jishie

GPT-5.4 mini

kenari/gpt-5-4-mini · family gpt-mini · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

freeBlended $/1M (3:1)
freeInput $/1M
freeOutput $/1M
free1M in + 1M out
Cache read $/1M
#156 of 5,000Cheapest rank
Provider
Kenari (kenari)
Context
400,000 tokens
Max output
128,000 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

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

ProviderInputOutputBlendedContext
Kenari (this)freefree$0.00400k
Xpersona$0.375$4$1.28272k
Impossibl$0.75$4.5$1.69400k
CrossModel$0.75$4.5$1.69400k
Vivgrid$0.75$4.5$1.69400k
FastRouter$0.75$4.5$1.69400k
NEAR AI Cloud$0.75$4.5$1.69400k
LLM Gateway$0.75$4.5$1.69400k
OpenCode Zen$0.75$4.5$1.69400k

Call it

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

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