@deeprelay/sdk 0.1.2 → 0.2.1

package/.openapi-generator/FILES

@@ -31,10 +31,6 @@ docs/ModelPricing.md
 docs/ModelRate.md
 docs/OpenAIErrorEnvelope.md
 docs/OpenAIErrorEnvelopeError.md
-docs/Operation.md
-docs/OperationError.md
-docs/OperationResult.md
-docs/OperationsApi.md
 docs/PeakWindow.md
 docs/Problem.md
 docs/RefereeStatus.md
@@ -65,7 +61,6 @@ package.json
 src/apis/BillingApi.ts
 src/apis/InferenceApi.ts
 src/apis/MetaApi.ts
-src/apis/OperationsApi.ts
 src/apis/UsageApi.ts
 src/apis/WebhooksApi.ts
 src/apis/index.ts
@@ -97,9 +92,6 @@ src/models/ModelPricing.ts
 src/models/ModelRate.ts
 src/models/OpenAIErrorEnvelope.ts
 src/models/OpenAIErrorEnvelopeError.ts
-src/models/Operation.ts
-src/models/OperationError.ts
-src/models/OperationResult.ts
 src/models/PeakWindow.ts
 src/models/Problem.ts
 src/models/RefereeStatus.ts

package/README.md

@@ -1,4 +1,4 @@
-# @deeprelay/sdk@0.1.2
+# @deeprelay/sdk@0.2.1
 
 A TypeScript SDK client for the api.deeprelay.ai API.
 
@@ -57,6 +57,7 @@ All URIs are relative to *https://api.deeprelay.ai/v1*
 *BillingApi* | [**createCryptoDeposit**](docs/BillingApi.md#createcryptodepositoperation) | **POST** /billing/deposits/crypto | Create a stablecoin deposit
 *BillingApi* | [**createSubscriptionCheckout**](docs/BillingApi.md#createsubscriptioncheckout) | **POST** /billing/subscription/checkout | Start a subscription checkout session
 *BillingApi* | [**createSubscriptionPortal**](docs/BillingApi.md#createsubscriptionportal) | **POST** /billing/subscription/portal | Open the billing portal to cancel or manage the subscription
+*BillingApi* | [**deleteSpendingLimit**](docs/BillingApi.md#deletespendinglimit) | **DELETE** /billing/spending-limit | Clear the org spending limit
 *BillingApi* | [**getBalance**](docs/BillingApi.md#getbalance) | **GET** /billing/balance | Get the org credit balance
 *BillingApi* | [**getDeposit**](docs/BillingApi.md#getdeposit) | **GET** /billing/deposits/{id} | Get one stablecoin deposit
 *BillingApi* | [**getReferral**](docs/BillingApi.md#getreferral) | **GET** /referrals | Get the org referral code, invite link, terms and stats
@@ -77,7 +78,6 @@ All URIs are relative to *https://api.deeprelay.ai/v1*
 *InferenceApi* | [**listVideos**](docs/InferenceApi.md#listvideos) | **GET** /videos | List video generation jobs
 *MetaApi* | [**getHealth**](docs/MetaApi.md#gethealth) | **GET** /health | Liveness probe
 *MetaApi* | [**getOpenApiSpec**](docs/MetaApi.md#getopenapispec) | **GET** /openapi.json | OpenAPI 3.1 specification
-*OperationsApi* | [**getOperation**](docs/OperationsApi.md#getoperation) | **GET** /operations/{id} | Get an async operation status
 *UsageApi* | [**listUsage**](docs/UsageApi.md#listusage) | **GET** /usage | Time-bucketed usage
 *WebhooksApi* | [**createWebhookEndpoint**](docs/WebhooksApi.md#createwebhookendpointoperation) | **POST** /webhook-endpoints | Create a webhook endpoint
 *WebhooksApi* | [**deleteWebhookEndpoint**](docs/WebhooksApi.md#deletewebhookendpoint) | **DELETE** /webhook-endpoints/{id} | Delete a webhook endpoint
@@ -114,9 +114,6 @@ All URIs are relative to *https://api.deeprelay.ai/v1*
 - [ModelRate](docs/ModelRate.md)
 - [OpenAIErrorEnvelope](docs/OpenAIErrorEnvelope.md)
 - [OpenAIErrorEnvelopeError](docs/OpenAIErrorEnvelopeError.md)
-- [Operation](docs/Operation.md)
-- [OperationError](docs/OperationError.md)
-- [OperationResult](docs/OperationResult.md)
 - [PeakWindow](docs/PeakWindow.md)
 - [Problem](docs/Problem.md)
 - [RefereeStatus](docs/RefereeStatus.md)
@@ -159,7 +156,7 @@ and is automatically generated by the
 [OpenAPI Generator](https://openapi-generator.tech) project:
 
