Class: AIGatewayInferenceClient

Defined in: src/ai-gateway/inference-client.ts:130

Prisma gateway runtime inference, independent of management OAuth and SCM plane URLs.

Example

const inference = new AIGatewayInferenceClient(); // PANW_AI_GW_INFERENCE_ENDPOINT / API_KEY
const result = await inference.createChatCompletion({
  model: '@provider/model', messages: [{ role: 'user', content: 'Hello' }],
});
console.log(result.choices[0].message.content);

Extends

AIGatewayRuntimeResourcesClient

Constructors

Constructor

new AIGatewayInferenceClient(options?): AIGatewayInferenceClient;

Defined in: src/ai-gateway/inference-client.ts:140

Parameters

Parameter	Type
`options`	`AIGatewayInferenceClientOptions`

Returns

AIGatewayInferenceClient

Overrides

AIGatewayRuntimeResourcesClient.constructor

Methods

connectRealtime()

connectRealtime(opts, options): Promise<GatewayRealtimeConnection>;

Defined in: src/ai-gateway/inference-client.ts:242

Experimental

Open a bounded realtime WebSocket on the explicitly configured gateway. HTTP 101 proves an upgrade, not provider session readiness. Provider errors remain events. The prescribed-model live probe upgrades, then returns invalid_model.

Parameters

Parameter	Type
`opts`	`objectOutputType`
`options`	`GatewayRealtimeOptions`

Returns

Promise<GatewayRealtimeConnection>

Example

const connection = await inference.connectRealtime({ model: '@provider/model' }, {
  webSocketFactory: (url, options) => new WebSocket(url, options),
});
try { for await (const event of connection) console.log(event.type); }
finally { await connection.cancel(); }

createCompletion()

Call Signature

createCompletion(body, options?): Promise<GatewayStream<GatewayInferenceCreateCompletionResponse>>;

Defined in: src/ai-gateway/inference-client.ts:278

Experimental

Create a legacy text completion; stream=true returns a cancellable iterator. The deployed route exists, but the prescribed model returns HTTP 404. Outside stability guarantees until live-verified; the SDK never substitutes a model.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateCompletionRequest` & { `stream`: `true`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayStream<GatewayInferenceCreateCompletionResponse>>

Example

`await inference.createCompletion({ model: '@provider/compatible-model', prompt: 'Hello', max_tokens: 16 });`

Call Signature

createCompletion(body, options?): Promise<GatewayInferenceCreateCompletionResponse>;

Defined in: src/ai-gateway/inference-client.ts:282

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateCompletionRequest` & { `stream?`: `false` \| `null`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateCompletionResponse>

Example

`await inference.createCompletion({ model: '@provider/compatible-model', prompt: 'Hello', max_tokens: 16 });`

Call Signature

createCompletion(body, options?): Promise<
  | GatewayInferenceCreateCompletionResponse
| GatewayStream<GatewayInferenceCreateCompletionResponse>>;

Defined in: src/ai-gateway/inference-client.ts:286

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateCompletionRequest`
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise< | GatewayInferenceCreateCompletionResponse | GatewayStream<GatewayInferenceCreateCompletionResponse>>

Example

`await inference.createCompletion({ model: '@provider/compatible-model', prompt: 'Hello', max_tokens: 16 });`

createPromptCompletion()

Call Signature

createPromptCompletion(
   promptId, 
   body, 
options?): Promise<GatewayStream<GatewayInferenceCreatePromptCompletionStreamResponse>>;

Defined in: src/ai-gateway/inference-client.ts:331

Experimental

Execute a saved prompt with variables and optional root-level parameter overrides. Route and handler dispatch confirmed in the deployed gateway; no owned template has been live-certified. Outside stability guarantees until live-verified. JSON may be a native chat/text completion or the upstream status/headers/body wrapper. Streaming emits native chat or legacy completion events, terminated by [DONE].

