mistralai/codestral-2508
256,000 context · $0.30/M input tokens · $0.90/M output tokens
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post
定价
按量付费
无需预付费用，仅按实际使用量付费
试用模型
API 使用
使用以下代码示例接入我们的 API：
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="mistralai/codestral-2508",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)模型介绍
Mistralai codestral-2508
mistralai codestral-2508
Why It Looks Great
- Large Language Model architecture for efficient processing
- 256000 context window for long document handling
- Competitive pricing at $0.3/$0.10 per million tokens
Key Features
- Context Window: 256000 tokens
- Max Output: 4096 tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Mistralai |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 256000 tokens |
| Max Output | 4096 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.3 |
| Output | $0.10 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: mistralai/codestral-2508
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="mistralai/codestral-2508",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "mistralai/codestral-2508",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: mistralai/codestral-2508
- Provider: Mistralai
信息
支持功能
API 访问指南
Codestral 2508 API
mistralai/codestral-2508
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
输入
$0.3 /M
输出
$0.9 /M
上下文
256K
最大输出
4K
工具调用
支持
在 WaveSpeedAI 试用 Codestral 2508
通过我们的统一 API 接入 Codestral 2508 — 兼容 OpenAI、无冷启动、透明计费。
关于 Codestral 2508 的常见问题
Codestral 2508 API 多少钱?+
WaveSpeedAI 定价:输入每百万 token $0.30,输出每百万 token $0.90。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。
Codestral 2508 的上下文窗口是多大?+
Codestral 2508 单次请求最多支持 256K 上下文 token,输出最多 4K token。
Codestral 2508 是否兼容 OpenAI?+
是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 Codestral 2508。把官方 OpenAI SDK 的 base URL 指向该地址,使用 WaveSpeedAI 的 API Key 即可,无需任何其他代码改动。
如何开始使用 Codestral 2508?+
登录 WaveSpeedAI,在 Access Keys 中生成 API Key,使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。新账户可获得免费额度,用于试用 Codestral 2508。