jishie

GPT-5.4

unorouter/gpt-5.4:free · family gpt · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagepdf.

freeBlended $/1M (3:1)
freeInput $/1M
freeOutput $/1M
free1M in + 1M out
Cache read $/1M
#237 of 5,000Cheapest rank
Provider
UnoRouter (unorouter)
Context
1,050,000 tokens
Max output
128,000 tokens
Capabilities
toolsreasoningtextimagepdf

Same model, other providers

“GPT-5.4” is offered by 9 providers — cheapest-effective first. This one (UnoRouter) is the cheapest.

ProviderInputOutputBlendedContext
UnoRouter (this)freefree$0.001050k
Xpersona$0.75$6$2.061050k
UnoRouter$1.8$10.8$4.051050k
Poe$2.2$14$5.151050k
Impossibl$2.5$15$5.631050k
CrossModel$2.5$15$5.631050k
Vivgrid$2.5$15$5.63400k
NEAR AI Cloud$2.5$15$5.631050k
DaoXE$2.5$15$5.631050k

Call it

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

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