LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Mistral Small 3.2 24B

mistral·mistral/mistral-small-3.2-24b-instruct·GA·Open weights·mistral-small series
Efficient Mistral model for fast chat, extraction, and production assistants

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.075 / $0.20
Blended $0.11 · 4.5× spread
Context
32,000
Output limit
8,192
Knowledge cutoff
2023-10-31
Released / updated
2025-06-20 / 2025-06-20
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Mistral Small 3.2 24B is offered by 8 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is NanoGPT at $0.075 / $0.20 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 4.5× across the providers that host it.

The context window is 32,000 tokens at the reference host, but hosts report different limits, from 32,000 to 256,000, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text and Image. 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.

Available at 8 providers8 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    $0.075 / $0.20
    Cache read $0.075Context 128,000 ⚠Output limit 16,384
  • OpenRouterGateway
    $0.075 / $0.20
    Context 256,000 ⚠Output limit 16,384
  • Kilo GatewayGateway
    $0.075 / $0.20
    Context 128,000 ⚠Output limit 16,384
  • AI/ML APIGateway
    $0.079 / $0.21
    Context 128,000 ⚠Output limit 16,384
  • Venice AIGateway
    mistral-small-3-2-24b-instruct
    $0.094 / $0.25
    Context 256,000 ⚠Output limit 16,384
  • OVHcloud AI EndpointsCloud
    mistral-small-3.2-24b-instruct-2506
    $0.10 / $0.31
    Context 131,072 ⚠Output limit 131,072
  • CortecsGateway
    mistral-small-3.2-24b-instruct-2506
    $0.10 / $0.31
    Context 131,000 ⚠Output limit 131,000
  • Berget.AIGateway
    mistralai/Mistral-Small-3.2-24B-Instruct-2506
    $0.34 / $0.34
    Context 32,000Output limit 8,192
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.075$0.20$0.075—128,000 ⚠16,384
OpenRouterGateway$0.075$0.20——256,000 ⚠16,384
Kilo GatewayGateway$0.075$0.20——128,000 ⚠16,384
AI/ML APIGateway$0.079$0.21——128,000 ⚠16,384
Venice AI
mistral-small-3-2-24b-instruct
Gateway$0.094$0.25——256,000 ⚠16,384
OVHcloud AI Endpoints
mistral-small-3.2-24b-instruct-2506
Cloud$0.10$0.31——131,072 ⚠131,072
Cortecs
mistral-small-3.2-24b-instruct-2506
Gateway$0.10$0.31——131,000 ⚠131,000
Berget.AI
mistralai/Mistral-Small-3.2-24B-Instruct-2506
Gateway$0.34$0.34——32,0008,192

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

Common scenarios
1NanoGPT$25.00
2OpenRouter$25.00
3Kilo Gateway$25.00
4AI/ML API$26.45
5Venice AI$31.25
6OVHcloud AI Endpoints$35.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.13$02026-08-052026-11-18
2026-11-18Input list —Output list —Min blended $0.11

Related models

Mistral Small 4same series$0.15 / $0.60Mistral Small (latest)same series$0.15 / $0.60Mistral Small 3.1 24Bsame series—
Data partly from models.dev (MIT)