jishie

GPT-5.4

requesty/gpt-5.4 · family gpt · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.

$5.57
Blended $/1M (3:1)
$2.48
Input $/1M
$14.85
Output $/1M
$17.32
1M in + 1M out
$0.2475 −90%
Cache read $/1M
#5847 of 6,829
Cheapest rank
Provider
Requesty (requesty)
Kind
text (outputs text)
Context
1,050,000 tokens
Max output
128,000 tokens
Capabilities
tools reasoning text image pdf

Same model, other providers

“GPT-5.4” is offered by 40 providers — cheapest-effective first. UnoRouter is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
UnoRouterfreefree$0.001.1M
Xpersona$0.75$6$2.061.1M
Poe$2.2$14$5.151.1M
Requesty (this)$2.48$14.85$5.571.1M
SAP AI Core$2.5$15$5.631.1M
302.AI$2.5$15$5.631.1M
AI-ROUTER$2.5$15$5.631.1M
Impossibl$2.5$15$5.631.1M
OpenRouter$2.5$15$5.631.1M
DaoXE$2.5$15$5.631.1M
CrossModel$2.5$15$5.631.1M
Databricks$2.5$15$5.631.1M
OpenAI$2.5$15$5.631.1M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Requesty and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.4","messages":[{"role":"user","content":"hello"}]}'

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

← all Requesty models · model index · JSON