Access is restricted to approved organizations; see official eligibility requirements.
Regions
Not collected
INPUT / 1M TOKENS$12.50
OUTPUT / 1M TOKENS$75.00
Standard text-token rates. Other modalities, tool usage and processing modes are billed separately. Long-context pricing applies to the full request; cached-rate treatment is shown only where explicit. Cached input price: $1.25 / 1M tokens (base tier).
Use prompt_cache_options.mode and prompt_cache_breakpoint for explicit control. ttl defaults to 30m. Up to four writes per request; implicit mode consumes one slot.Source for How to enable it (opens in a new tab)
Cache writes use 1.25× the uncached input rate instead of the normal input rate. Reads use the published model-specific cached rate. Output is still billed.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Exact rendered-prefix matching. No sharing across organizations or processing regions. Routing and load can prevent hits. Check account retention policy before selecting persistent caching.Source for Limits & data boundaries (opens in a new tab)
Standard text-token rates. Other modalities, tool usage and processing modes are billed separately. Long-context pricing applies to the full request; cached-rate treatment is shown only where explicit.
Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Caching reviewed 12 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Proprietary OpenAI release in the official hosted-model catalog. Explicit open-weight releases and unresolved routing aliases are excluded.
