Sonar Pro
Note: Sonar Pro pricing includes Perplexity search pricing.
sonar-proReleased 7 Mar 2025 (Mar 2025)Pricing
List prices at Perplexity, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $3.00 | $15.00 | |
| Web search $10.00 per 1,000 searches | $10.00 per 1,000 searches |
What it costs a month
At Perplexity list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$2,025
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,980
- Coding agent1,000 requests a day, 40K in / 2K out$4,500
- Overnight batch20,000 requests a day, 4K in / 0.4K out$10,800
Where to run it
3 hosts serve Sonar Pro. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
PerplexityGateway sonar-pro | $3.00 / $15.00 | sonar-pro | |
Vercel AI GatewayGateway sonar-pro | $3.00 / $15.00 | sonar-pro | |
Kyma APICloud sonar-pro | $4.05 / $20.25 +35% vs headline | sonar-pro |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Built-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Perplexity.
Smaller Perplexity models
- 42% less
- 67% less
- 86% less
Other frontier labs
- 20% less
- 33% less
- 33% less
- 50% less
Open-weight picks
- 27% less
- 33% less
- 50% less
- 67% less
Call it
Using Perplexity's API.
from litellm import completion
response = completion(
model="perplexity/sonar-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Sonar Pro cost?
On Perplexity, Sonar Pro costs $3.00 per million input tokens and $15.00 per million output tokens.
Which APIs offer Sonar Pro?
Sonar Pro runs on 3 APIs: Perplexity, Vercel AI Gateway and Kyma API.
What is Sonar Pro's context window?
200K tokens, with up to 8K tokens in one reply.
Is Sonar Pro being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Sonar Pro?
Models that cost less and keep most of what it can do: Sonar Reasoning Pro on Perplexity (42% less), GPT-5.3 Codex on OpenAI (20% less), Gemini 4 Carbon on Google AI Studio (33% less) and Command A Plus on AIHubMix (27% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Sonar Pro released?
Perplexity released it on 7 Mar 2025.
What is Sonar Pro's API model id?
Use sonar-pro with Perplexity.
Sources
Raw catalog entry for sonar-pro on Perplexity
{
"input_cost_per_token": 0.000003,
"litellm_provider": "perplexity",
"max_input_tokens": 200000,
"max_output_tokens": 8000,
"mode": "chat",
"output_cost_per_token": 0.000015,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.006,
"search_context_size_medium": 0.01
},
"supports_web_search": true
}