For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://modelgates.ai/docs/_mcp/server.
Generations - TypeScript SDK
The TypeScript SDK and docs are currently in beta. Report issues on GitHub.
Overview
Generation history endpoints
Available Operations
- getGeneration - Get request & usage metadata for a generation
- listGenerationContent - Get stored prompt and completion content for a generation
getGeneration
Get request & usage metadata for a generation
Example Usage
typescript
import { ModelGates } from "@modelgates/sdk"; const modelgates = new ModelGates({ httpReferer: "<value>", appTitle: "<value>", appCategories: "<value>", apiKey: process.env["MODELGATES_API_KEY"] ?? "",}); async function run() { const result = await modelgates.generations.getGeneration({ id: "<id>", }); console.log(result);} run();Standalone function
The standalone function version of this method:
typescript
import { ModelGatesCore } from "@modelgates/sdk/core.js";import { generationsGetGeneration } from "@modelgates/sdk/funcs/generationsGetGeneration.js"; // Use `ModelGatesCore` for best tree-shaking performance.// You can create one instance of it to use across an application.const modelgates = new ModelGatesCore({ httpReferer: "<value>", appTitle: "<value>", appCategories: "<value>", apiKey: process.env["MODELGATES_API_KEY"] ?? "",}); async function run() { const res = await generationsGetGeneration(modelgates, { id: "<id>", }); if (res.ok) { const { value: result } = res; console.log(result); } else { console.log("generationsGetGeneration failed:", res.error); }} run();Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
request | operations.GetGenerationRequest | :heavy_check_mark: | The request object to use for the request. |
options | RequestOptions | :heavy_minus_sign: | Used to set various options for making HTTP requests. |
options.fetchOptions | RequestInit | :heavy_minus_sign: | Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed. |
options.retries | RetryConfig | :heavy_minus_sign: | Enables retrying HTTP requests under certain failure conditions. |
Response
Promise<models.GenerationResponse>
Errors
| Error Type | Status Code | Content Type |
|---|---|---|
| errors.UnauthorizedResponseError | 401 | application/json |
| errors.PaymentRequiredResponseError | 402 | application/json |
| errors.NotFoundResponseError | 404 | application/json |
| errors.TooManyRequestsResponseError | 429 | application/json |
| errors.InternalServerResponseError | 500 | application/json |
| errors.BadGatewayResponseError | 502 | application/json |
| errors.EdgeNetworkTimeoutResponseError | 524 | application/json |
| errors.ProviderOverloadedResponseError | 529 | application/json |
| errors.ModelGatesDefaultError | 4XX, 5XX | */* |
listGenerationContent
Get stored prompt and completion content for a generation
Example Usage
typescript
import { ModelGates } from "@modelgates/sdk"; const modelgates = new ModelGates({ httpReferer: "<value>", appTitle: "<value>", appCategories: "<value>", apiKey: process.env["MODELGATES_API_KEY"] ?? "",}); async function run() { const result = await modelgates.generations.listGenerationContent({ id: "gen-1234567890", }); console.log(result);} run();Standalone function
The standalone function version of this method:
typescript
import { ModelGatesCore } from "@modelgates/sdk/core.js";import { generationsListGenerationContent } from "@modelgates/sdk/funcs/generationsListGenerationContent.js"; // Use `ModelGatesCore` for best tree-shaking performance.// You can create one instance of it to use across an application.const modelgates = new ModelGatesCore({ httpReferer: "<value>", appTitle: "<value>", appCategories: "<value>", apiKey: process.env["MODELGATES_API_KEY"] ?? "",}); async function run() { const res = await generationsListGenerationContent(modelgates, { id: "gen-1234567890", }); if (res.ok) { const { value: result } = res; console.log(result); } else { console.log("generationsListGenerationContent failed:", res.error); }} run();Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
request | operations.ListGenerationContentRequest | :heavy_check_mark: | The request object to use for the request. |
options | RequestOptions | :heavy_minus_sign: | Used to set various options for making HTTP requests. |
options.fetchOptions | RequestInit | :heavy_minus_sign: | Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed. |
options.retries | RetryConfig | :heavy_minus_sign: | Enables retrying HTTP requests under certain failure conditions. |
Response
Promise<models.GenerationContentResponse>
Errors
| Error Type | Status Code | Content Type |
|---|---|---|
| errors.UnauthorizedResponseError | 401 | application/json |
| errors.ForbiddenResponseError | 403 | application/json |
| errors.NotFoundResponseError | 404 | application/json |
| errors.TooManyRequestsResponseError | 429 | application/json |
| errors.InternalServerResponseError | 500 | application/json |
| errors.BadGatewayResponseError | 502 | application/json |
| errors.EdgeNetworkTimeoutResponseError | 524 | application/json |
| errors.ProviderOverloadedResponseError | 529 | application/json |
| errors.ModelGatesDefaultError | 4XX, 5XX | */* |