GPT-5.4 nano

model-oracle-ai/gpt-5.4-nano · family gpt-nano · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

—Blended $/1M (3:1)

—Input $/1M

—Output $/1M

—1M in + 1M out

—Cache read $/1M

—Cheapest rank

Provider: Model Oracle AI (model-oracle-ai)
Context: 400,000 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“GPT-5.4 nano” is offered by 9 providers — cheapest-effective first. Impossibl is the cheapest at $0.46 blended.

Provider	Input	Output	Blended	Context
Impossibl	$0.2	$1.25	$0.46	400k
CrossModel	$0.2	$1.25	$0.46	400k
Vivgrid	$0.2	$1.25	$0.46	400k
FastRouter	$0.2	$1.25	$0.46	400k
NEAR AI Cloud	$0.2	$1.25	$0.46	400k
LLM Gateway	$0.2	$1.25	$0.46	400k
OpenCode Zen	$0.2	$1.25	$0.46	400k
GitHub Copilot	$0.2	$1.25	$0.46	400k
Model Oracle AI (this)	—	—	—	400k

Call it

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

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