PublicEndpoint Type | OpenRouter TypeScript SDK | OpenRouter

The TypeScript SDK and docs are currently in beta. Report issues on GitHub.

Information about a specific model endpoint

Example Usage

1 import { PublicEndpoint } from "@openrouter/sdk/models";
2 
3 let value: PublicEndpoint = {
4   contextLength: 8192,
5   latencyLast30m: {
6     p50: 0.25,
7     p75: 0.35,
8     p90: 0.48,
9     p99: 0.85,
10   },
11   maxCompletionTokens: 4096,
12   maxPromptTokens: 8192,
13   modelId: "openai/gpt-4",
14   modelName: "GPT-4",
15   name: "OpenAI: GPT-4",
16   pricing: {
17     completion: "0.00006",
18     prompt: "0.00003",
19   },
20   providerName: "OpenAI",
21   quantization: "fp16",
22   supportedParameters: [
23     "temperature",
24     "top_p",
25     "max_tokens",
26   ],
27   supportsImplicitCaching: true,
28   tag: "openai",
29   throughputLast30m: {
30     p50: 45.2,
31     p75: 38.5,
32     p90: 28.3,
33     p99: 15.1,
34   },
35   uptimeLast1d: 99.8,
36   uptimeLast30m: 99.5,
37   uptimeLast5m: 100,
38 };

Fields

Field	Type	Required	Description	Example
`contextLength`	number	✔️	N/A
`latencyLast30m`	models.PercentileStats	✔️	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`	number	✔️	N/A
`maxPromptTokens`	number	✔️	N/A
`modelId`	string	✔️	The unique identifier for the model (permaslug)	openai/gpt-4
`modelName`	string	✔️	N/A
`name`	string	✔️	N/A
`pricing`	models.Pricing	✔️	N/A
`providerName`	models.ProviderName	✔️	N/A	OpenAI
`quantization`	models.PublicEndpointQuantization	✔️	N/A	fp16
`status`	models.EndpointStatus	➖	N/A	0
`supportedParameters`	models.Parameter[]	✔️	N/A
`supportsImplicitCaching`	boolean	✔️	N/A
`tag`	string	✔️	N/A
`throughputLast30m`	models.PercentileStats	✔️	N/A	`{"p50": 25.5,"p75": 35.2,"p90": 48.7,"p99": 85.3}`
`uptimeLast1d`	number	✔️	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`	number	✔️	N/A
`uptimeLast5m`	number	✔️	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.