Codestral: API pricing, context window and capabilities

Prices from official vendor price lists · October 2026

Codestral costs $0.3 per 1M input tokens and $0.9 per 1M output tokens, with a 128K context window. Mid-priced: dearer than 27% of this rating, with Mistral Small 4 as the nearest cheaper Mistral AI option. Recorded for coding, free tier.

Visit Mistral AI All Mistral AI models

Capabilities

API $/1M (in / out)

$0.3 / $0.9

Context window

128K tokens

Price / mo

API only

Overview Reviews

Codestral is an AI model from Mistral AI, priced at $0.3 input and $0.9 output per 1M tokens. That places it in the budget tier of this rating — cheaper than 72% of the 205 priced models listed.

It holds 128K tokens in a single conversation. Capabilities recorded in this rating: text & chat, coding, structured JSON output, prompt caching, batch API. Access is through the API rather than a consumer subscription.

API price$0.3 / $0.9per 1M tokens, in / out

Context128K tokenstokens per conversation

VendorMistral AIall models from this vendor

TierBudgetcheaper than 72% of models

Cost calculator

1M tokens/mo10M tokens/mo50M tokens/mo200M tokens/mo

Standard$0.75~~AED 3 per month~~

With batch −50%$0.38~~AED 1 per month~~

With caching on input$0.68~~AED 3 per month~~

Standard$7.50~~AED 28 per month~~

With batch −50%$3.75~~AED 14 per month~~

With caching on input$6.83~~AED 25 per month~~

Standard$37.50~~AED 138 per month~~

With batch −50%$18.75~~AED 69 per month~~

With caching on input$34.13~~AED 125 per month~~

Standard$150~~AED 551 per month~~

With batch −50%$75.00~~AED 275 per month~~

With caching on input$137~~AED 501 per month~~

Assumes a 1:3 input-to-output ratio, which is typical for chat and generation. Dirham figures use 3.6725 per dollar. Batch and caching discounts apply where the vendor offers them.

Compared with alternatives

How Codestral sits against its neighbours in this rating. Tap a card to open that model.

MiMo-V2.5-Pro

Cheaper

Xiaomi

$0.435 / $0.871.05M tokens

Qwen3.6 35B A3B

Closest match

Alibaba (Qwen)

$0.1 / $0.9262.1K tokens

Qwen3 Coder Flash

Step up

Alibaba (Qwen)

$0.195 / $0.9751M tokens

Good and poor fit

Good fit

Writing, reviewing and refactoring code, including fill-in-the-middle edits.
General text generation and conversation across languages.

Poor fit

Anything requiring image input — this model does not accept it.
Integrations that depend on structured function calls.

Related filters

Text & chat234 models for text generation and chat

Coding17 models built for writing code

Prompt caching153 models with cheap repeated context

Batch API146 models with half-price async processing

Free tier86 models with a free API allowance

Mistral AI11 models from this vendor

All 245 modelsThe full rating with filters and prices

Frequently asked questions

How much does Codestral cost?

$0.3 / $0.9 per 1M tokens, input and output. In dirhams that is roughly AED 1.10 per 1M input tokens. Batch processing halves it where the vendor offers it.

What is the context window of Codestral?

128K tokens in a single conversation.

What can Codestral do?

In this rating it is recorded with: text & chat, coding, structured JSON output, prompt caching, batch API, free tier, multilingual, proprietary API.

Is Codestral a good choice?

It depends on the job. See the good-fit and poor-fit lists above, and compare against the neighbouring models before committing.

Ratings 0

Avg. score 0

Rate this page

Help us improve