jishie

Perplexity Sonar Deep Research

perplexity/sonar-deep-research · in: text → out: text · price provider-declared (via models.dev). Capabilities: reasoning text.

$3.50
Blended $/1M (3:1)
$2
Input $/1M
$8
Output $/1M
$10.00
1M in + 1M out
—
Cache read $/1M
#6113 of 7,708
Cheapest rank
Provider
Perplexity (perplexity)
Kind
text (outputs text)
Context
128,000 tokens
Max output
32,768 tokens
Capabilities
reasoning text

Same model, other providers

“Perplexity Sonar Deep Research” is offered by 2 providers — cheapest-effective first. This one (Perplexity) is the cheapest.

ProviderInputOutputBlendedContext
Perplexity (this)$2$8$3.50128k
Helicone$2$8$3.50127k

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-deep-research","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Perplexity models · model index · JSON