Fields
| Field | Type | Required | Description | Example |
|---|---|---|---|---|
name | str | :heavy_check_mark: | N/A | |
model_name | str | :heavy_check_mark: | N/A | |
context_length | float | :heavy_check_mark: | N/A | |
pricing | components.Pricing | :heavy_check_mark: | N/A | |
provider_name | components.ProviderName | :heavy_check_mark: | N/A | OpenAI |
tag | str | :heavy_check_mark: | N/A | |
quantization | Nullable[components.PublicEndpointQuantization] | :heavy_check_mark: | N/A | fp16 |
max_completion_tokens | Nullable[float] | :heavy_check_mark: | N/A | |
max_prompt_tokens | Nullable[float] | :heavy_check_mark: | N/A | |
supported_parameters | List[components.Parameter] | :heavy_check_mark: | N/A | |
status | Optional[components.EndpointStatus] | :heavy_minus_sign: | N/A | 0 |
uptime_last_30m | Nullable[float] | :heavy_check_mark: | N/A | |
supports_implicit_caching | bool | :heavy_check_mark: | N/A | |
latency_last_30m | Nullable[components.PercentileStats] | :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. | |
throughput_last_30m | Nullable[components.PercentileStats] | :heavy_check_mark: | N/A |