> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# PublicEndpoint
Information about a specific model endpoint
## Fields
| Field | Type | Required | Description | Example |
| ------------------------- | --------------------------------------------------------------------------------------- | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- |
| `ContextLength` | `int64` | :heavy\_check\_mark: | N/A | |
| `LatencyLast30m` | [\*components.PercentileStats](../../models/components/percentilestats.mdx) | :heavy\_check\_mark: | Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests. | \{
"p50": 25.5,
"p75": 35.2,
"p90": 48.7,
"p99": 85.3
} |
| `MaxCompletionTokens` | `*int64` | :heavy\_check\_mark: | Maximum completion tokens for this endpoint. Input and output tokens share the context window, so the effective maximum output for a request is further limited by the context remaining after input tokens. | |
| `MaxPromptTokens` | `*int64` | :heavy\_check\_mark: | N/A | |
| `ModelID` | `string` | :heavy\_check\_mark: | The unique identifier for the model (permaslug) | openai/gpt-4 |
| `ModelName` | `string` | :heavy\_check\_mark: | N/A | |
| `Name` | `string` | :heavy\_check\_mark: | N/A | |
| `PerfLast30mByWorkload` | [\*components.PerfLast30mByWorkload](../../models/components/perflast30mbyworkload.mdx) | :heavy\_minus\_sign: | Endpoint performance over the last 30 minutes, keyed by the kind of request served (e.g. `text_generation`, `image_generation`). Additive to the legacy singular latency and throughput fields; image and video generation report end-to-end latency. Only visible when authenticated with an API key or cookie. | |
| `Pricing` | [components.Pricing](../../models/components/pricing.mdx) | :heavy\_check\_mark: | N/A | |
| `ProviderName` | [components.ProviderName](../../models/components/providername.mdx) | :heavy\_check\_mark: | N/A | OpenAI |
| `Quantization` | [\*components.Quantization](../../models/components/quantization.mdx) | :heavy\_check\_mark: | N/A | fp16 |
| `Status` | [\*components.EndpointStatus](../../models/components/endpointstatus.mdx) | :heavy\_minus\_sign: | N/A | 0 |
| `SupportedParameters` | \[][components.Parameter](../../models/components/parameter.mdx) | :heavy\_check\_mark: | N/A | |
| `SupportsImplicitCaching` | `bool` | :heavy\_check\_mark: | N/A | |
| `SupportsToolChoice` | [components.ToolChoiceSupport](../../models/components/toolchoicesupport.mdx) | :heavy\_check\_mark: | Per-variant `tool_choice` support. `tool_choice` in `supported_parameters` only says the parameter is accepted; these flags say which of its values passed testing. | \{
"auto": true,
"function": true,
"none": true,
"required": true
} |
| `SupportsVoiceCloning` | `*bool` | :heavy\_minus\_sign: | Whether this TTS endpoint accepts inline reference audio (`input_references`) for stateless voice cloning. Requests carrying reference audio are only routed to endpoints where this is true. | |
| `Tag` | `string` | :heavy\_check\_mark: | N/A | |
| `ThroughputLast30m` | [\*components.PercentileStats](../../models/components/percentilestats.mdx) | :heavy\_check\_mark: | N/A | \{
"p50": 25.5,
"p75": 35.2,
"p90": 48.7,
"p99": 85.3
} |
| `UptimeLast1d` | `*float64` | :heavy\_check\_mark: | Uptime percentage over the last 1 day, calculated as successful requests / (successful + error requests) \* 100. Rate-limited requests are excluded. Returns null if insufficient data. | |
| `UptimeLast30m` | `*float64` | :heavy\_check\_mark: | N/A | |
| `UptimeLast5m` | `*float64` | :heavy\_check\_mark: | Uptime percentage over the last 5 minutes, calculated as successful requests / (successful + error requests) \* 100. Rate-limited requests are excluded. Returns null if insufficient data. | |