Devstral 2 123B is Mistral AI's language model with a 256K context window and up to 8K output tokens, starting at $0.400 / 1M input and $2.00 / 1M output. The full 123B-parameter version of Devstral 2, Mistral AI's enterprise-grade agentic coding model for complex software engineering tasks.
Specifications
Canonical IDmistral-devstral-2-123b
TypeLanguage
StatusActive
CreatorMistral AIMistral AI
Providers
Context Window256K tokens
Max Output8K tokens
Input ModalitiesText
Output ModalitiesText
Parameters123B
Release Date · 3 months ago

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandardBatchFlexPriority
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
mistral.devstral-2-123b
$0.400$2.00$0.200$1.00$0.200$1.00$0.700$3.50
View Amazon Bedrock

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Devstral 2 123B256K$0.400$2.00Current
Devstral 2256K$0.400$2.00Available
Devstral Small 2256K$0.100$0.300Available
Devstral262K$0.400$2.00Available
Devstral Medium256K$0.400$2.00Available

Model IDs