LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Codestral 25.08

mistral·mistral/codestral-2508·GA·Closed·codestral series
Mistral code model for low-latency completion, fill-in-the-middle, and code generation

Specs & pricing

Input / output per 1M tokens
Official price·Mistral
$0.30 / $0.90
Blended $0.45 · Cache read $0.03
Lowest paid·MistralFirst-party
$0.30 / $0.90
Blended $0.45 · 1.2× spread
Context
256,000
Output limit
8,192
Knowledge cutoff
—
Released / updated
2025-07-30 / 2025-07-30
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF

Codestral 25.08 by mistral is offered by 12 providers on this page. Its official list price is $0.30 per 1M input tokens and $0.90 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 1.2× across the providers that host it.

The context window is 256,000 tokens at the reference host, but hosts report different limits, from 128,000 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 PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Available at 12 providers12 with public prices

  • ProviderInput / Output
  • MistralOfficialFirst-party
    $0.30 / $0.90
    Cache read $0.03Context 256,000Output limit 8,192
  • LLM GatewayGateway
    $0.30 / $0.90
    Context 256,000Output limit 256,000
  • NanoGPTGateway
    $0.30 / $0.90
    Cache read $0.15Context 256,000Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.30 / $0.90
    Context 256,000Output limit 16,384
  • VertexCloud
    codestral-2
    $0.30 / $0.90
    Context 128,000 ⚠Output limit 8,192
  • OpenRouterGateway
    $0.30 / $0.90
    Cache read $0.03Context 256,000Output limit 204,800
  • Eden AIGateway
    $0.30 / $0.90
    Cache read $0.03Context 256,000Output limit 8,192
  • Kilo GatewayGateway
    $0.30 / $0.90
    Cache read $0.03Context 256,000Output limit 204,800
  • LowRouterGateway
    $0.31 / $0.94
    Cache read $0.031Context 128,000 ⚠Output limit 8,192
  • AI/ML APIGateway
    $0.32 / $0.95
    Cache read $0.032Context 256,000Output limit 8,192
  • Eden AIGateway
    mistral/codestral-2508@eu
    $0.33 / $0.99
    Cache read $0.033Context 256,000Output limit 8,192
  • CortecsGateway
    $0.37 / $1.10
    Cache read $0.037Context 256,000Output limit 256,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
MistralOfficialFirst-party$0.30$0.90$0.03—256,0008,192
LLM GatewayGateway$0.30$0.90——256,000256,000
NanoGPTGateway$0.30$0.90$0.15—256,00032,768
DevPass (LLM Gateway)Gateway$0.30$0.90——256,00016,384
Vertex
codestral-2
Cloud$0.30$0.90——128,000 ⚠8,192
OpenRouterGateway$0.30$0.90$0.03—256,000204,800
Eden AIGateway$0.30$0.90$0.03—256,0008,192
Kilo GatewayGateway$0.30$0.90$0.03—256,000204,800
LowRouterGateway$0.31$0.94$0.031—128,000 ⚠8,192
AI/ML APIGateway$0.32$0.95$0.032—256,0008,192
Eden AI
mistral/codestral-2508@eu
Gateway$0.33$0.99$0.033—256,0008,192
CortecsGateway$0.37$1.10$0.037—256,000256,000

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
1Mistral · Official$72.60
2OpenRouter$72.60
3Eden AI$72.60
4Kilo Gateway$72.60
5LowRouter$75.94
6AI/ML API$76.81
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.90$02026-08-052026-10-08
2026-10-08Input list $0.30Output list $0.90Min blended $0.45

Related models

Codestral (latest)same series$0.30 / $0.90Codestral 25.01same series—Mistral: Mistral Codestralsame series—GPT-4o minicheaper alternative$0.15 / $0.60Nova Litecheaper alternative$0.06 / $0.24Nova Microcheaper alternative$0.035 / $0.14Ministral 3 14Bcheaper alternative$0.20 / $0.20
Data partly from models.dev (MIT) · Mistral official docs ↗