Model
gpt-5.6-luna
gpt-5.6-luna from OpenAI, Fast class. List prices per million tokens, and what the public benchmarks say about it.
- Class
- Fast
- Input, per million
- $0.20
- Output, per million
- $1.20
- Cached input
- $0.02
- Context window
- 400,000
- Longest answer
- 128,000
- Processed in
- global
- Prices from
- 5 October 2026
Calling it
Name it in the model field, or let auto choose it for you.
"model": "gpt-5.6-luna"Supports: images, tools, JSON schema
auto can pick this model when it suits the job and the line you chose.
What it costs
- Input $0.20 and output $1.20 per million tokens, at the provider list price.
- Input read from cache: $0.02 per million tokens.
- gpt-5.6-luna: prompts over 272,001 tokens cost $0.40 in and $1.80 out per 1M tokens.
Public results for this model
No public benchmark results for this model yet, and Zabio has not tested it either.
How routing picks between these models
Model and company names are trademarks of their owners. Zabio uses these models through their vendors' APIs and is not affiliated with the vendors.