Skip to content
Alpha
  • Models
  • Rankings
  • Ori
ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs models

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
  1. Home
  2. /
  3. Compare

Devstral 2 2512 vs Sonar Pro Search

Compare Devstral 2 2512 from Mistral AI and Sonar Pro Search from Perplexity on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for mistralai
Devstral 2 2512
Favicon for perplexity
Sonar Pro Search
Favicon for mistralai
Devstral 2 2512
Favicon for perplexity
Sonar Pro Search

Overview

Devstral 2 2512
Author
Mistral AI
Sonar Pro Search
Author
Perplexity
Devstral 2 2512
Context length
262Ktokens
Sonar Pro Search
Context length
200Ktokens
Devstral 2 2512
Reasoning
Sonar Pro Search
Reasoning
Devstral 2 2512
Input modalities
Sonar Pro Search
Input modalities
Devstral 2 2512
Output modalities
Sonar Pro Search
Output modalities

Devstral 2 2512 vs Sonar Pro Search: side-by-side summary

Devstral 2 2512 and Sonar Pro Search are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Devstral 2 2512, from Mistral AI, has a 262,144-token context window and is priced at $0.40/M tokens input, $2/M tokens output on OpenRouter.

Sonar Pro Search, from Perplexity, has a 200,000-token context window and is priced at $3/M tokens input, $15/M tokens output on OpenRouter.

Context window
  • Devstral 2 2512: 262,144 tokens
  • Sonar Pro Search: 200,000 tokens
Price
  • Devstral 2 2512: $0.40/M tokens input, $2/M tokens output
  • Sonar Pro Search: $3/M tokens input, $15/M tokens output
Provided by
  • Devstral 2 2512: Mistral AI
  • Sonar Pro Search: Perplexity
  • Devstral 2 2512 model details, providers and pricing
  • Sonar Pro Search model details, providers and pricing

Devstral 2 2512 vs Sonar Pro Search at a glance

Devstral 2 2512 vs Sonar Pro Search comparison
AttributeDevstral 2 2512Sonar Pro Search
Input price$0.40/M tokens$3/M tokens
Output price$2/M tokens$15/M tokens
Context window262,144 tokens200,000 tokens
Intelligence Index8.6Not available
Coding Index31.3Not available
Agentic Index2.3Not available
Latency (p50)0.63 s13.18 s
Throughput (p50)80.0 tok/s45.0 tok/s

Benchmark data updated Oct 13, 2026

Frequently asked questions

Is Devstral 2 2512 cheaper than Sonar Pro Search?

Devstral 2 2512 is cheaper than Sonar Pro Search on OpenRouter: Devstral 2 2512 costs $0.40/M tokens input and $2/M tokens output, while Sonar Pro Search costs $3/M tokens input and $15/M tokens output.

Which has the longer context window, Devstral 2 2512 or Sonar Pro Search?

Devstral 2 2512 has the longer context window at 262,144 tokens, compared with 200,000 tokens for Sonar Pro Search.

Which is faster, Devstral 2 2512 or Sonar Pro Search?

Devstral 2 2512 is faster on OpenRouter, generating a median 80.0 tokens per second compared with 45.0 tokens per second for Sonar Pro Search.