GPT-6-Luna
The small, cheap GPT-6 model for latency-sensitive and high-volume workloads. Keeps the generation's instruction following while shedding cost and context for speed.
At a glance
Released
Oct 1, 2026
Provider
OpenAI
Context window
400,000 tokens
Max output
32,000 tokens
Modalities
Text + image → text
Knowledge cutoff
June 2026
API model ID
gpt-6-lunaLicense
Proprietary (API only)
Pricing
Standard
Input$0.10 / 1M
Output$0.50 / 1M
Batch (50% off)
Input$0.05 / 1M
Output$0.25 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.0005 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withGPT-5-Luna (December 2025)
- Higher throughput and lower latency
- Better quality per dollar than the prior small model
- Improved short-context reasoning
- Smaller context and output ceiling
Best use cases
High-volume tasks
Runs classification and routing cheaply at scale.
Quick chat
Powers simple, latency-sensitive assistant flows.
Extraction
Pulls structured data from text at low cost.
Strengths & limitations
Strengths
- Very cheap
- Low latency
- High throughput
- Multimodal input
Limitations
- Limited deep reasoning
- Smaller context
How to test it
- No-code: open chatgpt.com and pick GPT-6-Luna from the model switcher — no API key needed.
- Playground: sign in to the OpenAI Platform and run prompts in the workbench, then copy the generated code.
- API: create a key in the OpenAI Platform and call the API (example below).
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-luna",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'