 - API version: `1.0.0`
-- Package version: `0.1.2`
+- Package version: `0.2.1`
 - Generator version: `7.24.0`
 - Build package: `org.openapitools.codegen.languages.TypeScriptFetchClientCodegen`
 

package/dist/apis/BillingApi.d.ts

@@ -83,6 +83,20 @@ export declare class BillingApi extends runtime.BaseAPI {
      * Open the billing portal to cancel or manage the subscription
      */
     createSubscriptionPortal(requestParameters?: CreateSubscriptionPortalRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<SubscriptionPortalSession>;
+    /**
+     * Creates request options for deleteSpendingLimit without sending the request
+     */
+    deleteSpendingLimitRequestOpts(): Promise<runtime.RequestOpts>;
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimitRaw(initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<void>>;
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimit(initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<void>;
     /**
      * Creates request options for getBalance without sending the request
      */

package/dist/apis/BillingApi.js

@@ -181,6 +181,49 @@ class BillingApi extends runtime.BaseAPI {
             return yield response.value();
         });
     }
+    /**
+     * Creates request options for deleteSpendingLimit without sending the request
+     */
+    deleteSpendingLimitRequestOpts() {
+        return __awaiter(this, void 0, void 0, function* () {
+            const queryParameters = {};
+            const headerParameters = {};
+            if (this.configuration && this.configuration.accessToken) {
+                const token = this.configuration.accessToken;
+                const tokenString = yield token("bearerAuth", []);
+                if (tokenString) {
+                    headerParameters["Authorization"] = `Bearer ${tokenString}`;
+                }
+            }
+            let urlPath = `/billing/spending-limit`;
+            return {
+                path: urlPath,
+                method: 'DELETE',
+                headers: headerParameters,
+                query: queryParameters,
+            };
+        });
+    }
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimitRaw(initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            const requestOptions = yield this.deleteSpendingLimitRequestOpts();
+            const response = yield this.request(requestOptions, initOverrides);
+            return new runtime.VoidApiResponse(response);
+        });
+    }
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimit(initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            yield this.deleteSpendingLimitRaw(initOverrides);
+        });
+    }
     /**
      * Creates request options for getBalance without sending the request
      */

package/dist/apis/UsageApi.d.ts

@@ -18,6 +18,8 @@ export interface ListUsageRequest {
     end?: Date;
     cursor?: string;
     limit?: number;
+    modality?: ListUsageModalityEnum;
+    model?: string;
 }
 /**
  *
@@ -28,10 +30,12 @@ export declare class UsageApi extends runtime.BaseAPI {
      */
     listUsageRequestOpts(requestParameters: ListUsageRequest): Promise<runtime.RequestOpts>;
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsageRaw(requestParameters: ListUsageRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<UsagePage>>;
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsage(requestParameters?: ListUsageRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<UsagePage>;
@@ -54,3 +58,13 @@ export declare const ListUsageGroupByEnum: {
     readonly GpuType: "gpu_type";
 };
 export type ListUsageGroupByEnum = typeof ListUsageGroupByEnum[keyof typeof ListUsageGroupByEnum];
+/**
+ * @export
+ */
+export declare const ListUsageModalityEnum: {
+    readonly Chat: "chat";
+    readonly Image: "image";
+    readonly Video: "video";
+    readonly Embedding: "embedding";
+};
+export type ListUsageModalityEnum = typeof ListUsageModalityEnum[keyof typeof ListUsageModalityEnum];