Parameters

Parameter	Type
`promptId`	`string`
`body`	`GatewayInferenceInputCreatePromptCompletionRequest` & { `stream`: `true`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayStream<GatewayInferenceCreatePromptCompletionStreamResponse>>

Example

`await inference.createPromptCompletion('owned-prompt', { variables: { user_input: 'Hello' }, model: '@provider/model', max_completion_tokens: 16 });`

Call Signature

createPromptCompletion(
   promptId, 
   body, 
options?): Promise<GatewayInferenceCreatePromptCompletionResponse>;

Defined in: src/ai-gateway/inference-client.ts:336

Experimental

Parameters

Parameter	Type
`promptId`	`string`
`body`	`GatewayInferenceInputCreatePromptCompletionRequest` & { `stream?`: `false` \| `null`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreatePromptCompletionResponse>

Example

`await inference.createPromptCompletion('owned-prompt', { variables: { user_input: 'Hello' }, model: '@provider/model', max_completion_tokens: 16 });`

Call Signature

createPromptCompletion(
   promptId, 
   body, 
   options?): Promise<
  | GatewayInferenceCreatePromptCompletionResponse
| GatewayStream<GatewayInferenceCreatePromptCompletionStreamResponse>>;

Defined in: src/ai-gateway/inference-client.ts:341

Experimental

Parameters

Parameter	Type
`promptId`	`string`
`body`	`GatewayInferenceInputCreatePromptCompletionRequest`
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise< | GatewayInferenceCreatePromptCompletionResponse | GatewayStream<GatewayInferenceCreatePromptCompletionStreamResponse>>

Example

`await inference.createPromptCompletion('owned-prompt', { variables: { user_input: 'Hello' }, model: '@provider/model', max_completion_tokens: 16 });`

createPromptRender()

createPromptRender(
   promptId, 
   body, 
options?): Promise<GatewayInferencePromptRenderResponse>;

Defined in: src/ai-gateway/inference-client.ts:386

Experimental

Render a saved prompt without making a completion request. The deployed route is registered; successful rendering of an owned template remains unverified. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`promptId`	`string`
`body`	`GatewayInferenceInputCreatePromptRenderRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferencePromptRenderResponse>

Example

`await inference.createPromptRender('owned-prompt', { variables: { user_input: 'Hello' } });`

createChatCompletion()

Call Signature

createChatCompletion(body, options?): Promise<GatewayStream<GatewayInferenceCreateChatCompletionStreamResponse>>;

Defined in: src/ai-gateway/inference-client.ts:404

Create a chat completion. stream=true returns a cancellable async iterator.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateChatCompletionRequest` & { `stream`: `true`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayStream<GatewayInferenceCreateChatCompletionStreamResponse>>

Example

`const result = await inference.createChatCompletion({ model: '@provider/model', messages: [{ role: 'user', content: 'Hello' }] });`

Call Signature

createChatCompletion(body, options?): Promise<GatewayInferenceCreateChatCompletionResponse>;

Defined in: src/ai-gateway/inference-client.ts:408

Create a chat completion. stream=true returns a cancellable async iterator.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateChatCompletionRequest` & { `stream?`: `false` \| `null`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateChatCompletionResponse>

Example

`const result = await inference.createChatCompletion({ model: '@provider/model', messages: [{ role: 'user', content: 'Hello' }] });`

Call Signature

createChatCompletion(body, options?): Promise<
  | GatewayInferenceCreateChatCompletionResponse
| GatewayStream<GatewayInferenceCreateChatCompletionStreamResponse>>;

Defined in: src/ai-gateway/inference-client.ts:412

Create a chat completion. stream=true returns a cancellable async iterator.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateChatCompletionRequest`
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise< | GatewayInferenceCreateChatCompletionResponse | GatewayStream<GatewayInferenceCreateChatCompletionStreamResponse>>

Example

`const result = await inference.createChatCompletion({ model: '@provider/model', messages: [{ role: 'user', content: 'Hello' }] });`

createEmbedding()

createEmbedding(body, options?): Promise<GatewayInferenceCreateEmbeddingResponse>;

Defined in: src/ai-gateway/inference-client.ts:444

Create embeddings without converting base64 output to a different wire representation.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateEmbeddingRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateEmbeddingResponse>

Example

`const result = await inference.createEmbedding({ model: '@provider/embedding', input: 'Hello', encoding_format: 'float' });`

createResponse()

Call Signature

createResponse(body, options?): Promise<GatewayStream<GatewayInferenceResponseStreamEvent>>;

