GLM 5.2 is live! Opus-level intelligence at open-source rates. Pay per token on serverless. Try it today.

Model Library
/Mistral/Devstral-Small-2505
Mistral Logo Icon

Devstral-Small-2505

Ready
model path:accounts/fireworks/models/devstral-small-2505

Devstral is an agentic LLM for software engineering tasks built under a collaboration between Mistral AI and All Hands AI πŸ™Œ. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents.

Devstral-Small-2505 API Features

Fine-tuning

Docs

Devstral-Small-2505 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

On-demand Deployment

Docs

On-demand deployments allow you to use Devstral-Small-2505 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
5/22/2025
Kind
Base model
Provider
Mistral

Specification

Calibrated
No
Mixture-of-Experts
No
Parameters
23.5B

Supported Functionality

Fine-tuning
Supported
Serverless
Not supported
Context Length
131k tokens
Function Calling
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported