Mistral: Devstral Small

Mistral coding agent model for repository tasks and software engineering workflows

Model lab: Mistral
Model family: devstral

Model resources

Hugging Face

Modalitiestext → text

Context window128,000

Maximum output128,000

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to mistral/devstral-small-2507.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "mistral/devstral-small-2507"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Devstral Small API Pricing

Price under review

Benchmarks

Intelligence Index · v4.37.6

Coding Index—

Agentic Index—

Benchmark	Score	Measurement	Source
SWE-Bench Verified	53.6	resolved · Date: 2025-07-10

Performance

Performance trends

Throughput86.5 tok/sCurrent

Time to first token1.5 sCurrent

End-to-end latency7.5 sCurrent

Throughput

Current86.5 tok/s

Window average88.8 tok/s

Time to first token

Current1.5 s

Window average1.4 s

End-to-end latency

Current7.5 s

Window average7.5 s

Tail latency (P99)

Current14.9 s

Window average17.1 s

Prompt cache hit rate

Current26.5%

Window average23.3%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Devstral Small Compare models

Model	Input price	Output price	Context window	Capabilities
Devstral SmallThis page	Price under review	Price under review	128,000	Text output · Tool calling
Devstral 2	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	262,144	Text output · Tool calling
Devstral 2 (latest)	USD 0.32 / 1M tokens	USD 1.6 / 1M tokens	262,144	Text output · Tool calling
Devstral Medium	Price under review	Price under review	128,000	Text output · Tool calling
Devstral Small 2	USD 0.08 / 1M tokens · Context ≤ 256000 tokens · Maximum output 131072 tokens	USD 0.24 / 1M tokens · Context ≤ 256000 tokens · Maximum output 131072 tokens	262,144	Text output · Tool calling

Model specifications

Input: text
Output: text
Context window: 128,000
Maximum output: 128,000
Release date: 2025-07-10
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Devstral Small for?

Mistral coding agent model for repository tasks and software engineering workflows

What inputs and outputs does Devstral Small support?

Recorded inputs: text; outputs: text.

How is Devstral Small priced?

This page does not list a price for this model yet.

What specifications are recorded for Devstral Small?

Current model records list Context window 128,000 tokens; Maximum output 128,000 tokens.

What model parameter does the Quickstart use?

The example uses mistral/devstral-small-2507. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.