Codestral (latest) pricing and specs
Codestral (latest) pricing and specsMistral code model for completions, refactors, and developer IDE workflows
Codestral (latest) price per 1M tokens
| Type | ₽ / 1M | $ / 1M |
|---|---|---|
| Input tokens | 25,35 ₽ | $0.3 |
| Output tokens | 76,06 ₽ | $0.9 |
Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.
Codestral (latest) specs and limits
- Context window
- 256K
- Max output
- 4K
- Input
- text
- Output
- text
- Family
- codestral
- Released
- 2024-05-29
- Updated
- 2025-01-04
- Knowledge cutoff
- 2024-10
- Also known as
- mistral codestral (latest), mistral ai codestral (latest), mistralai codestral (latest), le chat codestral (latest), mistral api codestral (latest), mistral llm codestral (latest)
What Codestral (latest) can do
- —Reasoning
- ✓Tool calling
- —Structured output
- —Attachments / files
- —Vision (images)
- ✓Temperature control
- ✓Open weights
Codestral (latest) benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Aider Polyglot | 11.1 | percent correct |
Model weights
Frequently asked questions
How much does the Codestral (latest) API cost?
Input costs $0.3 per 1M tokens (25.35 ₽) and output costs $0.9 per 1M (76.06 ₽). Mistral bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.
How much do 1,000 Codestral (latest) tokens cost?
List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.3 for input and $0.9 for output by 1,000. The same rates in rubles are 25.35 ₽ and 76.06 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.
How many tokens does Codestral (latest) hold?
The Codestral (latest) context window is 256K tokens (256,000). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Mistral model card as of September 2026.
What are the Codestral (latest) limits?
The context window is 256K tokens (256,000) and a single response is capped at 4K tokens, so longer output has to be generated in parts. Rate limits are set by Mistral per account and depend on your plan rather than on the model, so they are not listed here.
How is the Codestral (latest) price in rubles calculated?
Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For Codestral (latest) that gives 25.35 ₽ per 1M input tokens and 76.06 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.
How is Codestral (latest) different from other Mistral models?
Codestral (latest) belongs to the Codestral family at Mistral. Models in the Mistral line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Mistral model is listed on the provider page.
What capabilities does Codestral (latest) support?
The declared capabilities of Codestral (latest) are: tool calling. It accepts text as input, and every attachment consumes tokens from the shared context window of 256K tokens. The list comes from the Mistral model card and is refreshed with the catalog as of September 2026.
Does Codestral (latest) have open weights?
Yes, Codestral (latest) ships with open weights, so it can be downloaded and served on your own hardware instead of being used only through the Mistral API. What you may do with it is set by the license shown on the card. Catalog prices cover hosted API access.