Defined in: src/ai-gateway/inference-client.ts:461

Create a Responses API result, or a cancellable stream of typed lifecycle events.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateResponse` & { `stream`: `true`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayStream<GatewayInferenceResponseStreamEvent>>

Example

`const result = await inference.createResponse({ model: '@provider/model', input: 'Hello', store: false });`

Call Signature

createResponse(body, options?): Promise<GatewayInferenceResponse>;

Defined in: src/ai-gateway/inference-client.ts:465

Create a Responses API result, or a cancellable stream of typed lifecycle events.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateResponse` & { `stream?`: `false` \| `null`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceResponse>

Example

`const result = await inference.createResponse({ model: '@provider/model', input: 'Hello', store: false });`

Call Signature

createResponse(body, options?): Promise<
  | GatewayInferenceResponse
| GatewayStream<GatewayInferenceResponseStreamEvent>>;

Defined in: src/ai-gateway/inference-client.ts:469

Create a Responses API result, or a cancellable stream of typed lifecycle events.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateResponse`
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise< | GatewayInferenceResponse | GatewayStream<GatewayInferenceResponseStreamEvent>>

Example

`const result = await inference.createResponse({ model: '@provider/model', input: 'Hello', store: false });`

createImage()

createImage(body, options?): Promise<GatewayInferenceImagesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:155

Experimental

POST /images/generations. Provider routing uses options.headers['x-portkey-provider']. Offline JSON contract only. The prescribed-model generation probe returned HTTP 400; no alternate model used. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateImageRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceImagesResponse>

Example

`await inference.createImage(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createImage

createImageEdit()

createImageEdit(body, options?): Promise<GatewayInferenceImagesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:173

Experimental

POST /images/edits. Provider routing uses options.headers['x-portkey-provider']. Offline multipart contract only. The prescribed-model edit probe returned HTTP 400; successful live editing is unverified. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateImageEditRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceImagesResponse>

Example

`await inference.createImageEdit(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createImageEdit

createImageVariation()

createImageVariation(body, options?): Promise<GatewayInferenceImagesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:192

Experimental

POST /images/variations. Provider routing uses options.headers['x-portkey-provider']. Offline multipart contract only. The prescribed-model variation probe returned HTTP 404; successful live variation is unverified. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateImageVariationRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceImagesResponse>

Example

`await inference.createImageVariation(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createImageVariation

createRerank()

createRerank(body, options?): Promise<GatewayInferenceCreateRerankResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:211

Experimental

POST /rerank. Provider routing uses options.headers['x-portkey-provider']. Offline JSON contract only. The prescribed-provider rerank probe returned HTTP 500; no different provider was configured. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateRerankRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateRerankResponse>

Example

`await inference.createRerank(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createRerank

createOcr()

createOcr(body, options?): Promise<GatewayInferenceCreateOcrResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:229

Experimental

POST /ocr. Provider routing uses options.headers['x-portkey-provider']. Offline JSON contract only. The prescribed-provider OCR probe returned HTTP 500; no different provider was configured. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateOcrRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateOcrResponse>

Example

`await inference.createOcr(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createOcr

createSpeech()

createSpeech(body, options?): Promise<Uint8Array<ArrayBufferLike>>;

Defined in: src/ai-gateway/runtime-resources-client.ts:247

Experimental

POST /audio/speech. Provider routing uses options.headers['x-portkey-provider']. Offline binary-response contract only. The prescribed-model speech probe returned HTTP 404; no audio model was substituted. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateSpeechRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<Uint8Array<ArrayBufferLike>>

Example

`await inference.createSpeech(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createSpeech

createTranscription()

Call Signature

createTranscription(body, options?): Promise<GatewayInferenceCreateTranscriptionResponseJson>;

Defined in: src/ai-gateway/runtime-resources-client.ts:265

Experimental

POST /audio/transcriptions. Provider routing uses options.headers['x-portkey-provider']. Offline multipart/format-specific response contracts only. The prescribed-model transcription probe returned HTTP 400 with model incompatibility. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranscriptionRequest` & { `response_format?`: `"json"`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateTranscriptionResponseJson>

Example

`await inference.createTranscription(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranscription

