jishie

GPT-5.4 mini

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

$1.69
Blended $/1M (3:1)
$0.75
Input $/1M
$4.5
Output $/1M
$5.25
1M in + 1M out
$0.075 −90%
Cache read $/1M
#4324 of 6,829
Cheapest rank
Provider
Opper (opper)
Kind
text (outputs text)
Context
400,000 tokens
Max output
128,000 tokens
Capabilities
tools reasoning text image

Same model, other providers

“GPT-5.4 mini” is offered by 32 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.00400k
Xpersona$0.375$4$1.28272k
Requesty$0.675$4.05$1.52400k
Opper (this)$0.75$4.5$1.69400k
OrcaRouter$0.75$4.5$1.69400k
Impossibl$0.75$4.5$1.69400k
OpenRouter$0.75$4.5$1.69400k
CrossModel$0.75$4.5$1.69400k
Databricks$0.75$4.5$1.69400k
OpenAI$0.75$4.5$1.69400k
NEAR AI Cloud$0.75$4.5$1.69400k
Cloudflare AI Gateway$0.75$4.5$1.69400k
FastRouter$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 Opper 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-5.4-mini","messages":[{"role":"user","content":"hello"}]}'

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

← all Opper models · model index · JSON