Mistral AI

Codestral 2508

Mistral's coding-specialized model for fill-in-the-middle, repo-scale context, and agentic software work, available via OpenRouter and Azure.

ActiveAvailable from 4 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Mistral API pricing, Mistral model cards

Price per 1M tokens via Mistral (OpenRouter)
$0.3 in / $0.9 out
Context window256,000
Cache read$0.03 / M
ModalitiesText → Text
Priced across4 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.3 / M
Output$0.9 / M
Cache read$0.03 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Estimated monthly cost
$78.00
at current list prices
Fresh input$60.00
Cached input$0.00
Output$18.00
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
Azure AI FoundryLowest
$0.3$0.9——Direct
Mistral
$0.3$0.9$0.03—via OpenRouter
Azure AI Foundry · Data zone
$0.33$0.99——Direct
Azure AI Foundry · Regional
from$0.33$0.99——Direct

Regional deployments are priced per region; the lowest available region rate is shown.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.3 / $0.9 per 1M since July 10, 2026.

More from Mistral AI

Other models from the same provider.

Mistral Medium 3.5
mistral/mistral-medium-3-5
$1.5 / $7.5 in / out per 1M
Mistral Large 3
mistral/mistral-large-2512
$0.5 / $1.5 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Codestral 2508 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.