Devstral 2

mistralai/devstral-2512

Run Devstral 2 in a hosted Python Task with structured output and file inputs.

Mistral's Devstral 2 model via OpenRouter. 123B-parameter dense transformer model specializing in agentic coding across multiple files. Features 262K context window for handling complex codebases.

What Devstral 2 supports in qbash

Structured outputReplies as JSON that matches a schema you pass.
Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more files.
Prompt cachingRepeated input is billed at the cached rate.

What is qbash?

qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like Devstral 2 only at the ones that need judgment, with integrations, memory and files available in the same script.

A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.

How Tasks work

Specifications

Context window: 262Ktokens
Max output: 8,192tokens
Temperature: 0 to 1default 0.3

Structured output with Devstral 2 in a Python Task

qbash.ai.raw calls Devstral 2 from a Task. Pass a JSON Schema as output_schema and the reply comes back as a Python dict that matches it, ready to route to a connector.

main.py
ticket = qbash.inputs.get("ticket")

triage = qbash.ai.raw(
    f"Summarize this support ticket and rate its urgency:\n\n{ticket}",
    model="mistralai/devstral-2512",
    output_schema={
        "type": "object",
        "properties": {
            "summary": {"type": "string"},
            "urgency": {"type": "string", "enum": ["low", "medium", "high"]},
        },
        "required": ["summary", "urgency"],
    },
)

# triage is a dict, e.g. {"summary": "...", "urgency": "high"}
if triage["urgency"] == "high":
    qbash.integrations.slack.create_message(
        channel="#support",
        text=triage["summary"],
    )

qbash.output(triage)

Structured output in Tasks

Devstral 2 pricing

Input	$0.40 per 1M tokens
Output	$2.00 per 1M tokens
Cached input	$0.04 per 1M tokens

Standard rates in USD.

Supported file formats

Documents

PDF
TEXT
DOC
XLS
RTF
DOCX
XLSX
PPTX
PPT
ODT
ODP
ODS