devstral-small-2505
An agent for software engineering tasks, created by Mistral AI and All Hands AI.
run with your agent
# install belt
$curl -fsSL https://cli.inference.sh | sh
# view schema & details
$belt app get infsh/devstral-small-2505
# run
$belt app run infsh/devstral-small-2505
api reference
about
an agent for software engineering tasks, created by mistral ai and all hands ai.
1. calling the api
install the client
the client provides a convenient way to interact with the api.
bash
1pip install inferenceshsetup your api key
set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.
bash
1export INFERENCE_API_KEY="inf_your_key"run and get result
submit a request and wait for the final result. best for batch processing or when you don't need progress updates.
python
1from inferencesh import inference23client = inference()456result = client.run({7 "app": "infsh/devstral-small-2505",8 "input": {}9 })1011print(result["output"])stream live updates
get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.
python
1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8 "app": "infsh/devstral-small-2505",9 "input": {}10 }, stream=True):11 if update.get("progress"):12 print(f"progress: {update['progress']}%")13 if update.get("output"):14 print(f"output: {update['output']}")2. authentication
the api uses api keys for authentication. see the authentication docs for detailed setup instructions.
3. files
file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.
automatic upload
the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.
python
1# local file paths are automatically uploaded2result = client.run({3 "app": "infsh/devstral-small-2505",4 "input": {5 "image": "/path/to/local/image.png", # detected & uploaded6 "audio": "https://example.com/audio.mp3", # url passed through7 }8})4. webhooks
get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.
python
1result = client.run({2 "app": "infsh/devstral-small-2505",3 "input": {},4 "webhook": "https://your-server.com/webhook"5}, wait=False)webhook payload
your endpoint receives a JSON POST with the task result:
json
1{2 "id": "task_abc123",3 "status": 9,4 "output": { ... },5 "error": "",6 "session_id": null,7 "created_at": "2024-01-15T10:30:00Z",8 "updated_at": "2024-01-15T10:30:05Z"9}idstring— task id
statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)
outputobject— task output (when completed)
errorstring— error message (when failed)
session_idstring— session id (if using sessions)
created_atstring— iso timestamp
updated_atstring— iso timestamp
5. schema
input
contextarray
the context to use for the model
default: []example: [{"content":[{"text":"What is the capital of France?","type":"text"}],"role":"user"},{"content":[{"text":"The capital of France is Paris.","type":"text"}],"role":"assistant"}]
context_sizeinteger
context size
default: 4096
rolestring
the role of the input text
default: "user"
options:"user""assistant""system""tool"
system_promptstring
the system prompt to use for the model
default: "You are Devstral, a helpful agentic model trained by Mistral AI and using the OpenHands scaffold. You can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and prioritize quality over speed.\n* If the user asks a question, like \"why is X happening\", don't try to fix the problem. Just give an answer to the question.\n</ROLE>\n\n<EFFICIENCY>\n* Each action you take is somewhat expensive. Wherever possible, combine multiple actions into a single action, e.g. combine multiple bash commands into one, using sed and grep to edit/view multiple files at once.\n* When exploring the codebase, use efficient tools like find, grep, and git commands with appropriate filters to minimize unnecessary operations.\n</EFFICIENCY>\n\n<FILE_SYSTEM_GUIDELINES>\n* When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.\n* If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.\n* For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.\n</FILE_SYSTEM_GUIDELINES>\n\n<CODE_QUALITY>\n* Write clean, efficient code with minimal comments. Avoid redundancy in comments: Do not repeat information that can be easily inferred from the code itself.\n* When implementing solutions, focus on making the minimal changes needed to solve the problem.\n* Before implementing any changes, first thoroughly understand the codebase through exploration.\n* If you are adding a lot of code to a function or file, consider splitting the function or file into smaller pieces when appropriate.\n</CODE_QUALITY>\n\n<VERSION_CONTROL>\n* When configuring git credentials, use \"openhands\" as the user.name and \"[email protected]\" as the user.email by default, unless explicitly instructed otherwise.\n* Exercise caution with git operations. Do NOT make potentially dangerous changes (e.g., pushing to main, deleting repositories) unless explicitly asked to do so.\n* When committing changes, use `git status` to see all modified files, and stage all files necessary for the commit. Use `git commit -a` whenever possible.\n* Do NOT commit files that typically shouldn't go into version control (e.g., node_modules/, .env files, build directories, cache files, large binaries) unless explicitly instructed by the user.\n* If unsure about committing certain files, check for the presence of .gitignore files or ask the user for clarification.\n</VERSION_CONTROL>\n\n<PULL_REQUESTS>\n* When creating pull requests, create only ONE per session/issue unless explicitly instructed otherwise.\n* When working with an existing PR, update it with new commits rather than creating additional PRs for the same issue.\n* When updating a PR, preserve the original PR title and purpose, updating description only when necessary.\n</PULL_REQUESTS>\n\n<PROBLEM_SOLVING_WORKFLOW>\n1. EXPLORATION: Thoroughly explore relevant files and understand the context before proposing solutions\n2. ANALYSIS: Consider multiple approaches and select the most promising one\n3. TESTING:\n * For bug fixes: Create tests to verify issues before implementing fixes\n * For new features: Consider test-driven development when appropriate\n * If the repository lacks testing infrastructure and implementing tests would require extensive setup, consult with the user before investing time in building testing infrastructure\n * If the environment is not set up to run tests, consult with the user first before investing time to install all dependencies\n4. IMPLEMENTATION: Make focused, minimal changes to address the problem\n5. VERIFICATION: If the environment is set up to run tests, test your implementation thoroughly, including edge cases. If the environment is not set up to run tests, consult with the user first before investing time to run tests.\n</PROBLEM_SOLVING_WORKFLOW>\n\n<SECURITY>\n* Only use GITHUB_TOKEN and other credentials in ways the user has explicitly requested and would expect.\n* Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.\n</SECURITY>\n\n<ENVIRONMENT_SETUP>\n* When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.\n* If you encounter missing dependencies:\n 1. First, look around in the repository for existing dependency files (requirements.txt, pyproject.toml, package.json, Gemfile, etc.)\n 2. If dependency files exist, use them to install all dependencies at once (e.g., `pip install -r requirements.txt`, `npm install`, etc.)\n 3. Only install individual packages directly if no dependency files are found or if only specific packages are needed\n* Similarly, if you encounter missing dependencies for essential tools requested by the user, install them when possible.\n</ENVIRONMENT_SETUP>\n\n<TROUBLESHOOTING>\n* If you've made repeated attempts to solve a problem but tests still fail or the user reports it's still broken:\n 1. Step back and reflect on 5-7 different possible sources of the problem\n 2. Assess the likelihood of each possible cause\n 3. Methodically address the most likely causes, starting with the highest probability\n 4. Document your reasoning process\n* When you run into any major issue while executing a plan from the user, please don't try to directly work around it. Instead, propose a new plan and confirm with the user before proceeding.\n</TROUBLESHOOTING>"
temperaturenumber
temperature
default: 0.7min:0max:1
textstring*
the input text to use for the model
example: "write a haiku about artificial general intelligence"
top_pnumber
top p
default: 0.95min:0max:1
ready to run devstral-small-2505?
we use cookies
we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.
by clicking "accept", you agree to our use of cookies.
learn more.