jishie

Sonar Reasoning Pro

openrouter/perplexity/sonar-reasoning-pro · family sonar-reasoning · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: reasoningtextimage.

$3.50Blended $/1M (3:1)
$2Input $/1M
$8Output $/1M
$10.001M in + 1M out
Cache read $/1M
#4601 of 5,000Cheapest rank
Provider
OpenRouter (openrouter)
Context
128,000 tokens
Max output
128,000 tokens
Capabilities
reasoningtextimage

Same model, other providers

“Sonar Reasoning Pro” is offered by 3 providers — cheapest-effective first. This one (OpenRouter) is the cheapest.

ProviderInputOutputBlendedContext
OpenRouter (this)$2$8$3.50128k
LLM Gateway$2$8$3.50128k
Perplexity$2$8$3.50128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at OpenRouter 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-reasoning-pro","messages":[{"role":"user","content":"hello"}]}'

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