jishie

Sonar Reasoning Pro

vercel/perplexity/sonar-reasoning-pro · family sonar-reasoning · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: reasoning text image.

This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See Vercel AI Gateway’s docs for per-unit rates.

Provider
Vercel AI Gateway (vercel)
Kind
text (outputs text)
Context
127,000 tokens
Max output
8,000 tokens
Capabilities
reasoning text image

Same model, other providers

“Sonar Reasoning Pro” is offered by 6 providers — cheapest-effective first. OpenRouter is the cheapest at $3.50 blended.

ProviderInputOutputBlendedContext
OpenRouter$2$8$3.50128k
Perplexity$2$8$3.50128k
Opper$2$8$3.50128k
Eden AI$2$8$3.50128k
DevPass (LLM Gateway)$2$8$3.50128k
Vercel AI Gateway (this)———127k

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-reasoning-pro","messages":[{"role":"user","content":"hello"}]}'

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

← all Vercel AI Gateway models · model index · JSON