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...
按量付费
无需预付费用,仅按实际使用量付费
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)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.
| Specification | Value |
|---|---|
| Provider | Mistralai |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 131072 tokens |
| Max Output | tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.1 |
| Output | $0.3 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: mistralai/devstral-small
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 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!"}]
}'
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
通过我们的统一 API 接入 Devstral Small — 兼容 OpenAI、无冷启动、透明计费。
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 单次请求最多支持 131K 上下文 token,输出最多 — token。
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。
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。