Auto-generated comparison

Mistral: Mistral Medium 3.5 vs Perplexity: Sonar Pro

Mistral: Mistral Medium 3.5 wins on 5 of 6 axes — pricing and capability skew in its favour for most workloads.

Side-by-side comparison

CapabilityMistral: Mistral Medium 3.5Perplexity: Sonar ProWinner
Context window
Maximum number of input tokens the model can attend to in a single request.
262K200K🏆 Mistral: Mistral Medium 3.5
Input price (per 1M)
Cost per million input tokens billed by the provider.
$1.50$3.00🏆 Mistral: Mistral Medium 3.5
Output price (per 1M)
Cost per million output tokens billed by the provider.
$7.50$15.00🏆 Mistral: Mistral Medium 3.5
Tool / function calling
First-class support for emitting structured tool calls.
Yes🏆 Mistral: Mistral Medium 3.5
Vision input
Accepts image inputs alongside text.
YesYesTie
Reasoning mode
Internal chain-of-thought / extended-thinking support.
Yes🏆 Mistral: Mistral Medium 3.5

Frequently asked questions

Is Mistral: Mistral Medium 3.5 better than Perplexity: Sonar Pro?

Mistral: Mistral Medium 3.5 wins on 5 of 6 axes — pricing and capability skew in its favour for most workloads.

What's the price difference between Mistral: Mistral Medium 3.5 and Perplexity: Sonar Pro?

Input: $1.50 vs $3.00 per 1M tokens. Output: $7.50 vs $15.00 per 1M tokens.

What context windows do Mistral: Mistral Medium 3.5 and Perplexity: Sonar Pro support?

Mistral: Mistral Medium 3.5 supports up to 262K tokens. Perplexity: Sonar Pro supports up to 200K tokens.

Do both Mistral: Mistral Medium 3.5 and Perplexity: Sonar Pro support tool calling?

Mistral: Mistral Medium 3.5: yes. Perplexity: Sonar Pro: not advertised.

Compare Mistral: Mistral Medium 3.5 with other models

Compare Perplexity: Sonar Pro with other models