package/dist/apis/UsageApi.js

@@ -22,7 +22,7 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
     });
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.ListUsageGroupByEnum = exports.ListUsageBucketEnum = exports.UsageApi = void 0;
+exports.ListUsageModalityEnum = exports.ListUsageGroupByEnum = exports.ListUsageBucketEnum = exports.UsageApi = void 0;
 const runtime = require("../runtime");
 const UsagePage_1 = require("../models/UsagePage");
 /**
@@ -53,6 +53,12 @@ class UsageApi extends runtime.BaseAPI {
             if (requestParameters['limit'] != null) {
                 queryParameters['limit'] = requestParameters['limit'];
             }
+            if (requestParameters['modality'] != null) {
+                queryParameters['modality'] = requestParameters['modality'];
+            }
+            if (requestParameters['model'] != null) {
+                queryParameters['model'] = requestParameters['model'];
+            }
             const headerParameters = {};
             if (this.configuration && this.configuration.accessToken) {
                 const token = this.configuration.accessToken;
@@ -71,6 +77,7 @@ class UsageApi extends runtime.BaseAPI {
         });
     }
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsageRaw(requestParameters, initOverrides) {
@@ -81,6 +88,7 @@ class UsageApi extends runtime.BaseAPI {
         });
     }
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsage() {
@@ -107,3 +115,12 @@ exports.ListUsageGroupByEnum = {
     InstanceId: 'instance_id',
     GpuType: 'gpu_type'
 };
+/**
+ * @export
+ */
+exports.ListUsageModalityEnum = {
+    Chat: 'chat',
+    Image: 'image',
+    Video: 'video',
+    Embedding: 'embedding'
+};

package/dist/apis/index.d.ts

@@ -1,6 +1,5 @@
 export * from './BillingApi';
 export * from './InferenceApi';
 export * from './MetaApi';
-export * from './OperationsApi';
 export * from './UsageApi';
 export * from './WebhooksApi';

package/dist/apis/index.js

@@ -19,6 +19,5 @@ Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./BillingApi"), exports);
 __exportStar(require("./InferenceApi"), exports);
 __exportStar(require("./MetaApi"), exports);
-__exportStar(require("./OperationsApi"), exports);
 __exportStar(require("./UsageApi"), exports);
 __exportStar(require("./WebhooksApi"), exports);

package/dist/esm/apis/BillingApi.d.ts

@@ -83,6 +83,20 @@ export declare class BillingApi extends runtime.BaseAPI {
      * Open the billing portal to cancel or manage the subscription
      */
     createSubscriptionPortal(requestParameters?: CreateSubscriptionPortalRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<SubscriptionPortalSession>;
+    /**
+     * Creates request options for deleteSpendingLimit without sending the request
+     */
+    deleteSpendingLimitRequestOpts(): Promise<runtime.RequestOpts>;
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimitRaw(initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<void>>;
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimit(initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<void>;
     /**
      * Creates request options for getBalance without sending the request
      */

package/dist/esm/apis/BillingApi.js

@@ -178,6 +178,49 @@ export class BillingApi extends runtime.BaseAPI {
             return yield response.value();
         });
     }
+    /**
+     * Creates request options for deleteSpendingLimit without sending the request
+     */
+    deleteSpendingLimitRequestOpts() {
+        return __awaiter(this, void 0, void 0, function* () {
+            const queryParameters = {};
+            const headerParameters = {};
+            if (this.configuration && this.configuration.accessToken) {
+                const token = this.configuration.accessToken;
+                const tokenString = yield token("bearerAuth", []);
+                if (tokenString) {
+                    headerParameters["Authorization"] = `Bearer ${tokenString}`;
+                }
+            }
+            let urlPath = `/billing/spending-limit`;
+            return {
+                path: urlPath,
+                method: 'DELETE',
+                headers: headerParameters,
+                query: queryParameters,
+            };
+        });
+    }
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimitRaw(initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            const requestOptions = yield this.deleteSpendingLimitRequestOpts();
+            const response = yield this.request(requestOptions, initOverrides);
+            return new runtime.VoidApiResponse(response);
+        });
+    }
+    /**
+     * Removes the organization\'s monthly spending limit and daily spend cap entirely. Requires the `billing:write` scope AND org-admin privileges (a non-admin member gets 403). Returns 404 when no limit is configured. This is the only way to remove a limit through the API, because `PUT` floors `monthly_limit_dollars` at 1.00 and so cannot express \"no limit\".
+     * Clear the org spending limit
+     */
+    deleteSpendingLimit(initOverrides) {
+        return __awaiter(this, void 0, void 0, function* () {
+            yield this.deleteSpendingLimitRaw(initOverrides);
+        });
+    }
     /**
      * Creates request options for getBalance without sending the request
      */

