LLM Reference

Devstral Models by MistralAI

3 models2025Up to 256k ctxFrom $0.1/1M input

About

Devstral is a family of 3 AI models by MistralAI, released in 2025.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

3 in view

Use when the workload needs code, 256k context, and 24B parameters.

2025-12code256k context24B parameters

Use when the workload needs code, 123B parameters, and structured outputs.

2025-12code123B parametersstructured outputs

Use when the workload needs code, 131k context, and tool use.

2025-07code131k contexttool use

Release Timeline

2 release groups
2025-12
2 current
Devstral Small 2
code256k context24B parameters
Current
Mistral Devstral 2 123B
code123B parametersstructured outputs
Current
2025-07
1 current
Devstral Medium 2507
code131k contexttool use
Current

Specifications(3 models)

Devstral model specifications comparison
ModelReleasedContextParametersVisionMultimodalFn CallingTool UseStructured OutputsCode Exec
Devstral Small 22025-12256k24BYesYesYesYesYesYes
Mistral Devstral 2 123B2025-12123BNoNoNoNoYesYes
Devstral Medium 25072025-07131kNoNoYesYesNoNo

Available From(2 providers)

Pricing

Devstral model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Devstral Small 2Vercel AI Gateway$0.1$0.3Serverless
Mistral Devstral 2 123BAWS Bedrock$0.4$2Serverless

Frequently Asked Questions

What is Devstral used for?
Devstral is used for code, vision and multimodal work, and agent workflows and tool use. The family description and listed model capabilities point to those workloads as the best fit.
How does Devstral compare to Ministral?
Devstral by MistralAI is strongest where you need code, while Ministral by MistralAI is the closest related family to check for structured outputs. Devstral has 3 listed variants and reaches up to 256k context, while Ministral reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
Which Devstral model should I use?
For the lowest listed input price, start with Devstral Small 2 through Vercel AI Gateway at $0.1/1M input tokens. For the most capable/latest local choice, evaluate Devstral Small 2 with 256k context and tool use, function calling, structured outputs, and multimodal inputs.

Models(3)