Mistral AI logo

Mistral AI: Devstral Small 2

Compact multimodal coding model for repository exploration, file editing, and software agents

Source-linked devstral Open weights Apache-2.0 Released 2025-12-09
API record Report
InputT
OutputT
Input price$0.1/M
Output price$0.3/M
Context262.144K
Max output262.144K
Providers3
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Devstral Small 2
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Mistral labs-devstral-small-2512 256K 256K Tools Docs ↗
Pioneer devstral-small-2 256K 131.072K $0.1 $0.3 $0.1 Tools Docs ↗
Vercel AI Gateway mistral/devstral-small-2 256K 256K $0.1 $0.3 Tools Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.1/M

Across 2 priced providers

Median input $0.1/M

Midpoint of listed rates

Highest input $0.1/M

Same as the lowest listed rate

Output range $0.3 – $0.3

Per million output tokens

Pioneer $0.1/M
Vercel AI Gateway $0.1/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

2 providers list the identical $0.1 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
Tool calling Yes
? Structured output Unknown
Attachments Yes
Vision input Yes
Open weights Yes
Creator
Mistral AI
Model family
devstral
Knowledge cutoff
2025-12
License
Apache-2.0
Release date
2025-12-09
Model ID
mistral/devstral-small-2

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/mistral/devstral-small-2
curl
curl "https://model.kyssta.lol/api/v1/models/mistral/devstral-small-2"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Devstral Small 2?

Compact multimodal coding model for repository exploration, file editing, and software agents. It is published by Mistral AI and catalogued here from Models.dev.

How much does Devstral Small 2 cost?

Listed input pricing starts at $0.1 per million tokens from Pioneer.

What is the context length of Devstral Small 2?

Devstral Small 2 accepts up to 262.144K tokens of context and returns up to 262.144K output tokens.

Does Devstral Small 2 support tool calling and structured output?

Provider catalogs list support for tool calling, and image input.

Which providers serve Devstral Small 2?

3 providers list this model: Mistral, Pioneer, Vercel AI Gateway.

Are the weights for Devstral Small 2 open?

Yes. The weights are published and downloadable from Hugging Face under the Apache-2.0 license.

When was Devstral Small 2 released?

The catalog records a release date of 2025-12-09, last verified Sep 11, 2026.

More models from Mistral AI

View all →