Back to all models

Pricing and availability as of

Codestral

Code specialist model for low-latency code generation and FIM.

codestral-2508
Context
256,000
tokens
Input from
$0.30
per 1M tokens
Output from
$0.90
per 1M tokens
Providers
1
one route
Released
Jul 30, 2025
No ratings yetSign in to rate

Providers for Codestral

Compare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.

1 provider

ProviderActions
256k$0.30$0.90

Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.

Codestral API pricing

Codestral API pricing starts at $0.30 per 1M input tokens and $0.90 per 1M output tokens through LLM Gateway.

ProviderInput / 1M tokensOutput / 1M tokensCached input / 1M tokensContext window
Mistral AI$0.30$0.90—256,000 tokens

What Codestral costs at volume

Monthly usageCost on Mistral AI
1M input + 250K output tokens$0.525
10M input + 2.5M output tokens$5.25
100M input + 25M output tokens$52.50

Codestral cost calculator

Estimated monthly cost
$7.50
Cost per request
$0.0007

Frequently asked questions

What is Codestral?

Code specialist model for low-latency code generation and FIM. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Codestral cost?

Pricing for Codestral on LLM Gateway starts at $0.30 per million input tokens and $0.90 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Codestral?

Codestral supports a context window of up to 256,000 tokens on its largest provider deployment.

Which providers serve Codestral?

Codestral is served by Mistral AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Codestral support tool calling and structured outputs?

Codestral supports soft JSON output, but not tool calling or strict JSON output schema.

When was Codestral released?

Codestral was released on July 30, 2025.