Perplexity
Sonar
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources.
At a glance
- Input / 1M
- $1
- Output / 1M
- $1
- Context
- 127K
- Max output
- 114K
- Intelligence
- 7.7
- Released
- Jan 2025
Pricing
Sonar API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $1 |
|---|---|
| Output tokensPer 1M tokens | $1 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
| Web searchPer request | $0.005 |
Chat message
2K in, 500 out
$2.50
per 1,000 requests
Coding task
30K in, 4K out
$34
per 1,000 requests
Long document summary
150K in, 2K out
$152
per 1,000 requests
Benchmarks
Sonar benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
7.7
Coding index
Not available
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 127K tokens
- Max output
- 114K tokens
- Input types
- Image, Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- January 27, 2025
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Sonar vs other models
See how Sonar stacks up head to head on price, benchmarks, and features.
VS
Sonar vs GPT-4o-mini
Perplexity vs OpenAI
See comparisonVSSonar vs GPT-4.1 Mini
Perplexity vs OpenAI
See comparisonVSSonar vs Llama 3.3 70B Instruct
Perplexity vs Meta
See comparisonVS
Sonar vs DeepSeek V3 0324
Perplexity vs DeepSeek
See comparisonVS
Sonar vs Qwen3 Next 80B A3B Instruct
Perplexity vs Qwen
See comparisonVSSonar vs Qwen3 Coder Next
Perplexity vs Qwen
See comparisonAlternatives
Sonar alternatives
Similar models worth considering, and where each one has the edge.
OpenAI
GPT-4.1 Mini
DeepSeek
DeepSeek V3 0324
Qwen
Qwen3 Next 80B A3B Instruct
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Sonar cost?
Sonar costs $1 per 1M input tokens and $1 per 1M output tokens through the API. A typical chat message costs about $2.50 per 1,000 messages.
What is the context window of Sonar?
Sonar accepts up to 127K tokens of input and can write up to 114K tokens in a single response.
What is the best alternative to Sonar?
GPT-4.1 Mini from OpenAI is a strong alternative. It offers: higher intelligence score, larger 1.05m context, accepts file.
Can I use Sonar alongside other models?
Yes. Shortcut Chat sends one prompt to Sonar and any other models you pick at the same time, so you can compare answers side by side.
Try Sonar next to every other model.
Use Sonar alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.