package/dist/esm/apis/UsageApi.d.ts

@@ -18,6 +18,8 @@ export interface ListUsageRequest {
     end?: Date;
     cursor?: string;
     limit?: number;
+    modality?: ListUsageModalityEnum;
+    model?: string;
 }
 /**
  *
@@ -28,10 +30,12 @@ export declare class UsageApi extends runtime.BaseAPI {
      */
     listUsageRequestOpts(requestParameters: ListUsageRequest): Promise<runtime.RequestOpts>;
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsageRaw(requestParameters: ListUsageRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<UsagePage>>;
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsage(requestParameters?: ListUsageRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<UsagePage>;
@@ -54,3 +58,13 @@ export declare const ListUsageGroupByEnum: {
     readonly GpuType: "gpu_type";
 };
 export type ListUsageGroupByEnum = typeof ListUsageGroupByEnum[keyof typeof ListUsageGroupByEnum];
+/**
+ * @export
+ */
+export declare const ListUsageModalityEnum: {
+    readonly Chat: "chat";
+    readonly Image: "image";
+    readonly Video: "video";
+    readonly Embedding: "embedding";
+};
+export type ListUsageModalityEnum = typeof ListUsageModalityEnum[keyof typeof ListUsageModalityEnum];

package/dist/esm/apis/UsageApi.js

@@ -50,6 +50,12 @@ export class UsageApi extends runtime.BaseAPI {
             if (requestParameters['limit'] != null) {
                 queryParameters['limit'] = requestParameters['limit'];
             }
+            if (requestParameters['modality'] != null) {
+                queryParameters['modality'] = requestParameters['modality'];
+            }
+            if (requestParameters['model'] != null) {
+                queryParameters['model'] = requestParameters['model'];
+            }
             const headerParameters = {};
             if (this.configuration && this.configuration.accessToken) {
                 const token = this.configuration.accessToken;
@@ -68,6 +74,7 @@ export class UsageApi extends runtime.BaseAPI {
         });
     }
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsageRaw(requestParameters, initOverrides) {
@@ -78,6 +85,7 @@ export class UsageApi extends runtime.BaseAPI {
         });
     }
     /**
+     * Returns spend aggregated into time buckets over `[start, end)` (default: the last 30 days, `bucket=day`), newest bucket first.  The response has one of two row shapes, selected by the query:  - **Inference usage** — set `modality` and/or `model`. Rows aggregate serverless inference calls, one row per (bucket, modality, model), and carry `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count`. This is the usage a serverless-inference customer is billed for. - **Instance usage** — neither `modality` nor `model` set. Rows aggregate GPU instance billing sessions, optionally split by `group_by`. With no instance usage this returns an empty `data` array, so to read inference spend always pass `modality` or `model`.  Requires the `billing:read` scope.
      * Time-bucketed usage
      */
     listUsage() {
@@ -103,3 +111,12 @@ export const ListUsageGroupByEnum = {
     InstanceId: 'instance_id',
     GpuType: 'gpu_type'
 };
+/**
+ * @export
+ */
+export const ListUsageModalityEnum = {
+    Chat: 'chat',
+    Image: 'image',
+    Video: 'video',
+    Embedding: 'embedding'
+};

package/dist/esm/apis/index.d.ts

@@ -1,6 +1,5 @@
 export * from './BillingApi';
 export * from './InferenceApi';
 export * from './MetaApi';
-export * from './OperationsApi';
 export * from './UsageApi';
 export * from './WebhooksApi';

