GPT-5.2

perplexity-agent/openai/gpt-5.2 · family gpt · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$4.81Blended $/1M (3:1)

$1.75Input $/1M

$14Output $/1M

$15.751M in + 1M out

$0.175 −90%Cache read $/1M

#4927 of 5,000Cheapest rank

Provider: Perplexity Agent (perplexity-agent)
Context: 400,000 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“GPT-5.2” is offered by 9 providers — cheapest-effective first. QiHang is the cheapest at $0.69 blended.

Provider	Input	Output	Blended	Context
QiHang	$0.25	$2	$0.69	400k
UnoRouter	$1.05	$8.4	$2.89	400k
SAP AI Core	$1.25	$9.44	$3.30	400k
Jiekou.AI	$1.575	$12.6	$4.33	400k
Poe	$1.6	$13	$4.45	400k
Perplexity Agent (this)	$1.75	$14	$4.81	400k
Impossibl	$1.75	$14	$4.81	400k
LLM Gateway	$1.75	$14	$4.81	400k
OpenCode Zen	$1.75	$14	$4.81	400k

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":"openai/gpt-5.2","messages":[{"role":"user","content":"hello"}]}'

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