All prices › Mistral › Codestral

Codestral API pricing

As of October 16, 2026, Codestral costs $0.30 per million input tokens and $0.90 per million output tokens on the Mistral API. Cached input is $0.03 per million.

It is the 8th cheapest of 12 Mistral AI models tracked here, by blended price. The closest Budget-tier model from another provider is GPT-5.6 Luna (OpenAI) at $0.20 / $1.20; Codestral is 0% cheaper. First listed in the LiteLLM price data on May 31, 2024.

Input / 1M tokens$0.30
Output / 1M tokens$0.90
Context window128K
Max output128K

Every published rate

RatePer 1M tokens
Input (standard)$0.30
Output (standard)$0.90
Cached input (read)$0.03

What it costs in practice

TaskTokensPer requestPer 1,000 requests
Chatbot reply1,000 in / 500 out$0.00075$0.75
Summarize a long document20,000 in / 1,000 out$0.0069$6.90
Coding agent step50,000 in / 2,000 out$0.02$16.80

Standard rates, no caching or batch discount. Compare your own numbers across all models →

Price history

DateModelChange
2026-08-20CodestralContext window: 32K → 128K (+300%) source
2026-08-20CodestralName now points to a newer version: $1 / $3 → $0.3 / $0.9 source
2024-05-31CodestralNew model listed: $1 in / $3 out source

Dates are when each change first appeared in the LiteLLM price data, usually within days of the provider's announcement.

Details

ProviderMistral
Price tierBudget
FeaturesTool use
API model namescodestral-2508, codestral-latest
Official pricingdocs.mistral.ai

Models at a similar price

ModelInput / 1MOutput / 1M
DeepSeek V3.2$0.28$0.40
GPT-5.6 Luna$0.20$1.20
GPT-5.4 Nano$0.20$1.25
DeepSeek V3$0.27$1.10
DeepSeek V4 Flash$0.30$1.20
Gemini 3.1 Flash Lite$0.25$1.50

Other Mistral models

ModelInput / 1MOutput / 1M
Mistral Medium 3$1.50$7.50
Mistral Medium 3.5$1.50$7.50
Mistral Large 4$0.68$2.09
Mistral Large 3$0.50$1.50
Open Mistral Nemo$0.30$0.30
Mistral Small$0.15$0.60
Mistral Tiny$0.25$0.25
Ministral 3 14B$0.20$0.20
Voxtral Small$0.10$0.40
Ministral 3 8B$0.15$0.15
Ministral 3 3B$0.10$0.10