GPT 5.6 Luna pricing for categorization

Quick start

Call GPT 5.6 Luna with the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-5.6-luna",
    max_tokens=150,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.000340 per call at standard rates
# Input:  $0.20/MTok
# Output: $1.20/MTok

How GPT 5.6 Luna compares on cost

Per-call cost for all models scoring 50+ on categorization benchmarks. Hover for details.

Highest-quality affordable option: Gemini 3.5 Flash-Lite at $0.000615/call (1.8x the cost, 85/100 quality). GPT 5.6 Luna is already the cheapest choice for categorization.

What drives categorization cost

Classification into a fixed taxonomy is token-efficient by construction: the taxonomy is the same on every call and the output is one label. Put the taxonomy in the cached prefix and the marginal cost per item approaches the cost of the item text alone. Model tier matters less here than in any other use case tracked.

For GPT 5.6 Luna specifically, that means output tokens cost 6.0x more than input, at $1.20 vs $0.20 per MTok. At this use case’s 800/150 token split, output accounts for 53% of the $0.000340 per-call cost.

GPT 5.6 Luna quality benchmarks for categorization

Performance across all task types

GPT 5.6 Luna scores by task type. Categorization highlighted.

Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.

About GPT 5.6 Luna

Other models from GPT

You can compare GPT 5.6 Luna head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions