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

Fields

Field	Type	Required	Description	Example
`name`	string	✔️	N/A
`modelId`	string	✔️	The unique identifier for the model (permaslug)	openai/gpt-4
`modelName`	string	✔️	N/A
`contextLength`	number	✔️	N/A
`pricing`	models.Pricing	✔️	N/A
`providerName`	models.ProviderName	✔️	N/A	OpenAI
`tag`	string	✔️	N/A
`quantization`	models.PublicEndpointQuantization	✔️	N/A	fp16
`maxCompletionTokens`	number	✔️	N/A
`maxPromptTokens`	number	✔️	N/A
`supportedParameters`	models.Parameter[]	✔️	N/A
`status`	models.EndpointStatus	➖	N/A	0
`uptimeLast30m`	number	✔️	N/A
`supportsImplicitCaching`	boolean	✔️	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.
`throughputLast30m`	models.PercentileStats	✔️	N/A