Codestral (latest) pricing, context window and limits
Codestral (latest) costs $0.3 per million input tokens and $0.9 per million output tokens at Mistral AI list price. It accepts up to 256,000 tokens of context and returns up to 4,096 tokens.
- Model id
codestral-latest - Snapshot
What does Codestral (latest) cost?
| Input | $0.3 |
|---|---|
| Output | $0.9 |
| Cached input (read) | $0.03 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Codestral (latest) read and write?
| Context window | 256,000 |
|---|---|
| Max output | 4,096 |
What can Codestral (latest) do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | No |
| Input | text |
| Output | text |
What does a request to Codestral (latest) cost?
| A typical request: 1,000 tokens in, 500 out | $0.00075 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0039 |
| 1,000 typical requests | $0.75 |
| 1 million tokens in and 1 million out | $1.2 |
Input read from the provider's prompt cache costs $0.03 per million tokens instead of $0.3, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.00048 instead of $0.00075.
Among 40 Mistral AI models with a published price, Codestral (latest) is the 20th cheapest by input price. Its context window is the 20th largest of 40. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Codestral (latest) through DVARA?
Configure the mistral provider in the DVARA LLM Gateway and send the model id codestral-latest. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Mistral AI models are there?
- Codestral 25.08$0.3 in · $0.9 out · 256K context
- Devstral 2$0.4 in · $2 out · 262K context
- Devstral 2$0.4 in · $2 out · 262K context
- Devstral Medium$0.4 in · $2 out · 128K context
- Devstral 2 (latest)$0.4 in · $2 out · 262K context
- Devstral Small 2505$0.1 in · $0.3 out · 128K context
- Devstral Small$0.1 in · $0.3 out · 128K context
- GLM-5.2$1.4 in · $4.4 out · 1.05M context
- Devstral Small 2$0 in · $0 out · 256K context
- Leanstral 1.5$0 in · $0 out · 262K context
- Magistral Medium (latest)$2 in · $5 out · 262K context
- Ministral 3 14B$0.2 in · $0.2 out · 262K context
Which models from other providers are similar to Codestral (latest)?
These are the closest in context window and input price, one per provider.
- Qwen3 MaxAlibaba Qwen · $0.359 in · $1.434 out · 262K context
- MiniMax-M2Amazon Bedrock · $0.3 in · $1.2 out · 205K context
- GPT-5 MiniOpenAI · $0.25 in · $2 out · 400K context
- GLM-4.6VZhipu GLM · $0.3 in · $0.9 out · 128K context
- Kimi K2.6Moonshot AI · $0.95 in · $4 out · 262K context