> ## Documentation Index > Fetch the complete documentation index at: https://veniceai-mintlify-d2fddb8a.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Analyses d'utilisation de facturation (Beta) > **Beta**: This endpoint is currently in beta and may be unstable. Request/response schemas and behavior may change without notice. Get aggregated usage analytics for the authenticated user with breakdowns by date, model, and API key. This endpoint provides summary views of your API usage, ideal for dashboards and usage monitoring. Data is cached for 10 minutes. Il s'agit d'un endpoint en beta qui peut être instable ou changer sans préavis. Obtenez des analyses d'utilisation agrégées pour l'utilisateur authentifié, avec des ventilations par date, modèle et clé API. Cet endpoint fournit des vues récapitulatives de vos données d'utilisation de l'API pour construire des tableaux de bord et surveiller la consommation. Les données sont mises en cache pendant 10 minutes. ## Paramètres de requête Vous pouvez spécifier la période d'analyse en utilisant soit : * **lookback** : Une période relative comme "7d" (7 jours), "30d" (30 jours), jusqu'à "90d" (90 jours) * **startDate** et **endDate** : Une plage de dates personnalisée au format `YYYY-MM-DD`. Les deux sont requis si l'un est fourni. Si aucun paramètre n'est spécifié, la période de lookback par défaut est de 7 jours. ## Champs de la réponse ### lookback La période de lookback utilisée pour la requête. Soit au format "Nd" (par exemple "7d"), soit au format "startDate:endDate". ### byDate Totaux d'utilisation quotidienne pour la période demandée. * **date** : La date au format `YYYY-MM-DD` * **USD** : Utilisation totale en USD pour ce jour * **DIEM** : Utilisation totale en DIEM pour ce jour ### byModel Ventilation de l'utilisation par modèle, triée par dépense totale (la plus élevée d'abord). * **modelName** : Nom d'affichage du modèle (par exemple "GLM 5") * **unitType** : Type d'unités consommées (tokens, images, chars, minutes, seconds) * **modelType** : Type de modèle (LLM, IMAGE, TTS, ASR, VIDEO), ou null * **totalUsd** : Total USD dépensé sur ce modèle * **totalDiem** : Total DIEM dépensé sur ce modèle * **totalUnits** : Unités totales consommées pour ce modèle * **breakdown** : Tableau des ventilations d'utilisation par type (uniquement présent si plusieurs types). Chaque entrée contient : * **type** : Type de token (par exemple "Input", "Output", "Cache Read", "Cache Write") * **usd** : Montant en USD pour cette ventilation * **diem** : Montant en DIEM pour cette ventilation * **units** : Nombre d'unités pour cette ventilation ### byModelDaily Données de graphique quotidiennes pour les 8 meilleurs modèles. Chaque entrée contient une "date" (horodatage) plus les noms des modèles comme clés avec les valeurs d'utilisation DIEM. ### topModels Tableau des 8 meilleurs noms de modèles par utilisation, pour les légendes de graphique. ### byKey Ventilation de l'utilisation par clé API, triée par dépense totale (la plus élevée d'abord). * **apiKeyId** : L'ID de la clé API, ou null si l'utilisation provenait de l'application web * **description** : Description de la clé API ou "Web App" * **totalUsd** : Total USD dépensé via cette clé * **totalDiem** : Total DIEM dépensé via cette clé * **totalUnits** : Unités totales consommées via cette clé ### byKeyDaily Données de graphique quotidiennes pour les 8 meilleures clés API. Chaque entrée contient une "date" (horodatage) plus les descriptions de clé comme clés avec les valeurs d'utilisation DIEM. ### topKeyNames Tableau des 8 meilleures descriptions de clé API par utilisation, pour les légendes de graphique. ## Exemple d'utilisation ```bash theme={null} # Obtenir les analyses d'utilisation des 7 derniers jours (par défaut) curl -X GET "https://api.venice.ai/api/v1/billing/usage-analytics" \ -H "Authorization: Bearer YOUR_API_KEY" # Obtenir les analyses d'utilisation des 30 derniers jours curl -X GET "https://api.venice.ai/api/v1/billing/usage-analytics?lookback=30d" \ -H "Authorization: Bearer YOUR_API_KEY" # Obtenir les analyses d'utilisation pour une plage de dates spécifique curl -X GET "https://api.venice.ai/api/v1/billing/usage-analytics?startDate=2024-01-01&endDate=2024-01-31" \ -H "Authorization: Bearer YOUR_API_KEY" ``` ## OpenAPI ````yaml GET /billing/usage-analytics openapi: 3.0.0 info: description: The Venice.ai API. termsOfService: https://venice.ai/legal/tos title: Venice.ai API version: '20260622.204854' x-guidance: >- Venice.ai is an OpenAI-compatible inference API supporting text, image, audio, and video generation. **Authentication options:** - API Key: Use Bearer token in Authorization header - x402 