GPT-5.6 Luna
OpenAI's GPT-5.6 Luna is the cost-sensitive GPT-5.6 tier for high-volume workloads that still need current GPT-5.6 behavior, vision input, structured outputs, and tool support.
Provider
OpenAI
Model family
OpenAI GPT
Multimodal LLM
Cost tier
Luna
Status
Current
Why teams choose it
Broad capability envelope
Useful when the same stack must cover chat, multimodal inputs, tooling, or structured-output shapes without juggling many SKUs.
Long-context analysis
Helps teams summarize, compare, and extract insights from long documents without losing important nuance.
Coding and tools
Works well for code assistance, tool calling, and agent workflows where instructions must stay consistent across steps.
Cost-efficient routing
Useful as part of a routing stack where cheap models handle drafts and confirmations and this tier handles genuinely hard passages.
Tradeoffs to know
- Do not use as the default for frontier reasoning without task-level evals.
When not to use this
- Not ideal for simple tasks where cheaper models in the same lineup are good enough.
- Avoid for regulated or high-stakes outputs without evaluations that mimic your tooling, data, and review process.
- Pair catalog notes with comparisons and your own benchmarks before declaring a routing winner.
Technical specs
- Inputs
- text, image
- Outputs
- text
- Capabilities
- reasoning, vision, function calling, structured outputs, low cost
- License
- Proprietary API
- Model string
gpt-5-6-luna
Benchmarks
No benchmark data yet.
OpenAI GPT family lineup
Previous versions
Compare with
Explore next
Models, tools, and comparisons that connect to this reference.