Skip to content

Codestral 2

mistral/codestral-2
Coding

Fast, 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

Free
Pricing for Codestral 2, per 1M tokens
RatePriceUnit
Input$0.00per 1M tokens
Output not charged

Free at the point of use; fair-use rate limits apply to the free tier. Illustrative placeholder pricing.

Context window

256Ktokens

covers prompt and response together, so a long input leaves less room for the answer.

256K tokens against a peer range of 128K to 1M, median 256K. Compared across 4 coding models.

Supported features

Feature support for Codestral 2
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputNot supported
Audio inputNot supported
Long contextNot supported
Open weightsNot supported
ReasoningNot supported
Fine-tunableSupported
BatchNot supported
CachingNot supported

Example use cases

  • IDE completion

    Very fast completions

  • Code translation

    Fine-tunable

  • Everyday generation

    80+ language coverage

Comparison

Codestral 2 compared with DeepSeek Coder V2 and Qwen3 Coder
AttributeCodestral 2DeepSeek Coder V2Qwen3 Coder
Context window256K128K256K
Input price$0.00$0.00$0.00
Output price not charged not charged not charged
Tool callingSupportedSupportedSupported
JSON modeSupportedSupportedSupported
Vision inputNot supportedNot supportedNot supported
Open weightsNot supportedSupportedSupported
Prompt cachingNot supportedNot supportedNot supported

Best value in each row is highlighted. Illustrative placeholder data.

Provider information

View Mistral
Mistral4 models

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 $0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.