LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Mistral: Mistral Small 3

mistral·mistral/mistral-small-24b-instruct-2501·GA·Open weights·mistral-small series·NEW
Efficient Mistral model for fast chat, extraction, and production assistants

Mistral: Mistral Small 3 is offered by 3 providers on this page. Its reference price is $0.116 per 1M input tokens and $0.346 per 1M output tokens. The lowest paid channel is Kilo Gateway at $0.05 / $0.08 per 1M, about 2.3× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 32,768 tokens, with an output limit of 8,192 tokens. It supports structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-10-31.

Specs & pricing

Input / output per 1M tokens
Reference price·NanoGPT
$0.12 / $0.35
Blended $0.17 · Cache read —
Lowest paid·Kilo GatewayGateway
$0.05 / $0.08
Blended $0.058 · 2.3× spread
Context
32,768
Output limit
8,192
Knowledge cutoff
2023-10-31
Released / updated
2025-01-30 / 2026-09-10
Capabilities
ReasoningTool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Available at 3 providers3 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kilo GatewayGateway$0.05$0.08——32,76816,384
OpenRouterGateway$0.05$0.08——32,76816,384
NanoGPTGateway$0.12$0.35——32,7688,192

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Kilo Gateway$14.00
2OpenRouter$14.00
3NanoGPT$40.43
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.35$02026-08-052026-09-122026-08-05 · Input list $0.052026-08-06 · Input list $0.052026-08-07 · Input list $0.052026-08-08 · Input list $0.052026-08-09 · Input list $0.052026-08-10 · Input list $0.052026-08-11 · Input list $0.052026-08-12 · Input list $0.052026-08-13 · Input list $0.052026-09-12 · Input list $0.122026-08-05 · Output list $0.082026-08-06 · Output list $0.082026-08-07 · Output list $0.082026-08-08 · Output list $0.082026-08-09 · Output list $0.082026-08-10 · Output list $0.082026-08-11 · Output list $0.082026-08-12 · Output list $0.082026-08-13 · Output list $0.082026-09-12 · Output list $0.352026-08-05 · Min blended $0.0582026-08-06 · Min blended $0.0582026-08-07 · Min blended $0.0582026-08-08 · Min blended $0.0582026-08-09 · Min blended $0.0582026-08-10 · Min blended $0.0582026-08-11 · Min blended $0.0582026-08-12 · Min blended $0.0582026-08-13 · Min blended $0.0582026-09-12 · Min blended $0.058

Related models

Mistral Small 3.2 24B Instructsame series$0.094 / $0.25Mistral Small 3.2 24B Instruct 2506same series$0.33 / $0.33Mistral Small 4 119B Thinkingsame series$0.40 / $1.40Ministral 3Bcheaper alternative$0.04 / $0.04Command R7Bcheaper alternative$0.038 / $0.15inSchematron V2 Smallcheaper alternative$0.05 / $0.23inSchematron V2 Turbocheaper alternative$0.03 / $0.15
Data partly from models.dev (MIT) · NanoGPT official docs ↗