Mistral Codestral

MistralPersonalstable热度: 53

Coding-focused model

Function CallMCPJSON Modecoding
上下文
32,000 tokens
最大输出
8,192 tokens
发布时间
2024/5/29
供应商
2

Overview

Coding-focused model

Key Highlights

  • Function Call
  • MCP
  • JSON Mode

Brand

Mistral

Personal

国家: France

View all models, pricing and details from Mistral.

Specifications

Basic Information

模型Mistral Codestral
品牌Mistral
Version2024-05
Model Typecoding
状态stable
发布时间2024/5/29
热度53

Architecture

Parameter SizeUnknown / Not disclosed
Architecture TypeUnknown / Not disclosed
Attention MechanismUnknown / Not disclosed
TokenizerUnknown / Not disclosed
Vocabulary SizeUnknown / Not disclosed

Context & I/O

上下文32,000 tokens
最大输出8,192 tokens
ModalitiesFunction Call, MCP, JSON Mode
LanguagesUnknown / Not disclosed

Capabilities

VisionNo
AudioNo
ReasoningNo
Function CallYes
MCPYes
JSON ModeYes
EmbeddingNo

Training Data

Training DatasetUnknown / Not disclosed
Estimated Data SizeUnknown / Not disclosed
Knowledge CutoffUnknown / Not disclosed

Inference & Deployment

API AccessYes
VRAM EstimateUnknown / Not disclosed
Quantization SupportUnknown / Not disclosed
Hardware RequirementsUnknown / Not disclosed

Safety & Compliance

Safety EvaluationsUnknown / Not disclosed
Content PolicyUnknown / Not disclosed
Region RestrictionsUnknown / Not disclosed

License & Pricing

LicenseUnknown / Not disclosed
Commercial UseUnknown / Not disclosed
Open SourceNo

Provider & Pricing

供应商输入输出缓存批量官网
Mistral API¥1.440/1M¥4.320/1M¥0.720/1M¥2.160/1M访问官网

价格变动

暂无价格变动。

基准测试

No benchmark data available.

Changelog

  • Page created / data imported
    2026/9/12
  • Last updated
    2026/9/12

FAQ

What is Mistral Codestral?

Coding-focused model

Who developed Mistral Codestral?

Mistral Codestral was developed by Mistral. You can learn more on the brand page or official website.

What is the context length of Mistral Codestral?

Mistral Codestral supports up to 32,000 tokens of context.

How much does Mistral Codestral API cost?

API pricing for Mistral Codestral starts at ¥1.440/1M per 1M input tokens and ¥4.320/1M per 1M output tokens. See the pricing table above for provider-specific rates.

References

More from Mistral