Mistral Medium 3.5 vs Sonar Reasoning Pro

Compare Mistral Medium 3.5 from Mistral AI and Sonar Reasoning Pro 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.

Mistral Medium 3.5 vs Sonar Reasoning Pro: side-by-side summary

Mistral Medium 3.5 and Sonar Reasoning Pro are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Mistral Medium 3.5, from Mistral AI, has a 262,144-token context window and is priced at $1.50/M tokens input, $7.50/M tokens output on OpenRouter.

Sonar Reasoning Pro, from Perplexity, has a 128,000-token context window and is priced at $2/M tokens input, $8/M tokens output on OpenRouter.

Context window

Mistral Medium 3.5: 262,144 tokens
Sonar Reasoning Pro: 128,000 tokens

Price

Mistral Medium 3.5: $1.50/M tokens input, $7.50/M tokens output
Sonar Reasoning Pro: $2/M tokens input, $8/M tokens output

Provided by

Mistral Medium 3.5: Mistral AI
Sonar Reasoning Pro: Perplexity

Mistral Medium 3.5 vs Sonar Reasoning Pro at a glance

Mistral Medium 3.5 vs Sonar Reasoning Pro comparison
Attribute	Mistral Medium 3.5	Sonar Reasoning Pro
Input price	$1.50/M tokens	$2/M tokens
Output price	$7.50/M tokens	$8/M tokens
Context window	262,144 tokens	128,000 tokens
Intelligence Index	14.2	11.8
Coding Index	46.9	Not available
Agentic Index	7.0	Not available
Latency (p50)	0.54 s	19.54 s
Throughput (p50)	127.0 tok/s	21.0 tok/s

Benchmark data updated Oct 5, 2026

Frequently asked questions

Is Mistral Medium 3.5 cheaper than Sonar Reasoning Pro?

Mistral Medium 3.5 is cheaper than Sonar Reasoning Pro on OpenRouter: Mistral Medium 3.5 costs $1.50/M tokens input and $7.50/M tokens output, while Sonar Reasoning Pro costs $2/M tokens input and $8/M tokens output.

Which has the longer context window, Mistral Medium 3.5 or Sonar Reasoning Pro?

Mistral Medium 3.5 has the longer context window at 262,144 tokens, compared with 128,000 tokens for Sonar Reasoning Pro.

Which is faster, Mistral Medium 3.5 or Sonar Reasoning Pro?

Mistral Medium 3.5 is faster on OpenRouter, generating a median 127.0 tokens per second compared with 21.0 tokens per second for Sonar Reasoning Pro.

Mistral Medium 3.5 vs Sonar Reasoning Pro

Mistral Medium 3.5 vs Sonar Reasoning Pro

Overview