Magistral Medium vs Sonar Deep Research
Side-by-side API pricing comparison · Mistral vs Perplexity
🏆
Magistral Medium is 42.9% cheaper on blended cost ($3.50 vs $5.00/Mtok)
Magistral Medium
by Mistral
Current reasoningInput
$2.00/Mtok
Output
$5.00/Mtok
✓ Cheaper
| Blended avg | $3.50/Mtok |
|---|---|
| Context | 128K tokens |
| Modality | text |
| Parameters | Proprietary |
| Released | Jun 1, 2025 |
Sonar Deep Research
by Perplexity
Current reasoningInput
$2.00/Mtok
Output
$8.00/Mtok
| Blended avg | $5.00/Mtok |
|---|---|
| Context | 200K tokens |
| Modality | text |
| Parameters | Proprietary |
| Released | Apr 1, 2025 |
Cost at scale — 1M tokens (50/50 input/output)
| Volume | Magistral Medium | Sonar Deep Research | Savings |
|---|---|---|---|
| 1M tokens | $3.5 | $5 | $1.5 (30%) |
| 10M tokens | $35 | $50 | $15 (30%) |
| 100M tokens | $350 | $500 | $150 (30%) |
| 1000M tokens | $3500 | $5000 | $1500 (30%) |
Summary
Magistral Medium by Mistral costs $2.00/Mtok input and $5.00/Mtok output, with a 128K-token context window. It supports text input.
Sonar Deep Research by Perplexity costs $2.00/Mtok input and $8.00/Mtok output, with a 200K-token context window. It supports text input.
On a blended cost basis, Magistral Medium is 42.9% cheaper than Sonar Deep Research.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.