Wallet: Use USDC credits via EVM or Solana wallet (no account required) **For x402 wallet access:** 1. POST /x402/top-up without headers to get payment requirements 2. Choose one of the returned Base or Solana payment options and sign a USDC payment using the x402 SDK 3. POST /x402/top-up with PAYMENT-SIGNATURE header to add credits 4. Call any inference endpoint with SIGN-IN-WITH-X header **Pricing:** Prepaid credits consumed per request. Check /models for available models and their capabilities. servers: - url: https://api.venice.ai/api/v1 security: - BearerAuth: [] tags: - description: >- Generate speech/audio, transcribe audio, and manage asynchronous audio generation jobs. name: Audio - description: >- Given a list of messages comprising a conversation, the model will return a response. Supports multimodal inputs including text, images, audio (input_audio), and video (video_url) for compatible models. name: Chat - description: List and describe the various models available in the API. name: Models - description: Generate and manipulate images using AI models. name: Image - description: Generate videos using AI models. name: Video - description: List and retrieve character information for use in completions. name: Characters - description: >- Billing and usage analytics. **Beta**: This API is currently in beta and may be unstable. Endpoints, request/response schemas, and behavior may change without notice. name: Billing - description: Proxy JSON-RPC requests to blockchain nodes. Billed per credit. name: Crypto RPC - description: >- Wallet-based API access using the x402 protocol. No API key required — authenticate with an EVM or Solana wallet. **How it works:** 1. **Authenticate** — Send a `SIGN-IN-WITH-X` header (base64-encoded signed SIWX payload) with any request. EVM wallets sign an EIP-4361 SIWE message; Solana wallets sign the Solana SIWX message with Ed25519. See the `siwx` security scheme for the exact format. 2. **Top up** — `POST /x402/top-up` without a payment header returns an `accepts` array with Base and Solana USDC payment options. Choose one entry, sign it using the x402 SDK (`npm install x402`), and re-submit with the `PAYMENT-SIGNATURE` header (the legacy `X-402-Payment` and `X-PAYMENT` names are also accepted). 3. **Use any endpoint** — All inference endpoints (chat, image, audio, video, embeddings) accept `siwx` as an alternative to `BearerAuth`. Charges are deducted from your USDC credit balance. 4. **Monitor balance** — `GET /x402/balance/{walletAddress}` returns your current balance. The `X-Balance-Remaining` response header on inference calls also reports it. **Quick start (5 lines):** ``` import { VeniceClient } from '@venice-ai/x402-client' const venice = new VeniceClient(process.env.WALLET_KEY) await venice.topUp(10) // $10 USDC on a supported x402 rail const res = await venice.chat({ model: 'zai-org-glm-5-1', messages: [{ role: 'user', content: 'Hello!' }] }) ``` **Payment:** USDC on Base (chain ID 8453) or Solana mainnet. Minimum top-up: $5. Alternatively, stake DIEM tokens for daily credits (1 DIEM = $1/day). name: x402 externalDocs: description: Venice.ai API documentation url: https://docs.venice.ai paths: /billing/usage-analytics: get: tags: - Billing summary: /api/v1/billing/usage-analytics description: >- **Beta**: This endpoint is currently in beta and may be unstable. Request/response schemas and behavior may change without notice. Get aggregated usage analytics for the authenticated user with breakdowns by date, model, and API key. This endpoint provides summary views of your API usage, ideal for dashboards and usage monitoring. Data is cached for 10 minutes. operationId: getBillingUsageAnalytics parameters: - schema: type: string pattern: ^[1-9]\d*d$ default: 7d description: >- Lookback period for usage data. Format: number followed by "d" (e.g., "7d", "30d"). Maximum: 90d example: 7d required: false name: lookback in: query - schema: type: string pattern: ^\d{4}-\d{2}-\d{2}$ description: >- Start date for filtering records (YYYY-MM-DD). If provided, endDate is also required. example: '2024-01-01T00:00:00.000Z' required: false name: startDate in: query - schema: type: string pattern: ^\d{4}-\d{2}-\d{2}$ description: >- End date for filtering records (YYYY-MM-DD). If provided, startDate is also required. example: '2024-01-31T00:00:00.000Z' required: false name: endDate in: query responses: '200': description: Successful response with aggregated usage analytics content: application/json: schema: type: object properties: lookback: type: string description: >- The lookback period used for the query. Either "Nd" format or "startDate:endDate" format. example: 7d byDate: