfra/fp8/priority$0.1125$0.30not listedfp8102knot matchednonenonenot matched98.57%
- DeepInfranot matchednot matchednot matchednot matchedno offer57 tok/s34335ms12,781 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer41 tok/s251.61s7 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer51 tok/s9307ms2,530 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: 4 of the 5 timed routes are slower than it, and the middle route runs at 46 tok/s. The widest median-to-p90 gap is DeepInfra's, 5.67x.
DeepInfra publishes 3 offers and had 3 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 . 4 of the 6 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Parasail at 1.82% on 15 Nov 2026, Venice at 31.22% on 19 Nov 2026, Mistral at 84.55% on 23 Oct 2026, and DeepInfra (deepinfra/fp8/priority) at 96.86% 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
17 parameters · 5 sellers- frequency_penaltyevery seller
- max_tokensevery seller
- presence_penaltyevery seller
- response_formatevery seller
- stopevery seller
- structured_outputsevery seller
- temperatureevery seller
- top_kevery seller
- top_pevery seller
- logit_bias4 of 5not Venice
- repetition_penalty4 of 5not Venice
- seed4 of 5not Venice
- tools4 of 5not Parasail
- min_p3 of 5not Parasail and Venice
- tool_choice2 of 5not DeepInfra (deepinfra/fp8/flex), DeepInfra (deepinfra/fp8/priority), and Parasail
- logprobs1 of 5only Parasail
- top_logprobs1 of 5only Parasail
9 of these 17 are accepted by every one of the 5 sellers that publish a list; the other 8 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 $0.15 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 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.
- Code · Models895 Elowin rate 39.8% · source rank 142the board, 120 ranked
- Data visualisation · Models929 Elowin rate 43.3% · source rank 128the board, 110 ranked
- Game development · Models877 Elowin rate 39.4% · source rank 143the board, 120 ranked
- UI components · Models895 Elowin rate 40.5% · source rank 136the board, 116 ranked
- Websites · Models886 Elowin rate 38.3% · source rank 146the board, 126 ranked
Epoch AI has not placed Mistral Small 3.2 24B 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 Mistral Small 3.2 24B 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.
