Skip to content
LLMs
Mistral AI logo

Mistral: Devstral 2 2512

by Mistral AI

Mistral: Devstral 2 2512 is a large language model from Mistral AI. It costs $0.400 per million input tokens and $2.00 per million output tokens. Its context window is 262K tokens.

Tool callingStructured outputPrompt cachingOpen weightsfile input
Input / 1M tokens
$0.400
Output / 1M tokens
$2.00
Cached input / 1M
$0.040

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

1 hosts serve Devstral 2 2512. Same weights, same API - the price difference is pure margin and routing.

Providers serving Mistral: Devstral 2 2512, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
MistralCheapest$0.400$2.00262K-100.0%

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
9.4
Coding index
31.3
Agentic index
4.9

About Devstral 2 2512

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

Specifications

Mistral: Devstral 2 2512 specifications
Model IDmistralai/devstral-2512
ProviderMistral AI
Context window262K tokens
Max output210K tokens
Input modalitiestext, file
Output modalitiestext
Knowledge cutoff-
Open weightsYes - mistralai/Devstral-2-123B-Instruct-2512
ReleasedDecember 9, 2025

Cheaper alternatives

Models that cost less than Devstral 2 2512 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Mistral: Devstral 2 2512 cost?

$0.400 per million input tokens and $2.00 per million output tokens. Cached input reads cost $0.040 per million tokens.

What is the context window of Mistral: Devstral 2 2512?

262K tokens, with up to 210K tokens of output per request.

Confirm against the source: Mistral AI official pricing.