package/dist/esm/apis/index.js

@@ -3,6 +3,5 @@
 export * from './BillingApi';
 export * from './InferenceApi';
 export * from './MetaApi';
-export * from './OperationsApi';
 export * from './UsageApi';
 export * from './WebhooksApi';

package/dist/esm/models/UsageBucket.d.ts

@@ -10,41 +10,74 @@
  * Do not edit the class manually.
  */
 /**
+ * One `/usage` row. Every row carries `bucket_start`, `gpu_seconds` and `cost_cents`. When the request set `modality` or `model` the row is an inference-usage row: it also carries `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count` (aggregating every serverless inference call in the bucket for that modality and model), and `gpu_seconds` is always 0. Otherwise it is an instance-usage row, carrying `instance_id` / `gpu_type` when `group_by` asked for them.
  *
  * @export
  * @interface UsageBucket
  */
 export interface UsageBucket {
     /**
-     *
+     * Start of the time bucket (truncated to `bucket`).
      * @type {Date}
      * @memberof UsageBucket
      */
     bucketStart: Date;
     /**
-     *
+     * Instance-usage rows with `group_by=instance_id` only.
      * @type {string}
      * @memberof UsageBucket
      */
     instanceId?: string;
     /**
-     *
+     * Instance-usage rows with `group_by=gpu_type` only.
      * @type {string}
      * @memberof UsageBucket
      */
     gpuType?: string;
     /**
-     *
+     * GPU instance seconds billed in the bucket. Always 0 on inference-usage rows.
      * @type {number}
      * @memberof UsageBucket
      */
     gpuSeconds: number;
     /**
-     *
+     * Total cost of the row, in US cents.
      * @type {number}
      * @memberof UsageBucket
      */
     costCents: number;
+    /**
+     * Inference-usage rows only: the modality of the calls in this row (chat, image, video or embedding).
+     *
+     * @type {string}
+     * @memberof UsageBucket
+     */
+    modality?: string;
+    /**
+     * Inference-usage rows only: the model `id` the calls in this row were made against.
+     *
+     * @type {string}
+     * @memberof UsageBucket
+     */
+    model?: string;
+    /**
+     * Inference-usage rows only. Sum of input tokens; 0 for modalities not billed per token.
+     * @type {number}
+     * @memberof UsageBucket
+     */
+    promptTokens?: number;
+    /**
+     * Inference-usage rows only. Sum of output tokens; 0 for modalities not billed per token.
+     * @type {number}
+     * @memberof UsageBucket
+     */
+    completionTokens?: number;
+    /**
+     * Inference-usage rows only. Sum of generated images; 0 for non-image modalities.
+     * @type {number}
+     * @memberof UsageBucket
+     */
+    imageCount?: number;
 }
 /**
  * Check if a given object implements the UsageBucket interface.

package/dist/esm/models/UsageBucket.js

@@ -36,6 +36,11 @@ export function UsageBucketFromJSONTyped(json, ignoreDiscriminator) {
         'gpuType': json['gpu_type'] == null ? undefined : json['gpu_type'],
         'gpuSeconds': json['gpu_seconds'],
         'costCents': json['cost_cents'],
+        'modality': json['modality'] == null ? undefined : json['modality'],
+        'model': json['model'] == null ? undefined : json['model'],
+        'promptTokens': json['prompt_tokens'] == null ? undefined : json['prompt_tokens'],
+        'completionTokens': json['completion_tokens'] == null ? undefined : json['completion_tokens'],
+        'imageCount': json['image_count'] == null ? undefined : json['image_count'],
     };
 }
 export function UsageBucketToJSON(json) {
@@ -51,5 +56,10 @@ export function UsageBucketToJSONTyped(value, ignoreDiscriminator = false) {
         'gpu_type': value['gpuType'],
         'gpu_seconds': value['gpuSeconds'],
         'cost_cents': value['costCents'],
+        'modality': value['modality'],
+        'model': value['model'],
+        'prompt_tokens': value['promptTokens'],
+        'completion_tokens': value['completionTokens'],
+        'image_count': value['imageCount'],
     };
 }