Call Signature

createTranscription(body, options?): Promise<GatewayInferenceCreateTranscriptionResponseVerboseJson>;

Defined in: src/ai-gateway/runtime-resources-client.ts:269

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranscriptionRequest` & { `response_format`: `"verbose_json"`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateTranscriptionResponseVerboseJson>

Example

`await inference.createTranscription(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranscription

Call Signature

createTranscription(body, options?): Promise<string>;

Defined in: src/ai-gateway/runtime-resources-client.ts:273

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranscriptionRequest` & { `response_format`: `"text"` \| `"srt"` \| `"vtt"`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<string>

Example

`await inference.createTranscription(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranscription

Call Signature

createTranscription(body, options?): Promise<
  | string
  | GatewayInferenceCreateTranscriptionResponseJson
| GatewayInferenceCreateTranscriptionResponseVerboseJson>;

Defined in: src/ai-gateway/runtime-resources-client.ts:279

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranscriptionRequest`
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise< | string | GatewayInferenceCreateTranscriptionResponseJson | GatewayInferenceCreateTranscriptionResponseVerboseJson>

Example

`await inference.createTranscription(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranscription

createTranslation()

Call Signature

createTranslation(body, options?): Promise<GatewayInferenceCreateTranslationResponseJson>;

Defined in: src/ai-gateway/runtime-resources-client.ts:320

Experimental

POST /audio/translations. Provider routing uses options.headers['x-portkey-provider']. Offline multipart/format-specific response contracts only. The prescribed-model translation probe returned HTTP 400 with model incompatibility. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranslationRequest` & { `response_format?`: `"json"`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateTranslationResponseJson>

Example

`await inference.createTranslation(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranslation

Call Signature

createTranslation(body, options?): Promise<GatewayInferenceCreateTranslationResponseVerboseJson>;

Defined in: src/ai-gateway/runtime-resources-client.ts:324

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranslationRequest` & { `response_format`: `"verbose_json"`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateTranslationResponseVerboseJson>

Example

`await inference.createTranslation(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranslation

Call Signature

createTranslation(body, options?): Promise<string>;

Defined in: src/ai-gateway/runtime-resources-client.ts:328

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranslationRequest` & { `response_format`: `"text"` \| `"srt"` \| `"vtt"`; }
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise<string>

Example

`await inference.createTranslation(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranslation

Call Signature

createTranslation(body, options?): Promise<
  | string
  | GatewayInferenceCreateTranslationResponseJson
| GatewayInferenceCreateTranslationResponseVerboseJson>;

Defined in: src/ai-gateway/runtime-resources-client.ts:334

Experimental

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateTranslationRequest`
`options?`	`GatewayInferenceRequestOptions`

Returns

Promise< | string | GatewayInferenceCreateTranslationResponseJson | GatewayInferenceCreateTranslationResponseVerboseJson>

Example

`await inference.createTranslation(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createTranslation

listFiles()

listFiles(opts?, options?): Promise<GatewayInferenceListFilesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:374

GET /files. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`opts`	`GatewayInferenceInputListFilesQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListFilesResponse>

Example

`await inference.listFiles({});`

Inherited from

AIGatewayRuntimeResourcesClient.listFiles

createFile()

createFile(body, options?): Promise<GatewayInferenceOpenAIFile>;

Defined in: src/ai-gateway/runtime-resources-client.ts:390

POST /files. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateFileRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceOpenAIFile>

Example

`await inference.createFile(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createFile

deleteFile()

deleteFile(file_id, options?): Promise<GatewayInferenceDeleteFileResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:408

DELETE /files/{file_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`file_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceDeleteFileResponse>

Example

`await inference.deleteFile('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.deleteFile

retrieveFile()

retrieveFile(file_id, options?): Promise<GatewayInferenceOpenAIFile>;

Defined in: src/ai-gateway/runtime-resources-client.ts:423

GET /files/{file_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`file_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceOpenAIFile>

Example

`await inference.retrieveFile('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.retrieveFile

downloadFile()

downloadFile(file_id, options?): Promise<Uint8Array<ArrayBufferLike>>;

Defined in: src/ai-gateway/runtime-resources-client.ts:438

GET /files/{file_id}/content. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`file_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<Uint8Array<ArrayBufferLike>>

