LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Ministral 3 8B 2512

mistral·mistral/ministral-8b-2512·GA·Open weights·ministral series
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·KitaniGateway
$0.14 / $0.14
Blended $0.14 · 2.4× spread
Context
262,144
Output limit
209,715
Knowledge cutoff
—
Released / updated
2025-12-02 / 2025-12-02
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Ministral 3 8B 2512 by mistral is offered by 10 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 Kitani at $0.135 / $0.135 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 2.4× across the providers that host it.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 8,192 to 262,144, 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.

Available at 10 providers10 with public prices

  • ProviderInput / Output
  • KitaniGateway
    $0.14 / $0.14
    Cache read $0.068Context 8,192 ⚠Output limit 4,096
  • LLM GatewayGateway
    $0.15 / $0.15
    Context 262,144Output limit 262,144
  • NanoGPTGateway
    $0.15 / $0.15
    Cache read $0.015Context 262,144Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.15 / $0.15
    Context 262,144Output limit 8,192
  • OpenRouterGateway
    $0.15 / $0.15
    Cache read $0.015Context 262,144Output limit 209,715
  • Eden AIGateway
    $0.15 / $0.15
    Cache read $0.015Context 262,144Output limit 209,715
  • Kilo GatewayGateway
    $0.15 / $0.15
    Cache read $0.015Context 262,144Output limit 209,715
  • Eden AIGateway
    mistral/ministral-8b-2512@eu
    $0.17 / $0.17
    Cache read $0.017Context 262,144Output limit 209,715
  • CortecsGateway
    $0.18 / $0.18
    Cache read $0.017Context 256,000 ⚠Output limit 256,000
  • AI/ML APIGateway
    $0.32 / $0.32
    Cache read $0.016Context 262,144Output limit 209,715
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
KitaniGateway$0.14$0.14$0.068—8,192 ⚠4,096
LLM GatewayGateway$0.15$0.15——262,144262,144
NanoGPTGateway$0.15$0.15$0.015—262,14432,768
DevPass (LLM Gateway)Gateway$0.15$0.15——262,1448,192
OpenRouterGateway$0.15$0.15$0.015—262,144209,715
Eden AIGateway$0.15$0.15$0.015—262,144209,715
Kilo GatewayGateway$0.15$0.15$0.015—262,144209,715
Eden AI
mistral/ministral-8b-2512@eu
Gateway$0.17$0.17$0.017—262,144209,715
CortecsGateway$0.18$0.18$0.017—256,000 ⚠256,000
AI/ML APIGateway$0.32$0.32$0.016—262,144209,715

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$21.30
2OpenRouter$21.30
3Eden AI$21.30
4Kilo Gateway$21.30
5Eden AI$23.43
6Cortecs$25.31
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.15$02026-08-052026-11-15
2026-11-15Input list —Output list —Min blended $0.14

Related models

Ministral 3 3B Reasoning 2512same series—Ministral 3 14B Reasoning 2512same series—Ministral 3 14B 2512same series—Ministral 3 3B 2512same lab—Mistral Largesame lab—
Data partly from models.dev (MIT)