LLM Pricing

← All Models

Mistral: Devstral 2 2512

🇫🇷 Mistral AI · Devstral 2

Input Price $0.400 per million tokens NT$12.8
Output Price $2.00 per million tokens NT$64.0
Context Window 262K tokens
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

Mistral: Devstral 2 2512 is a large language model API from Mistral AI, part of its Devstral 2 model family. Priced at $0.400 per million input tokens and $2.00 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 5× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. A large 262K-token context window (≈393 pages of text) lets it take in whole books, large codebases, or lengthy transcripts in a single call. Beyond plain text it also accepts File input, so it can be applied to multimodal tasks rather than text alone. On Artificial Analysis's Intelligence Index it scores 19 (D grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $0.400 NT$12.8
Output per 1M tokens $2.00 NT$64.0
Cached Input per 1M tokens $0.040 NT$1.3

Provider
Mistral AI
Model Family
Devstral 2
Version String
mistralai/devstral-2512
Status
Active
Modality
Text, File
Context Window
262,144 tokens
Output Limit
— tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Agentic Index 11 F Measured: 2026-07-01
Coding Index 31 C Measured: 2026-07-01
Intelligence Index 19 D Measured: 2026-07-01

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 30.0% D Measured: 2026-07-01
GPQA Diamond 59.4% C Measured: 2026-07-01
HLE 3.6% D Measured: 2026-07-01
IFBench 38.1% D Measured: 2026-07-01
Non-Hallucination 14.9% Measured: 2026-07-01
Omniscience Accuracy 21.0% Measured: 2026-07-01
SciCode 33.1% B Measured: 2026-07-01
Tau2 24.9% Measured: 2026-07-01
TerminalBench 18.9% Measured: 2026-07-01

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 1.6s Measured: 2026-07-01
Output Speed 47 t/s Measured: 2026-07-01
Response Time 12.3s Measured: 2026-07-01

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter
Input $0.400 OpenRouter
Cached Input $0.040 OpenRouter
Output $2.00 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • Mistral: Devstral 2 2512 Input price: $0.4/M tokens
  • Mistral: Devstral 2 2512 Output price: $2/M tokens
  • Context window: 262,144 tokens
  • Provider: Mistral AI
  • Model family: Devstral 2
  • Modalities: Text, File
  • Data source: OpenRouter, updated daily