Example

`await inference.downloadFile('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.downloadFile

createFineTuningJob()

createFineTuningJob(body, options?): Promise<GatewayInferenceFineTuningJob>;

Defined in: src/ai-gateway/runtime-resources-client.ts:454

Experimental

POST /fine_tuning/jobs. Provider routing uses options.headers['x-portkey-provider']. No training job was started. The designated inference model does not support fine-tuning; offline contract only. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateFineTuningJobRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceFineTuningJob>

Example

`await inference.createFineTuningJob(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createFineTuningJob

listPaginatedFineTuningJobs()

listPaginatedFineTuningJobs(opts?, options?): Promise<GatewayInferenceListPaginatedFineTuningJobsResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:471

GET /fine_tuning/jobs. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`opts`	`GatewayInferenceInputListPaginatedFineTuningJobsQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListPaginatedFineTuningJobsResponse>

Example

`await inference.listPaginatedFineTuningJobs({});`

Inherited from

AIGatewayRuntimeResourcesClient.listPaginatedFineTuningJobs

retrieveFineTuningJob()

retrieveFineTuningJob(fine_tuning_job_id, options?): Promise<GatewayInferenceFineTuningJob>;

Defined in: src/ai-gateway/runtime-resources-client.ts:488

Experimental

GET /fine_tuning/jobs/{fine_tuning_job_id}. Provider routing uses options.headers['x-portkey-provider']. No owned training job was available; offline contract only. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`fine_tuning_job_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceFineTuningJob>

Example

`await inference.retrieveFineTuningJob('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.retrieveFineTuningJob

listFineTuningEvents()

listFineTuningEvents(
   fine_tuning_job_id, 
   opts?, 
options?): Promise<GatewayInferenceListFineTuningJobEventsResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:504

Experimental

GET /fine_tuning/jobs/{fine_tuning_job_id}/events. Provider routing uses options.headers['x-portkey-provider']. No owned training job was available; offline contract only. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`fine_tuning_job_id`	`string`
`opts`	`GatewayInferenceInputListFineTuningEventsQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListFineTuningJobEventsResponse>

Example

`await inference.listFineTuningEvents('resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.listFineTuningEvents

cancelFineTuningJob()

cancelFineTuningJob(fine_tuning_job_id, options?): Promise<GatewayInferenceFineTuningJob>;

Defined in: src/ai-gateway/runtime-resources-client.ts:522

Experimental

POST /fine_tuning/jobs/{fine_tuning_job_id}/cancel. Provider routing uses options.headers['x-portkey-provider']. No owned training job was available; existing jobs were not changed. Offline contract only. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`fine_tuning_job_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceFineTuningJob>

Example

`await inference.cancelFineTuningJob('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.cancelFineTuningJob

listFineTuningJobCheckpoints()

listFineTuningJobCheckpoints(
   fine_tuning_job_id, 
   opts?, 
options?): Promise<GatewayInferenceListFineTuningJobCheckpointsResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:538

Experimental

GET /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints. Provider routing uses options.headers['x-portkey-provider']. No owned training job checkpoints were available; offline contract only. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`fine_tuning_job_id`	`string`
`opts`	`GatewayInferenceInputListFineTuningJobCheckpointsQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListFineTuningJobCheckpointsResponse>

Example

`await inference.listFineTuningJobCheckpoints('resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.listFineTuningJobCheckpoints

listModels()

listModels(opts?, options?): Promise<GatewayInferenceListModelsResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:555

GET /models. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`opts`	`GatewayInferenceInputListModelsQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListModelsResponse>

Example

`await inference.listModels({});`

Inherited from

AIGatewayRuntimeResourcesClient.listModels

retrieveModel()

retrieveModel(model, options?): Promise<GatewayInferenceModel>;

Defined in: src/ai-gateway/runtime-resources-client.ts:571

GET /models/{model}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`model`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceModel>

Example

`await inference.retrieveModel('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.retrieveModel

deleteModel()

deleteModel(model, options?): Promise<GatewayInferenceDeleteModelResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:587

