GPT 5.6 Luna

vercel/openai/gpt-5.6-luna · family gpt-luna · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagepdf.

$0.45Blended $/1M (3:1)

$0.2Input $/1M

$1.2Output $/1M

$1.401M in + 1M out

$0.02 −90%Cache read $/1M

#2090 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 1,050,000 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtextimagepdf

Same model, other providers

“GPT 5.6 Luna” is offered by 3 providers — cheapest-effective first. NanoGPT is the cheapest at $0.23 blended.

Provider	Input	Output	Blended	Context
NanoGPT	$0.1	$0.6	$0.23	1050k
Vercel AI Gateway (this)	$0.2	$1.2	$0.45	1050k
Vivgrid	$1	$6	$2.25	1050k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway 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-5.6-luna","messages":[{"role":"user","content":"hello"}]}'

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