Devstral 2 123B
Mistral AI · Active · available in 13 of 31 regions
- Context window
- —
- Max output
- —
- Input / 1M
- —
- Output / 1M
- —
What Devstral 2 123B is good for
editorialDevstral 2 123B, with no token price published by AWS. Callable in 13 of 31 regions.
Suits
- Nothing specific stands out from the published capabilities.
Think twice if
- Agentic loops. No prompt caching published, so every step re-pays full price for the prompt prefix. Expensive for agents that resend a long context.
- Function calling. No tool use, so it cannot drive an agent loop or call your APIs — it answers from what is in the prompt.
- Documents with layout. Text only. Scanned PDFs, screenshots and charts need a vision model or an OCR step first.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Where teams typically use it
Coding
Writing, reviewing and refactoring code, usually across more than one file.
- · A review pass that flags real defects with a severity and leaves style alone.
- · A framework upgrade applied across a repository, one module at a time, tests green between each.
- · Turning a failing bug report into a reproducing test and then a fix.
Agentic workflows
Multi-step work where the model calls tools, reads the results and decides what to do next.
- · A support agent that looks up the order, checks the refund policy and drafts the reply before a human approves it.
- · An on-call assistant that reads logs and metrics, forms a hypothesis, and proposes the one command to run.
- · A migration bot that opens a pull request per file and reruns the test suite between each change.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Pricing by region
USD per 1M tokensNo published token pricing
The AWS Price List API publishes no token SKU for this model, and it is not in our curated overlay. This is common for embedding, image and video models, which bill per request or per second rather than per token.
Check the AWS pricing page →Region availability
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, Devstral 2 123B can be served without the request leaving 12 of the 25 jurisdictions with a Bedrock region.
Common questions
- Which AWS regions support Devstral 2 123B?
- 13 of 31 regions: us-east-1, us-east-2, us-west-2, eu-west-1, eu-west-2, eu-central-1, eu-north-1, eu-south-1, ap-northeast-1, ap-south-1, ap-southeast-2, ap-southeast-3, sa-east-1.
- What is the model ID for Devstral 2 123B on Bedrock?
- mistral.devstral-2-123b.