Experimental

DELETE /models/{model}. Provider routing uses options.headers['x-portkey-provider']. No owned fine-tuned model was provisioned for deletion; offline contract only. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`model`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceDeleteModelResponse>

Example

`await inference.deleteModel('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.deleteModel

createModeration()

createModeration(body, options?): Promise<GatewayInferenceCreateModerationResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:603

Experimental

POST /moderations. Provider routing uses options.headers['x-portkey-provider']. Offline JSON contract only. The prescribed-model moderation probe returned HTTP 400; no specialized model was substituted. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateModerationRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceCreateModerationResponse>

Example

`await inference.createModeration(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createModeration

getResponse()

getResponse(
   response_id, 
   opts?, 
options?): Promise<GatewayInferenceResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:620

GET /responses/{response_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`response_id`	`string`
`opts`	`GatewayInferenceInputGetResponseQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceResponse>

Example

`await inference.getResponse('resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.getResponse

deleteResponse()

deleteResponse(response_id, options?): Promise<void>;

Defined in: src/ai-gateway/runtime-resources-client.ts:637

DELETE /responses/{response_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`response_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<void>

Example

`await inference.deleteResponse('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.deleteResponse

listInputItems()

listInputItems(
   response_id, 
   opts?, 
options?): Promise<GatewayInferenceResponseItemList>;

Defined in: src/ai-gateway/runtime-resources-client.ts:651

GET /responses/{response_id}/input_items. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`response_id`	`string`
`opts`	`GatewayInferenceInputListInputItemsQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceResponseItemList>

Example

`await inference.listInputItems('resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.listInputItems

listVectorStores()

listVectorStores(opts?, options?): Promise<GatewayInferenceListVectorStoresResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:668

GET /vector_stores. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`opts`	`GatewayInferenceInputListVectorStoresQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListVectorStoresResponse>

Example

`await inference.listVectorStores({});`

Inherited from

AIGatewayRuntimeResourcesClient.listVectorStores

createVectorStore()

createVectorStore(body, options?): Promise<GatewayInferenceVectorStoreObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:684

POST /vector_stores. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateVectorStoreRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreObject>

Example

`await inference.createVectorStore(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createVectorStore

getVectorStore()

getVectorStore(vector_store_id, options?): Promise<GatewayInferenceVectorStoreObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:701

GET /vector_stores/{vector_store_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreObject>

Example

`await inference.getVectorStore('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.getVectorStore

modifyVectorStore()

modifyVectorStore(
   vector_store_id, 
   body, 
options?): Promise<GatewayInferenceVectorStoreObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:716

POST /vector_stores/{vector_store_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`body`	`GatewayInferenceInputUpdateVectorStoreRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreObject>

Example

`await inference.modifyVectorStore('resource-id', body);`

Inherited from

AIGatewayRuntimeResourcesClient.modifyVectorStore

deleteVectorStore()

deleteVectorStore(vector_store_id, options?): Promise<GatewayInferenceDeleteVectorStoreResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:734

DELETE /vector_stores/{vector_store_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceDeleteVectorStoreResponse>

Example

`await inference.deleteVectorStore('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.deleteVectorStore

listVectorStoreFiles()

listVectorStoreFiles(
   vector_store_id, 
   opts?, 
options?): Promise<GatewayInferenceListVectorStoreFilesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:749

GET /vector_stores/{vector_store_id}/files. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`opts`	`GatewayInferenceInputListVectorStoreFilesQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListVectorStoreFilesResponse>

Example

`await inference.listVectorStoreFiles('resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.listVectorStoreFiles

createVectorStoreFile()

createVectorStoreFile(
   vector_store_id, 
   body, 
options?): Promise<GatewayInferenceVectorStoreFileObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:766

POST /vector_stores/{vector_store_id}/files. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`body`	`GatewayInferenceInputCreateVectorStoreFileRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreFileObject>

Example

`await inference.createVectorStoreFile('resource-id', body);`

Inherited from

AIGatewayRuntimeResourcesClient.createVectorStoreFile

getVectorStoreFile()

getVectorStoreFile(
   vector_store_id, 
   file_id, 
options?): Promise<GatewayInferenceVectorStoreFileObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:784

GET /vector_stores/{vector_store_id}/files/{file_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`file_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreFileObject>

