Sonar
vercel/perplexity/sonar · family sonar · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.81
Blended $/1M (3:1)
$0.25
Input $/1M
$2.5
Output $/1M
$2.75
1M in + 1M out
—
Cache read $/1M
#4007 of 8,512
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 127,000 tokens
- Max output
- 8,000 tokens
- Capabilities
- tools text image
Same model, other providers
“Sonar” is offered by 9 providers — cheapest-effective first. This one (Vercel AI Gateway) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Vercel AI Gateway (this) | $0.25 | $2.5 | $0.81 | 127k |
| Perplexity Agent | $0.25 | $2.5 | $0.81 | 128k |
| DevPass (LLM Gateway) | $0.25 | $2.5 | $0.81 | 130k |
| SAP AI Core | $1 | $1 | $1.00 | 128k |
| Perplexity | $1 | $1 | $1.00 | 128k |
| OpenRouter | $1 | $1 | $1.00 | 127k |
| Eden AI | $1 | $1 | $1.00 | 127k |
| Opper | $1 | $1 | $1.00 | 128k |
| AI/ML API | $1 | $1 | $1.00 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway 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):