Seedance 2.0 | Special Offer ✦ 10% OFF NOW | Ends May 13 (UTC+0)
mistral
mistralai/devstral-small

mistralai/devstral-small

131,072 context · $0.10/M input tokens · $0.30/M output tokens

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...

定价

按量付费

无需预付费用,仅按实际使用量付费

输入$0.10 / M Tokens
输出$0.30 / M Tokens

试用模型

mistralai/devstral-small
在线
mistral
你好!我是乐于助人的 AI 助手。需要我帮你做什么?

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/devstral-small",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

模型介绍

Mistralai devstral-small

Devstral Small 1

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and released under the Apache 2.0 license, it features a 128k token context window and supports both Mistral-style function calling and XML output formats.

Designed for agentic coding workflows, Devstral Small 1.1 is optimized for tasks such as codebase exploration, multi-file edits, and integration into autonomous development agents like OpenHands and Cline. It achieves 53.6% on SWE-Bench Verified, surpassing all other open models on this benchmark, while remaining lightweight enough to run on a single 4090 GPU or Apple silicon machine. The model uses a Tekken tokenizer with a 131k vocabulary and is deployable via vLLM, Transformers, Ollama, LM Studio, and other OpenAI-compatible runtimes.


Why It Looks Great

  • Large Language Model architecture for efficient processing
  • 131072 context window for long document handling
  • Competitive pricing at $0.1/$0.3 per million tokens

Key Features

  • Context Window: 131072 tokens
  • Max Output: N/A tokens
  • Vision: Supported
  • Function Calling: Supported

Specifications

SpecificationValue
ProviderMistralai
Model TypeLarge Language Model (LLM)
ArchitectureN/A
Context Window131072 tokens
Max Outputtokens
InputText
OutputText
VisionSupported
Function CallingSupported

Pricing

Token TypeCost per Million Tokens
Input$0.1
Output$0.3

How to Use

  1. Write your prompt — describe the task, provide context, and specify desired output format.
  2. 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/devstral-small


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/devstral-small",
    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/devstral-small",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: mistralai/devstral-small
  • Provider: Mistralai

信息

提供商mistral
类型llm

支持功能

输入
文本
输出
文本
上下文131,072
最大输出-
视觉-
函数调用✓ 支持

API 访问指南

Base URLhttps://llm.wavespeed.ai/v1
API 端点chat/completions
Model IDmistralai/devstral-small

Devstral Small API

mistralai/devstral-small

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...

输入

$0.1 /M

输出

$0.3 /M

上下文

131K

工具调用

支持

在 WaveSpeedAI 试用 Devstral Small

通过我们的统一 API 接入 Devstral Small — 兼容 OpenAI、无冷启动、透明计费。

关于 Devstral Small 的常见问题

Devstral Small API 多少钱?+

WaveSpeedAI 定价:输入每百万 token $0.10,输出每百万 token $0.30。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。

Devstral Small 的上下文窗口是多大?+

Devstral Small 单次请求最多支持 131K 上下文 token,输出最多 — token。

Devstral Small 是否兼容 OpenAI?+

是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 Devstral Small。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 Devstral Small?+

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 Devstral Small。

相关 LLM API