Example

`await inference.getVectorStoreFile('resource-id', 'resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.getVectorStoreFile

deleteVectorStoreFile()

deleteVectorStoreFile(
   vector_store_id, 
   file_id, 
options?): Promise<GatewayInferenceDeleteVectorStoreFileResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:800

DELETE /vector_stores/{vector_store_id}/files/{file_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`file_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceDeleteVectorStoreFileResponse>

Example

`await inference.deleteVectorStoreFile('resource-id', 'resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.deleteVectorStoreFile

createVectorStoreFileBatch()

createVectorStoreFileBatch(
   vector_store_id, 
   body, 
options?): Promise<GatewayInferenceVectorStoreFileBatchObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:816

POST /vector_stores/{vector_store_id}/file_batches. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`body`	`GatewayInferenceInputCreateVectorStoreFileBatchRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreFileBatchObject>

Example

`await inference.createVectorStoreFileBatch('resource-id', body);`

Inherited from

AIGatewayRuntimeResourcesClient.createVectorStoreFileBatch

getVectorStoreFileBatch()

getVectorStoreFileBatch(
   vector_store_id, 
   batch_id, 
options?): Promise<GatewayInferenceVectorStoreFileBatchObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:834

GET /vector_stores/{vector_store_id}/file_batches/{batch_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`batch_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreFileBatchObject>

Example

`await inference.getVectorStoreFileBatch('resource-id', 'resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.getVectorStoreFileBatch

cancelVectorStoreFileBatch()

cancelVectorStoreFileBatch(
   vector_store_id, 
   batch_id, 
options?): Promise<GatewayInferenceVectorStoreFileBatchObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:851

Experimental

POST /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel. Provider routing uses options.headers['x-portkey-provider']. The owned file-batch cancellation endpoint returned HTTP 500; successful cancellation remains unverified. Create, completed retrieval and file listing passed. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`vector_store_id`	`string`
`batch_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceVectorStoreFileBatchObject>

Example

`await inference.cancelVectorStoreFileBatch('resource-id', 'resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.cancelVectorStoreFileBatch

listFilesInVectorStoreBatch()

listFilesInVectorStoreBatch(
   vector_store_id, 
   batch_id, 
   opts?, 
options?): Promise<GatewayInferenceListVectorStoreFilesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:867

GET /vector_stores/{vector_store_id}/file_batches/{batch_id}/files. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`vector_store_id`	`string`
`batch_id`	`string`
`opts`	`GatewayInferenceInputListFilesInVectorStoreBatchQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListVectorStoreFilesResponse>

Example

`await inference.listFilesInVectorStoreBatch('resource-id', 'resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.listFilesInVectorStoreBatch

createBatch()

createBatch(body, options?): Promise<GatewayInferenceBatch>;

Defined in: src/ai-gateway/runtime-resources-client.ts:885

POST /batches. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateBatchRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceBatch>

Example

`await inference.createBatch(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createBatch

listBatches()

listBatches(opts?, options?): Promise<GatewayInferenceListBatchesResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:902

GET /batches. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`opts`	`GatewayInferenceInputListBatchesQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceListBatchesResponse>

Example

`await inference.listBatches({});`

Inherited from

AIGatewayRuntimeResourcesClient.listBatches

getBatchOutput()

getBatchOutput(batch_id, options?): Promise<Uint8Array<ArrayBufferLike>>;

Defined in: src/ai-gateway/runtime-resources-client.ts:918

GET /batches/{batch_id}/output. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`batch_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<Uint8Array<ArrayBufferLike>>

Example

`await inference.getBatchOutput('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.getBatchOutput

retrieveBatch()

retrieveBatch(batch_id, options?): Promise<GatewayInferenceBatch>;

Defined in: src/ai-gateway/runtime-resources-client.ts:933

GET /batches/{batch_id}. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`batch_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceBatch>

Example

`await inference.retrieveBatch('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.retrieveBatch

cancelBatch()

cancelBatch(batch_id, options?): Promise<GatewayInferenceBatch>;

Defined in: src/ai-gateway/runtime-resources-client.ts:948

POST /batches/{batch_id}/cancel. Provider routing uses options.headers['x-portkey-provider'].

