Sonar Pro
perplexity/sonar-pro · family sonar-pro · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.
$6.00
Blended $/1M (3:1)
$3
Input $/1M
$15
Output $/1M
$18.00
1M in + 1M out
—
Cache read $/1M
#6878 of 7,708
Cheapest rank
- Provider
- Perplexity (
perplexity) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- text image
Same model, other providers
“Sonar Pro” is offered by 5 providers — cheapest-effective first. This one (Perplexity) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Perplexity (this) | $3 | $15 | $6.00 | 200k |
| OpenRouter | $3 | $15 | $6.00 | 200k |
| Opper | $3 | $15 | $6.00 | 200k |
| Eden AI | $3 | $15 | $6.00 | 200k |
| DevPass (LLM Gateway) | $3 | $15 | $6.00 | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Perplexity and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"sonar-pro","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):