OpenAI · Simple tasks at low cost
GPT-6 Luna
A cost-effective option for clearly defined, repetitive tasks.
- Costs
- $0.10 input / $0.50 output per million tokens. Above 272 thousand input tokens: 2× input and 1.5× output.
- Speed
- We have not independently measured speed on a comparable basis.
- Availability
- OpenAI API
- Input length
- 1,050,000 tokens in total; output capped at 128 thousand tokens.
- Inputs
- Text and images → text
Data checked . Published September 22, 2026. Specifications and prices are provided by the vendor; usage recommendations come from the editorial team. We do not yet have our own comparative test of this version.
Ideal use
When to choose it
- Text classification and brief summaries
- Processing a large number of simple requests
Usage boundaries
When to choose another model
- For complex tasks, check whether the low price leads to more corrections.
Traceable supporting sources
Data and measurement sources
Distinguish between the manufacturer's documentation and the results of a specific test. Measurements also depend on the settings and the task set used.
Vendor documentation
Specifications, availability, and termsManufacturer data verified as of the review date. Recommended use is an editorial interpretation.
Open original source ↗Efficiency in practice
With what GPT-6 Luna combine
Many tasks without unnecessary costs
A low-cost model handles routine work, and the more expensive one gets only the truly difficult cases.
Use your own data to verify when a stronger model should take over the work. A model cannot reliably assess its own answer.Trends over time
Related events from AI Radar
OpenAI fixed a bug in image encoding in the GPT-6 Sol and GPT-6 Luna models
Developers who used image inputs with the GPT-6 Sol or GPT-6 Luna models may have encountered worse results due to a bug in image encoding; after the fix, it is advisable to retest your tasks involving visual content.
Companies running pipelines with image inputs via the GPT-6 Sol or GPT-6 Luna models (API, Codex, computer use) may have received worse results on visual tasks due to a bug; it is now advisable to re-verify output quality and, if needed, recompute the affected workflows.
Cloudflare releases Clef and Clef-flash models for AI agent decision-making
A developer can use the Clef and Clef-flash models in a project to obtain predefined decisions with probabilities and connect them to further steps of their agent.
Customer support can use the models to sort requests by urgency and responsible team, including escalation or handoff to a human.
Next step
Compare the model using your actual task.
A benchmark narrows the selection. A short trial on your data determines the choice.