type: array items: type: object properties: date: type: string description: Date in YYYY-MM-DD format example: '2024-01-15T00:00:00.000Z' USD: type: number description: Total USD usage for this date DIEM: type: number description: Total DIEM usage for this date required: - date - USD - DIEM description: Daily usage totals for the requested period byModel: type: array items: type: object properties: modelName: type: string description: Display name of the model example: GLM 5.1 unitType: type: string description: >- Type of units (tokens, images, chars, minutes, seconds) example: tokens modelType: type: string nullable: true description: Type of model (LLM, IMAGE, TTS, ASR, VIDEO) example: LLM totalUsd: type: number description: Total USD usage for this model totalDiem: type: number description: Total DIEM usage for this model totalUnits: type: number description: Total units consumed for this model breakdown: type: array items: type: object properties: type: type: string description: >- Token type (e.g., "Input", "Output", "Cache Read", "Cache Write") usd: type: number description: USD amount for this breakdown diem: type: number description: DIEM amount for this breakdown units: type: number description: Number of units for this breakdown required: - type - usd - diem - units description: >- Breakdown by token type (only present if multiple types) required: - modelName - unitType - modelType - totalUsd - totalDiem - totalUnits description: >- Usage breakdown by model, sorted by total spend (highest first) byModelDaily: type: array items: type: object additionalProperties: type: number description: >- Daily chart data for top 8 models. Each entry has "date" (timestamp) plus model names as keys. topModels: type: array items: type: string description: Names of the top 8 models by usage (for chart legends) byKey: type: array items: type: object properties: apiKeyId: type: string nullable: true description: API key ID, or null if usage was from web app description: type: string description: API key description or "Web App" example: My Production Key totalUsd: type: number description: Total USD usage for this key totalDiem: type: number description: Total DIEM usage for this key totalUnits: type: number description: Total units consumed for this key required: - apiKeyId - description - totalUsd - totalDiem - totalUnits description: >- Usage breakdown by API key, sorted by total spend (highest first) byKeyDaily: type: array items: type: object additionalProperties: type: number description: >- Daily chart data for top 8 API keys. Each entry has "date" (timestamp) plus key descriptions as keys. topKeyNames: type: array items: type: string description: >- Descriptions of the top 8 API keys by usage (for chart legends) required: - lookback - byDate - byModel - byModelDaily - topModels - byKey - byKeyDaily - topKeyNames additionalProperties: false description: >- Aggregated usage analytics response with breakdowns by date, model, and API key example: lookback: 7d byDate: - date: '2024-01-15T00:00:00.000Z' USD: 0.5 DIEM: 10.25 - date: '2024-01-14T00:00:00.000Z' USD: 0.3 DIEM: 8.75 byModel: - modelName: GLM 5.1 unitType: tokens modelType: LLM totalUsd: 0.4 totalDiem: 12.5 totalUnits: 50000 breakdown: - type: Output usd: 0.3 diem: 10 units: 35000 - type: Input usd: 0.1 diem: 2.5 units: 15000 byModelDaily: - date: 1705276800000 GLM 5.1: 5.5 Kimi K2.6: 3.2 topModels: - GLM 5.1 - Kimi K2.6 byKey: - apiKeyId: key_abc123 description: Production Key totalUsd: 0.8 totalDiem: 15 totalUnits: 75000 - apiKeyId: null description: Web App totalUsd: 0 totalDiem: 4 totalUnits: 25000 byKeyDaily: - date: 1705276800000 Production Key: 8.5 Web App: 2 topKeyNames: - Production Key - Web App '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/DetailedError' '401': description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/StandardError' '500': description: Inference processing failed content: application/json: schema: $ref: '#/components/schemas/StandardError' '504': description: Query timed out - try reducing the lookback period content: application/json: schema: properties: error: description: Error message indicating query timeout type: string type: object components: schemas: DetailedError: type: object properties: details: type: object properties: {} description: Details about the incorrect input example: _errors: [] field: _errors: - Field is required error: type: string description: A description of the error required: - error StandardError: type: object properties: error: type: string description: A description of the error required: - error securitySchemes: BearerAuth: bearerFormat: JWT scheme: bearer type: http ````