Mistral Devstral 2 123B

Name: Mistral Devstral 2 123B
Author: MistralAI

Released

2025-12-01

Last refreshed

2026-09-14

Status

Researched 18d ago

Open weightsCommercial use: conditionalCodingAgentsClassificationJSON / Tool use

MistralAI releases · 16 in the last 12 months · this family litChangelog →

Specifications

Family: Devstral
Released: 2025-12-01
Parameters: 123B
Specialization: code
Openness: Open weights
License: Mistral Modified MIT LicenseCommercial use: conditional
Weights: Not released
Code: Unknown

Created by

MistralAI

Enterprise AI solutions for trust and transparency.

Paris, France

Founded 2023

Website

Pricing

Output / 1M

$2.00

Input / 1M

$0.400

Cheapest of 2 routes · AWS Bedrock

Providers(2)

AWS Bedrock Mistral AI Studio

View 2 provider routes

About

Mistral Devstral 2 123B is MistralAI's Devstral model focused on code generation and software engineering. It was released 2025-12-01.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
AWS Bedrock	$0.400	$2.00	Serverless
Mistral AI Studio	$0.400	$2.00	Serverless

Available via routers & gateways(11)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSMistral AI Studio

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughMistral AI Studio

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionMistral AI Studio

AIRouter

Router

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough + feeMistral AI Studio

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Martian

Router

AI-powered LLM router that analyzes each prompt in real-time to select the optimal model, targeting 20–97% cost reduction while maintaining quality; San Francisco startup reportedly nearing $1.3B valuation.

Passthrough + feeMistral AI Studio