Mistral Small 3.2 24B pricing.

prices as of · 16 providers · 19 prices

Mistral Small 3.2 24B holds 256k tokens of context and reads images as well as text. Open weights, so anyone may host it, which is why the prices below differ so much.

Mistral Small 3.2 24B costs $0.09 in and $0.25 out per million tokens from OpenRouter; the cheapest price we can explain is $0.42 at DeepInfra, checked 16 Sept 2026.

tool callingreads imagesstructured outputopen weights256k contextreleased 20 Jun 2025

OpenRouter list price

$0.53/M tokens

$0.09 in · $0.25 out

read · 85% below the market median

Cheapest price we can explain

$0.43/M tokens

$0.07 in · $0.20 out · 20% under list

DeepInfra
View at DeepInfra

read

What it costs for your work

pages a month

OpenRouter list price

$0.0713a month

cheapest we can explain · DeepInfra

$0.057a month

difference

$0.0143saved

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

Mistral AI publishes the weights, so you can run Mistral Small 3.2 24B on a server you rent by the month. It needs about 17.1 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is OVHcloud VPS-4 2027 at $27.11/mo, streaming an estimated 1.3–2.6 tok/s.

Every provider selling Mistral Small 3.2 24B

Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against OpenRouter's price. Mistral AI trained Mistral Small 3.2 24B and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.

Cheaper, and we know why

5 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • DeepInfra

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    128k context hereDeepInfra

    $0.07 / $0.20in / out per M

    0.80×of list price

  • DeepInfra

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    128k context herefp8 precisionDeepInfra

    $0.07 / $0.20in / out per M

    0.80×of list price

  • Nous Portal

    Resells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.

    $0.07 / $0.20in / out per M

    0.80×of list price

  • TrustedRouter

    Routes to a host serving the open weights; precision not disclosed.

    128k context hereTrustedRouter

    $0.08 / $0.21in / out per M

    0.84×of list price

  • Parasail

    4% under the list price, an ordinary reseller margin.

    131k context herebf16 precisionParasail

    $0.09 / $0.30in / out per M

    1.07×of list price

Same price as the maker

11 prices

The same price the maker charges, sold by someone else.

  • OpenRouter

    The same price OpenRouter charges.

    $0.09 / $0.25in / out per M

    1.00×of list price

  • Venice

    The same price OpenRouter charges.

    $0.09 / $0.25in / out per M

    1.00×of list price

  • Kilo Gateway

    The same price OpenRouter charges.

    $0.09 / $0.25in / out per M

    1.00×of list price

  • Venice

    The same price OpenRouter charges.

    fp8 precisionVenice

    $0.09 / $0.25in / out per M

    1.00×of list price

  • OVHcloud AI Endpoints

    7% above OpenRouter's price.

    131k context hereOVHcloud AI Endpoints

    $0.10 / $0.31in / out per M

    1.15×of list price

  • Eden AI

    7% above OpenRouter's price.

    131k context hereEden AI

    $0.10 / $0.31in / out per M

    1.15×of list price

  • Cortecs

    11% above OpenRouter's price.Routes only to EU-hosted providers, prices in euros, and adds a flat 5% fee.

    131k context hereCortecs

    $0.10 / $0.32in / out per M

    1.19×of list price

  • Scaleway

    60% above OpenRouter's price.

    128k context hereScaleway

    $0.15 / $0.35in / out per M

    1.51×of list price

  • NanoGPT

    113% above OpenRouter's price.

    128k context hereNanoGPT

    $0.20 / $0.40in / out per M

    1.88×of list price

  • GreenPT

    143% above OpenRouter's price.

    128k context here

    $0.23 / $0.46in / out per M

    2.15×of list price

  • LLMTR

    160% above OpenRouter's price.

    128k context hereLLMTR

    $0.24 / $0.49in / out per M

    2.30×of list price

Cheaper, and nobody says why

2 prices · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

  • Berget AI

    We could not read this provider's prices reliably, so the row is listed but never ranked.

    32k context hereBerget AI

    $0.30 / $0.30in / out per M

    2.26×of list price

  • Featherless

    We could not read this provider's prices reliably, so the row is listed but never ranked.

    33k context hereFeatherless

    $0.70 / $1.16in / out per M

    6.13×of list price

Given away with limits

1 free tiers · never ranked

These providers give Mistral Small 3.2 24B away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.

  • Meganova

Frequently asked

Who sells Mistral Small 3.2 24B cheapest?
DeepInfra, at $0.07 in and $0.20 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
Is Mistral Small 3.2 24B open weights?
Yes. Mistral AI publishes the weights, so anyone may host Mistral Small 3.2 24B, which is why 16 providers sell it and why their prices differ so much.
How much context does Mistral Small 3.2 24B hold?
256,000 tokens in one call, which is about 256k, and it can call your own functions.
How does Mistral Small 3.2 24B compare with the rest of the market?
At $0.53 per million tokens, OpenRouter's price is 85% below the $3.55 median across the 337 text models we track.
More from Mistral AIMistral NemoMistral Large 3Mistral Small 3.2Codestral (latest)Similar contextKimi K2.6Kimi K2.7 CodeGLM-5.1Kimi K2.5