Parameters

Parameter	Type
`batch_id`	`string`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceBatch>

Example

`await inference.cancelBatch('resource-id');`

Inherited from

AIGatewayRuntimeResourcesClient.cancelBatch

createFeedback()

createFeedback(body, options?): Promise<GatewayInferenceFeedbackResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:963

POST /feedback. Verified on the explicit Prisma runtime endpoint with a runtime key, not SCM OAuth. No deletion API is declared; synthetic audit records may persist.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputFeedbackRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceFeedbackResponse>

Example

`await inference.createFeedback(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createFeedback

updateFeedback()

updateFeedback(
   id, 
   body, 
options?): Promise<GatewayInferenceFeedbackResponse>;

Defined in: src/ai-gateway/runtime-resources-client.ts:982

Experimental

PUT /feedback/{id}. Explicit Prisma runtime endpoint/key only, not SCM OAuth. Successful response shapes are upstream contracts, not live-certified in this tenant. Uses the declared PUT operation, not the inconsistent POST curl sample. No automatic retry by default. Confirmed runtime handler; owned-record PUT returns HTTP 500 because feedback lookup requires uninitialized ClickHouse in control-plane storage mode. Typed contracts are experimental, not a successful live update. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`id`	`string`
`body`	`GatewayInferenceInputFeedbackUpdateRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceFeedbackResponse>

Example

`await inference.updateFeedback('550e8400-e29b-41d4-a716-446655440000', body);`

Inherited from

AIGatewayRuntimeResourcesClient.updateFeedback

createLogs()

createLogs(body, options?): Promise<string>;

Defined in: src/ai-gateway/runtime-resources-client.ts:1001

POST /logs. Verified on the explicit Prisma runtime endpoint with a runtime key, not SCM OAuth. No deletion API is declared; synthetic audit records may persist.

Parameters

Parameter	Type
`body`	`GatewayInferenceInputCreateLogsRequest`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<string>

Example

`await inference.createLogs(body);`

Inherited from

AIGatewayRuntimeResourcesClient.createLogs

getLog()

getLog(
   logId, 
   opts?, 
options?): Promise<GatewayInferenceLogObject>;

Defined in: src/ai-gateway/runtime-resources-client.ts:1020

Experimental

GET /logs/{logId}. Explicit Prisma runtime endpoint/key only, not SCM OAuth. Successful response shapes are upstream contracts, not live-certified in this tenant. v2 storage paths require an ISO timestamp with a timezone; omit type for ordinary logs. Log bodies may contain sensitive data and are always omitted from SDK debug output. Confirmed runtime handler; owned-log reads return HTTP 500 because the deployed handler has no control-plane storage branch. Typed contracts and v2 timestamp validation are experimental, not successful live retrieval. Outside stability guarantees until live-verified.

Parameters

Parameter	Type
`logId`	`string`
`opts`	`GatewayInferenceInputGetLogQuery`
`options`	`GatewayInferenceRequestOptions`

Returns

Promise<GatewayInferenceLogObject>

Example

`await inference.getLog('resource-id', {});`

Inherited from

AIGatewayRuntimeResourcesClient.getLog

Example​

Extends​

Constructors​

Constructor​

Parameters​

Returns​

Overrides​

Methods​

connectRealtime()​

Parameters​

Returns​

Example​

createCompletion()​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

createPromptCompletion()​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

createPromptRender()​

Parameters​

Returns​

Example​

createChatCompletion()​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

createEmbedding()​

Parameters​

Returns​

Example​

createResponse()​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

Call Signature​

Parameters​

Returns​

Example​

createImage()​

Parameters​

Returns​

Example​

Inherited from​

createImageEdit()​

Parameters​

Returns​

Example

Extends

Constructors

Constructor

Parameters

Returns

Overrides

Methods

connectRealtime()

Parameters

Returns

Example

createCompletion()

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

createPromptCompletion()

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

createPromptRender()

Parameters

Returns

Example

createChatCompletion()

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

createEmbedding()

Parameters

Returns

Example

createResponse()

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

Call Signature

Parameters

Returns

Example

createImage()

Parameters

Returns

Example

Inherited from

createImageEdit()

Parameters

Returns