package/dist/esm/models/UsagePage.d.ts

@@ -17,6 +17,7 @@ import type { UsageBucket } from './UsageBucket';
  */
 export interface UsagePage {
     /**
+     * Inference-usage rows when the request set `modality` or `model`; instance-usage rows otherwise. One page never mixes the two.
      *
      * @type {Array<UsageBucket>}
      * @memberof UsagePage

package/dist/esm/models/index.d.ts

@@ -25,9 +25,6 @@ export * from './ModelPricing';
 export * from './ModelRate';
 export * from './OpenAIErrorEnvelope';
 export * from './OpenAIErrorEnvelopeError';
-export * from './Operation';
-export * from './OperationError';
-export * from './OperationResult';
 export * from './PeakWindow';
 export * from './Problem';
 export * from './RefereeStatus';

package/dist/esm/models/index.js

@@ -27,9 +27,6 @@ export * from './ModelPricing';
 export * from './ModelRate';
 export * from './OpenAIErrorEnvelope';
 export * from './OpenAIErrorEnvelopeError';
-export * from './Operation';
-export * from './OperationError';
-export * from './OperationResult';
 export * from './PeakWindow';
 export * from './Problem';
 export * from './RefereeStatus';

package/dist/esm/runtime.js

@@ -61,7 +61,7 @@ export class Configuration {
         return undefined;
     }
     get headers() {
-        return Object.assign({ 'User-Agent': 'deeprelay-sdk-ts/0.1.2' }, this.configuration.headers);
+        return Object.assign({ 'User-Agent': 'deeprelay-sdk-ts/0.2.1' }, this.configuration.headers);
     }
     get credentials() {
         return this.configuration.credentials;

package/dist/models/UsageBucket.d.ts

@@ -10,41 +10,74 @@
  * Do not edit the class manually.
  */
 /**
+ * One `/usage` row. Every row carries `bucket_start`, `gpu_seconds` and `cost_cents`. When the request set `modality` or `model` the row is an inference-usage row: it also carries `modality`, `model`, `prompt_tokens`, `completion_tokens` and `image_count` (aggregating every serverless inference call in the bucket for that modality and model), and `gpu_seconds` is always 0. Otherwise it is an instance-usage row, carrying `instance_id` / `gpu_type` when `group_by` asked for them.
  *
  * @export
  * @interface UsageBucket
  */
 export interface UsageBucket {
     /**
-     *
+     * Start of the time bucket (truncated to `bucket`).
      * @type {Date}
      * @memberof UsageBucket
      */
     bucketStart: Date;
     /**
-     *
+     * Instance-usage rows with `group_by=instance_id` only.
      * @type {string}
      * @memberof UsageBucket
      */
     instanceId?: string;
     /**
-     *
+     * Instance-usage rows with `group_by=gpu_type` only.
      * @type {string}
      * @memberof UsageBucket
      */
     gpuType?: string;
     /**
-     *
+     * GPU instance seconds billed in the bucket. Always 0 on inference-usage rows.
      * @type {number}
      * @memberof UsageBucket
      */
     gpuSeconds: number;
     /**
-     *
+     * Total cost of the row, in US cents.
      * @type {number}
      * @memberof UsageBucket
      */
     costCents: number;
+    /**
+     * Inference-usage rows only: the modality of the calls in this row (chat, image, video or embedding).
+     *
+     * @type {string}
+     * @memberof UsageBucket
+     */
+    modality?: string;
+    /**
+     * Inference-usage rows only: the model `id` the calls in this row were made against.
+     *
+     * @type {string}
+     * @memberof UsageBucket
+     */
+    model?: string;
+    /**
+     * Inference-usage rows only. Sum of input tokens; 0 for modalities not billed per token.
+     * @type {number}
+     * @memberof UsageBucket
+     */
+    promptTokens?: number;
+    /**
+     * Inference-usage rows only. Sum of output tokens; 0 for modalities not billed per token.
+     * @type {number}
+     * @memberof UsageBucket
+     */
+    completionTokens?: number;
+    /**
+     * Inference-usage rows only. Sum of generated images; 0 for non-image modalities.
+     * @type {number}
+     * @memberof UsageBucket
+     */
+    imageCount?: number;
 }
 /**
  * Check if a given object implements the UsageBucket interface.