Codestral
Language model for code completion specializing in low-latency, high-frequency tasks such as fill-in-the-middle and code generation.
Specs
- Context
- 131.1K
- Max output
- —
- Input price
- $0.3/ 1M tokens
- Output price
- $0.9/ 1M tokens
- Released
- 2025-07-30
Context
- Context window
- 131.1K
- Max input
- —
- Max output
- —
Pricing · USD / 1M tokens
- Input
- $0.3
- Output
- $0.9
- Cache read
- $0.03
- Cache write
- —
Modalities
- Input
- Text
- Output
- Text
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2025-07-30
- Knowledge cutoff
- —
Features
- Confirmed
How to call
1 provider
mistralmodel = codestral-2508
chat
POSThttps://api.mistral.ai/v1/chat/completions
batch
POSThttps://api.mistral.ai/v1/batch
JSON
Standard format
{
"id": "codestral-2508",
"object": "model",
"created": 1753833600,
"owned_by": "mistral",
"name": "Codestral",
"api": {
"types": [
"chat",
"batch"
]
},
"limits": {
"context": 131072,
"input": null,
"output": null
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.3,
"output": 0.9,
"cache_read": 0.03,
"cache_write": null
},
"features": [
"tools",
"structured_output",
"caching",
"batch"
],
"info": {
"status": "active",
"release_date": "2025-07-30",
"knowledge_cutoff": null,
"description": "Language model for code completion specializing in low-latency, high-frequency tasks such as fill-in-the-middle and code generation.",
"docs": "https://docs.mistral.ai/models/codestral-25-08",
"verified_at": "2026-10-10"
}
}Official sources
4