GPT-5 Nano

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

$0.14Blended $/1M (3:1)

$0.05Input $/1M

$0.4Output $/1M

$0.451M in + 1M out

$0.005 −90%Cache read $/1M

#925 of 5,000Cheapest rank

Provider: Impossibl (impossibl)
Context: 400,000 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“GPT-5 Nano” is offered by 9 providers — cheapest-effective first. This one (Impossibl) is the cheapest.

Provider	Input	Output	Blended	Context
Impossibl (this)	$0.05	$0.4	$0.14	400k
FastRouter	$0.05	$0.4	$0.14	400k
NEAR AI Cloud	$0.05	$0.4	$0.14	400k
LLM Gateway	$0.05	$0.4	$0.14	400k
OpenCode Zen	$0.05	$0.4	$0.14	400k
Neon	$0.05	$0.4	$0.14	400k
Pioneer	$0.05	$0.4	$0.14	400k
Abacus	$0.05	$0.4	$0.14	400k
Azure Cognitive Services	$0.05	$0.4	$0.14	400k

Call it

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

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