Sonar
perplexity-agent/perplexity/sonar · family sonar · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.81
Blended $/1M (3:1)
$0.25
Input $/1M
$2.5
Output $/1M
$2.75
1M in + 1M out
$0.0625 −75%
Cache read $/1M
#3712 of 7,708
Cheapest rank
- Provider
- Perplexity Agent (
perplexity-agent) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools text
Same model, other providers
“Sonar” is offered by 7 providers — cheapest-effective first. This one (Perplexity Agent) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Perplexity Agent (this) | $0.25 | $2.5 | $0.81 | 128k |
| SAP AI Core | $1 | $1 | $1.00 | 128k |
| OpenRouter | $1 | $1 | $1.00 | 127k |
| Perplexity | $1 | $1 | $1.00 | 128k |
| Opper | $1 | $1 | $1.00 | 128k |
| Eden AI | $1 | $1 | $1.00 | 127k |
| DevPass (LLM Gateway) | $1 | $1 | $1.00 | 130k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Perplexity Agent and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"perplexity/sonar","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):