AI model comparison
Sonar Pro vs Mistral Large
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Perplexity
Sonar Pro
Note: Sonar Pro pricing includes Perplexity search pricing.
- Input / 1M
- $3
- Output / 1M
- $15
- Context
- 200K
Mistral
Mistral Large
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.
- Input / 1M
- $2
- Output / 1M
- $6
- Context
- 128K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mistral Large
1.9x cheaper for a typical chat
Higher intelligence score
Sonar Pro
7.6 vs 5.8 on Artificial Analysis
Larger context window
Sonar Pro
200K vs 128K tokens
Newer release
Sonar Pro
Released March 7, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Sonar Pro7.6Mistral Large5.8Coding index
Sonar ProNot availableMistral LargeNot availableAgentic index
Sonar ProNot availableMistral LargeNot availablePricing
Sonar Pro vs Mistral Large API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Sonar Pro | Mistral Large |
|---|---|---|
| Input tokensPer 1M tokens | $3 | $2 |
| Output tokensPer 1M tokens | $15 | $6 |
| Cached input (read)Per 1M tokens | Not available | $0.20 |
| Cache writePer 1M tokens | Not available | Not available |
| Web searchPer request | $0.005 | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Sonar Pro$13.50Mistral Large$7Coding task
30K in, 4K out
Sonar Pro$150Mistral Large$84$30 cachedLong document summary
150K in, 2K out
Sonar Pro$480Mistral Large$312$42 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Sonar Pro | Mistral Large |
|---|---|---|
| Context window | 200K tokens | 128K tokens |
| Max output | 8K tokens | 102K tokens |
| Input types | Image, Text | File, Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | March 7, 2025 | February 26, 2024 |
Features
Supported features
API features available for each model.
| Metric | Sonar Pro | Mistral Large |
|---|---|---|
| Tool calling | Not supported | Supported |
| Structured outputs | Not supported | Supported |
| JSON mode | Not supported | Supported |
| Reasoning | Not supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Not supported | Supported |
| Deterministic seed | Not supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Mistral LargeView full model details- Mistral Large vs Mistral Medium 3.1
- Mistral Large vs Mistral Medium 3
- Mistral Large vs Devstral 2 2512
- Mistral Large vs GPT-4o (2024-11-20)
- Mistral Large vs GPT-4o (2024-08-06)
- Mistral Large vs Mistral Large 2407
- Mistral Large vs Hermes 4 405B
- Mistral Large vs GPT-4o (2024-05-13)
- Mistral Large vs Nova Pro 1.0
- Mistral Large vs GPT-4 Turbo
- Mistral Large vs GPT-4
- Mistral Large vs Mixtral 8x22B Instruct
Our take
Mistral Large is 1.9x cheaper for a typical chat. Sonar Pro scores higher on the Artificial Analysis Intelligence Index (7.6 vs 5.8). Sonar Pro has the larger context window (200K vs 128K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Sonar Pro or Mistral Large cheaper?
Mistral Large is cheaper for a typical chat (2K input tokens and 500 output tokens). Mistral Large costs $2 per 1M input tokens and $6 per 1M output tokens, while Sonar Pro costs $3 per 1M input tokens and $15 per 1M output tokens.
Which has a bigger context window, Sonar Pro or Mistral Large?
Sonar Pro supports up to 200K tokens of context, compared with 128K for Mistral Large.
Is Sonar Pro smarter than Mistral Large?
On the Artificial Analysis Intelligence Index, Sonar Pro scores 7.6 and Mistral Large scores 5.8, putting Sonar Pro ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Sonar Pro and Mistral Large at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Sonar Pro and Mistral Large answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Sonar Pro and Mistral Large at the same time. Compare the answers side by side and keep the best one.