GPT-5.6 Luna pricing, context window, and cost calculator
An OpenAI model with tracked short-context, long-context, and cached-input pricing.
Verified fields
Quick facts
gpt-5.6-lunaSupported capabilities
- Streaming
- Function calling
- Structured outputs
- Prompt caching
- Batch API
- Reasoning
Only capabilities explicitly tracked from provider documentation are shown.
Source-tracked rates
Verified pricing profiles
Amounts are USD per 1M tokens unless the column states an hourly storage unit.
| Profile | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M | Notes |
|---|---|---|---|---|---|
| standard / short contextDefault | $0.20 USD | $0.02 USD | $0.25 USD | $1.20 USD | Used for default estimates. |
| standard / long context | $0.40 USD | $0.04 USD | $0.50 USD | $1.80 USD | Tracked separately; select explicitly when modeling this profile. |
Official price history
GPT-5.6 Luna price changes
Verified changes for the same model and pricing profile. Cross-model generational price differences are not treated as history.
OpenAI · Standard · Short Context
GPT-5.6 Luna
| Rate | Earlier price | Later recorded price | Change | Percentage |
|---|---|---|---|---|
| Input / 1M | $1.00 | $0.20 | -$0.80 | -80.0% |
| Cached input / 1M | $0.10 | $0.02 | -$0.08 | -80.0% |
| Output / 1M | $6.00 | $1.20 | -$4.80 | -80.0% |
| Cache write / 1M | $1.25 | $0.25 | -$1.00 | -80.0% |
StackLens first observed the lower price on the current official OpenAI pricing source; the provider's original effective date was not independently established.
OpenAI · Standard · Long Context
GPT-5.6 Luna
| Rate | Earlier price | Later recorded price | Change | Percentage |
|---|---|---|---|---|
| Input / 1M | $2.00 | $0.40 | -$1.60 | -80.0% |
| Cached input / 1M | $0.20 | $0.04 | -$0.16 | -80.0% |
| Output / 1M | $9.00 | $1.80 | -$7.20 | -80.0% |
| Cache write / 1M | $2.50 | $0.50 | -$2.00 | -80.0% |
Long-context rates are derived from OpenAI's documented 2x input and 1.5x output multipliers applied to the current base rates.
Workload estimate
GPT-5.6 Luna cost calculator
Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.
Estimated monthly total$8.00
- Monthly input cost
- $2.00
- Monthly output cost
- $6.00
- Per 1,000 requests
- $0.80
- Active profile
- standard / short context
Estimate excludes untracked provider-specific charges.
Explicit assumptions
Common workload examples
1M input tokens
$0.20 under the standard.short_context profile, excluding output and other charges.
1M output tokens
$1.20 under the standard.short_context profile, excluding input and other charges.
10,000 monthly requests
At 1,000 input and 500 output tokens per request: $8.00 under standard / short context.
50% cached input
The same default workload with 50% cached input is estimated at $7.10. Cache savings apply only to the tracked cached-input rate.
Research layer
Experience and rollout notes
Official facts are separated from user reports. Community reports are useful signals, not controlled benchmarks.
Official model specification
OpenAI publishes Luna as a distinct GPT-5.6 API model with its own pricing and specification record. StackLens keeps its rates separate from Sol and Terra.
What this does not prove: The model page documents official fields; it does not prove suitability for a specific agent setup.
Implementation work and usage value
Several early users describe Luna as useful for implementation work and subagents at an attractive usage level. Reports are less consistent on complex, multi-step workflows.
What this does not prove: These are early product experiences, not a controlled cost-quality comparison. Test escalation rules for difficult tasks.
No controlled StackLens benchmark yet
StackLens has not run a controlled GPT-5.6 Luna benchmark. The notes above separate official documentation from independent user reports.
Research reviewed 2026-07-13. Reports may change as GPT-5.6 Luna reaches more workflows.
Tracked relationships
Related models
StackLens relationship map based on model families and published decision comparisons. Find a workload match → Open relationship map → Open price map →
Featured comparisons
- GPT-5.6 Luna vs GPT-5.6 Terra cost
- GPT-5.6 Luna vs GPT-5.6 Sol cost
- GPT-5.6 Luna vs Gemini 2.5 Flash cost
- GPT-5.6 Luna vs DeepSeek V4 Pro cost
- GPT-5.6 Luna vs Claude Haiku 4.5 cost
- GPT-5.6 Luna vs gpt-5.4-nano cost
Continue your research
Verification
Sources and methodology
Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.
Calculator profile rule: standard.short_context is the verified default. Requests with more than 272,000 input tokens use the higher long-context rate for the full request.