Devstral 2 2512

Provider: Mistral AI EU Official API price

Input price
$0.40
/ 1M tokens
Output price
$2.00
/ 1M tokens
Cache price
$0.04
/ 1M tokens (read)
Context
262K tokens
Max output 210K tokens

Overview

Mistral AI (EU) offers Devstral 2 2512 as a powerful, long-context model targeting advanced developer workloads. It is positioned for flagship-level performance in applications requiring extensive context processing and structured interactions.

Strengths

  • Features an extensive 262,144 token context window for processing vast amounts of information.
  • Supports robust function-calling, enabling complex tool integration and agentic workflows.
  • Provides reliable JSON-mode output for structured data generation and API interactions.
  • Offers a low cache read price of $0.04/M tokens, indicating efficiency for repeated context use.
  • Competitive input pricing ($0.40/M tokens) compared to many high-tier peers from other providers.

Best use cases

  • Analyzing large codebases or extensive legal and technical documentation.
  • Building sophisticated agents that interact with external tools via function calling.
  • Generating structured data outputs for database population or API requests.
  • Summarizing very long conversations, articles, or books with deep context.
  • Advanced RAG applications requiring the ingestion of massive input texts.

Pricing position

Devstral 2 2512 is Mistral AI's most premium offering, with an input price of $0.40/M tokens and an output price of $2.00/M tokens. This makes it substantially more expensive than sibling models like Mistral Small 3.2 ($0.075/M in, $0.20/M out). Its input cost is identical to many high-end peers such as GPT-4.1 Mini, though its output price is higher than Llama 3.1 70B Instruct ($0.40/M out) but lower than MiniMax M1 ($2.20/M out).

Caveats

The maximum output token limit for Devstral 2 2512 is currently unknown based on the provided data. Developers should consider more cost-optimized Mistral models like Small 3 for shorter context tasks or if the high output price of $2.00/M becomes a concern. This model does not offer a free tier, requiring immediate paid access for usage.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
210K tokens
Listed on OpenRouter
2025-12-09
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Function callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.14
1M (small app) 1 0.5 $1.40
10M (mid scale) 10 5 $14.00
100M (large) 100 50 $140.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API (mistralai/devstral-2512)