GPT-5.6 Luna

Active

gpt-5-6-luna

Low-cost long-context generation for high-volume coding and agent workloads.

Open Console Explore the API

Context window: 1,100,000
Max output: 128,000

Official model price

The published model price used for every request.

Per 1M tokens

Cached input

$0.10

Uncached input

$1.00

Output

$6.00

Use it with your stack

Use this PAI model ID from the client that already fits your stack.

curl https://router.omnitools.ai/v1/responses \
  -H "Authorization: Bearer $PAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": "Explain cache-aware routing in one sentence.",
  "max_output_tokens": 160,
  "model": "gpt-5-6-luna"
}'