OpenAI
GPT-5.6 Luna
OpenAI's efficient GPT-5.6 reasoning model for cost-sensitive, high-volume workloads, with a 1.05M-token context window and text and image input
Context Length1,050,000 tokens
Max Input922K tokens
Max Output128K tokens
Pricing & Specs
π° Pricing
Input$1 / M tokens
Output$6 / M tokens
Cache Write$1.25 / M tokens
Cache Hit$0.10 / M tokens
βοΈ Specs
Context Length1,050,000 tokens
Max Input922K tokens
Max Output128K tokens
PositioningDesigned for cost-sensitive, high-volume workloads, roughly corresponding to the nano tier in earlier GPT-5 families
API AvailabilitySupports the Responses API, Chat Completions API, and Batch API
MultimodalSupports text and image input, text output
Reasoning EffortSupports none, low, medium (default), high, xhigh, and max
Caching SupportSupports cache reads and writes; cache writes cost 1.25x the uncached input rate
Short-context Pricing (β€272K)Input $1; cached input $0.10; cache write $1.25; output $6 / M tokens
Long-context Pricing (>272K)Input $2; cached input $0.20; cache write $2.50; output $9 / M tokens for the full request
Snapshotgpt-5.6-luna
Knowledge CutoffFebruary 16, 2026
API Examples
Python
from openai import OpenAI
client = OpenAI(
base_url="https://api.zairouter.com/v1",
api_key="your-api-key"
)
response = client.chat.completions.create(
model="gpt-5.6-luna",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://api.zairouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-5.6-luna",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'