Codestral 2
mistral/codestral-2Fast, focused code generation, the efficiency pick for completion and everyday engineering.
Model overview
Context window
256K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
4
of 11 tags
Description
Codestral 2 is a coding model from Mistral. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Mistral’s stated focus is europe's frontier lab; efficient and open. The weights are not published, so it is API-only.
Capabilities
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- JSON mode
- Constrains the response to valid JSON matching a schema you supply.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Fine-tunable
- Can be further trained on your own data to specialise it.
Strengths & weaknesses
Strengths
- Very fast completions
- Fine-tunable
- 80+ language coverage
Weaknesses
- Agentic depth trails Sonnet and Qwen3 Coder
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
This model is not provisioned yet; the rate is quoted on request.
Context window
256Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Not supported |
| Reasoning | Not supported |
| Fine-tunable | Supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
IDE completion
Code translation
Everyday generation
Comparison
Compare against anything →| Attribute | Codestral 2 | DeepSeek Coder V2 | Qwen3 Coder |
|---|---|---|---|
| Context window | 256K | 128K | 256K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Supported | Supported |
| Vision input | Not supported | Not supported | Not supported |
| Open weights | Not supported | Supported | Supported |
| Prompt caching | Not supported | Not supported | Not supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View Mistral →Mistral · Paris, France · est. 2023
Mistral proved a small European team could ship frontier-relevant models within months of founding. Its efficient architectures, open releases and EU regulatory alignment made it the default choice for European enterprises, with Codestral and Voxtral extending the family into code and speech.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.
No. Codestral 2 is served through its provider's API only; the weights are not published, so self-hosting is not an option.
Prompt and response share one window: Codestral 2 accepts up to 256K tokens in total, so a long input leaves less room for the answer. The median across coding models is 256K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
DeepSeek Coder V2 is the closest neighbour in the catalogue, with 128K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.