Devstral 2
Mistral AIdocs.mistral.ai/models/devstral-2-25-12
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
Updated 6 h ago · first seen 11 Sept 2026
model_01M2943ZTNM6587XB64Q2V4CWZ
Overview
Identity
Identity block not returned by the API for this entity.
Openness
Openness not classified yet — no sourced evidence to place this model in the ontology.
Key facts
- Release date
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
- Status
Source:Mistral AI docsT1observed 13 h agohigh
- Version
Source:Mistral AI docsT1observed 13 h agohigh
- Deprecation date
Source:Mistral AI docsT1observed 13 h agohigh
- Retirement date
Source:Mistral AI docsT1observed 13 h agohigh
- Official page
Source:Mistral AI docsT1observed 13 h agohigh
- API model id
Source:Mistral AI docsT1observed 13 h agohigh
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
Architecture
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
Capabilities
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 10 h agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 13 h agomedium
Benchmarks10
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
No benchmark results recorded
Providers & Pricing1
All offers in the price terminal →USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Price history
Output price · USD / 1M tokens 1 provider
- Mistral AI La Plateforme
- Mistral AI La Plateformefirst observed $211 Sept 2026
Input price · USD / 1M tokens 1 provider
- Mistral AI La Plateforme
- Mistral AI La Plateformefirst observed $0.4011 Sept 2026
Timeline14
Full timeline →Devstral 2: context length changed from 256000 to 262144
Context window256K tokens→262.1K tokensopenrouterDevstral 2 scores 53.8% on SWE-bench Verified
swebench_leaderboardDevstral 2 scores 18.94% on Terminal-Bench
artificial_analysisDevstral 2 scores 30.34% on Terminal-Bench
artificial_analysisDevstral 2 scores 3.57% on Humanity's Last Exam
artificial_analysisDevstral 2 scores 9.41 on Artificial Analysis Intelligence Index
artificial_analysisDevstral 2: context length changed from 262144 to 256000
Context window262.1K tokens→256K tokensartificial_analysisMistral AI La Plateforme lists Devstral 2 at $0.4 in / $2 out per 1M tokens
openrouter
Change history20
Viewing AI Atlas as of 12 Mar 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Devstral 2 was not yet in AI Atlas on 12 Mar 2026
Versionversion1
Release daterelease_date1
Statusstatus1
Context windowcontext_length1
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Tokenizertokenizer1
API model idapi_model_id1
Deprecation datedeprecation_date1
Retirement dateretirement_date1
Hugging Face repohf_repo1
Official pageofficial_url1
Descriptiondescription1
File inputfile_input1
Openrouter idopenrouter_id1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
24
Source tiers
T1T26 / 18
Freshest observation
6 h ago
Conflicts
None
Source documents 4
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (69/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →