Input billingNot collectedPlayground product / research
Output billingNot collectedNo inferred price
Specifications
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Context / input limit
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Maximum input tokens
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Maximum output
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Maximum prompt characters
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Reasoning
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Tool calling
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Structured output
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Streaming
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Batch processing
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Fine-tuning
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Context caching
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Knowledge cutoff
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Release date
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Parameters
Not collected
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Not established for this exact model or operation. Media controls, research training sizes and integration protocols do not establish language-model token or capability limits.
Image-captioning model described on the official v3 page. No independent public API selector or tariff established.
Regions
Deployment regions not established
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Playground product / research
Not verified
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
How it works
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
Minimum reusable input
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
Lifetime & refresh
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
How to enable it
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
Usage fields
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
Billing rules
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
Limits & data boundaries
Not collected
No reviewed prompt-cache support contract or tariff. Fixed generation, image history and asynchronous task polling are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 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
Private hosted/research classification is inferred from the provider describing its own model and no matching weights in its reviewed official public repository inventory. Public Playground v1/v2/v2.5 weights and the frozen upstream Llama encoder are excluded from this claim. Exact weight-license terms remain unverified.
