> ## Documentation Index > Fetch the complete documentation index at: /docs/llms.txt > Use this file to discover all available pages before exploring further. # Retrieve a budget > Retrieves the metadata for an existing budget by its unique identifier. Returns `NotFound` when the budget does not exist in the caller's workspace. Requires a Management Key with the Budgets permission; project-scoped API keys cannot manage budgets. > [!NOTE] > > **Related guide**: Budgets guide. See the [Budgets guide](/docs/ai-gateway/budgets.md) for a walkthrough with examples. ## OpenAPI ````yaml get /v2/budgets/{budget_id} openapi: 3.1.0 info: title: Toqan Router API version: '2.0' description: Toqan Router API documentation servers: - url: https://router.toqan.ai/eu description: Frankfurt (Europe) - url: https://router.toqan.ai/br description: São Paulo (Brazil) security: - ApiKey: [] tags: - description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. name: API keys - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: Telemetry description: >- Unified query envelope for traces, metrics, and logs. One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. - name: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. - name: Views description: Saved filters and columns for workspace observability pages. - description: List models available through the AI Router. name: Models - name: Alerts description: >- Alerts evaluate a telemetry metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the Toqan Router model catalog: every model Toqan Router offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Monitors description: >- Monitors are custom observability dashboards for traces, runtime metrics, and logs. Each monitor holds widgets that chart one telemetry query. List the metrics, operations, and dimensions available to your workspace with `GET /v3/telemetry/capabilities`, or start from a preset with `GET /v2/monitors/presets`. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Threads description: Threads group related trace invocations and their aggregate usage - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Responses - name: Embeddings - description: Beta. Run typed classification questions against a classify model. name: Classify - description: Beta. Run classification decisions with the classify contract. name: Decisions - description: >- Run large offline workloads as JSONL batches and download OpenAI-compatible result files. name: Batches paths: /v2/budgets/{budget_id}: get: tags: - Budgets summary: Retrieve a budget description: >- Retrieves the metadata for an existing budget by its unique identifier. Returns `NotFound` when the budget does not exist in the caller's workspace. Requires a Management Key with the Budgets permission; project-scoped API keys cannot manage budgets. operationId: BudgetGet parameters: - name: budget_id in: path description: Budget id to retrieve. required: true schema: type: string responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/GetBudgetResponse' '401': description: >- Authentication required. See https://router.toqan.ai/docs/reference/errors for the error codes. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: >- Not permitted for this key, project or workspace. See https://router.toqan.ai/docs/reference/errors for the error codes. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - ApiKey: [] components: schemas: GetBudgetResponse: required: - budget type: object properties: budget: allOf: - $ref: '#/components/schemas/BudgetRestResponse' description: Requested budget. ErrorResponse: type: object properties: message: type: string description: Human-readable error message. code: type: integer description: Numeric error code, when one is available. details: type: array items: {} description: Additional error details, when the service reports any. required: - message BudgetRestResponse: required: - budgetId - limits - createdAt - updatedAt type: object properties: budgetId: type: string scope: allOf: - $ref: '#/components/schemas/BudgetScopeRestResponse' description: >- Scope the budget was created for, used to group and filter budgets in the console. Not used for matching: the `match` expression decides which requests a budget applies to. Unset for budgets created from a raw CEL expression ("custom"). match: allOf: - $ref: '#/components/schemas/BudgetMatch' description: |- The matching semantics of the budget. A budget applies to a request when `match.cel` evaluates to true against the request context. Creating a budget for a scope derives the expression for that scope (e.g. `provider == "openai"`); an empty expression matches every request in the workspace. limits: $ref: '#/components/schemas/BudgetLimitsRestResponse' rateLimit: $ref: '#/components/schemas/RateLimitRestResponse' isActive: type: boolean default: false expiresAt: type: string format: date-time createdAt: type: string format: date-time updatedAt: type: string format: date-time usage: allOf: - $ref: '#/components/schemas/BudgetUsage' description: |- Latest available consumption used for enforcement in the current period. This is not an exact billing ledger. Populated by read paths (Get / List); omitted on write responses (Create / Update / Reset) where it carries no signal. Absent or all-zero for a budget that has not been spent against in the current period. alerts: type: array items: $ref: '#/components/schemas/BudgetAlertRestResponse' description: Threshold notifications. Absent when the budget has none. description: Budget defines limits and matching rules used to govern consumption. BudgetScopeRestResponse: type: object properties: workspace: $ref: '#/components/schemas/WorkspaceBudgetScope' project: $ref: '#/components/schemas/ProjectBudgetScopeRestResponse' identity: $ref: '#/components/schemas/IdentityBudgetScopeRestResponse' apiKey: $ref: '#/components/schemas/ApiKeyBudgetScopeRestResponse' provider: $ref: '#/components/schemas/ProviderBudgetScope' model: $ref: '#/components/schemas/ModelBudgetScopeRestResponse' description: >- Closed oneof of workspace, project, identity, api_key, provider, or model. Exactly one variant must be set. BudgetMatch: type: object properties: cel: type: string description: >- CEL expression that decides whether a budget applies to a request. Available variables: `model`, `provider`, `model_id`, `api_key`, `identity`, `project`, `metadata` (map), `headers` (map, lowercase keys). Required unless the budget is created from a `scope`, and rejected on update when left empty. A workspace-wide budget stores an empty expression, which matches every request in the workspace. Expressions are syntax-validated at write time. BudgetLimitsRestResponse: type: object properties: period: $ref: '#/components/schemas/BudgetPeriod' amount: type: number format: double tokenLimit: type: number description: |- Token ceiling for the budget period. Token counts are whole numbers and stored as integers. format: double description: |- BudgetLimits is the per-period spend and token ceiling. At least one of `amount`, `token_limit`, or RateLimit.requests_per_minute MUST be set on a Budget; the API rejects a budget that sets none of the three. RateLimitRestResponse: type: object properties: requestsPerMinute: type: integer format: int32 description: |- Per-minute request ceiling applied to the requests this budget matches. BudgetUsage: type: object properties: amount: type: number format: double tokens: type: number description: Tokens accumulated in the current period. format: double requests: type: integer format: int32 description: |- BudgetUsage is the latest available current-period consumption used for budget enforcement, not an exact billing ledger. Each dimension is the consumed side of the matching limit dimension: `amount` is the accumulated cost in USD (vs limits.amount), `tokens` is the accumulated token count (vs limits.token_limit), and `requests` is the count in the rolling 60-second window (vs rate_limit.requests_per_minute). All three are explicit-presence so the triple is always emitted in full, zeros included — a never-spent budget serializes {amount:0, tokens:0, requests:0} rather than dropping its zero dimensions. BudgetAlertRestResponse: required: - thresholdPercent - notifierIds type: object properties: id: type: string description: >- Assigned by Toqan Router. Supply an existing id to edit that alert in place. thresholdPercent: type: integer description: Percentage of the dimension's limit at which the alert fires, 1–100. format: uint32 notifierIds: type: array items: type: string description: Must be workspace-scoped; project-scoped notifiers are rejected. dimension: $ref: '#/components/schemas/BudgetAlertDimension' description: Defaults to COST when unset. description: |- Notifies every listed notifier once current-period consumption on `dimension` reaches `threshold_percent` of the matching limit. Each alert fires at most once per period, re-arming on rollover or a limit change. The dimension must have a limit set, or the write is rejected. A TOKENS alert is rejected. WorkspaceBudgetScope: type: object properties: {} description: Workspace-wide ceiling. The implicit target is the caller's workspace. ProjectBudgetScopeRestResponse: type: object properties: projectId: type: string description: Per-project cap. IdentityBudgetScopeRestResponse: type: object properties: identityExternalId: type: string description: |- Per-identity cap. Keyed by the contact's external identifier so the scope is stable across imports. ApiKeyBudgetScopeRestResponse: type: object properties: apiKeyId: type: string description: |- Per-api-key cap. Replaces the legacy embedded `constraints.budget` associated with an API key. ProviderBudgetScope: type: object properties: provider: type: string description: |- Per-provider cap. The value is the provider identifier, for example "openai" or "anthropic". ModelBudgetScopeRestResponse: required: - modelId type: object properties: modelId: type: string description: |- Per-model cap. The value is the FULL model reference as callers send it ("openai/gpt-4o", or "workspaceKey@openai/gpt-4o" for private models). BudgetPeriod: type: string enum: - BUDGET_PERIOD_DAILY - BUDGET_PERIOD_WEEKLY - BUDGET_PERIOD_MONTHLY - BUDGET_PERIOD_YEARLY - BUDGET_PERIOD_ONE_TIME BudgetAlertDimension: type: string enum: - BUDGET_ALERT_DIMENSION_COST - BUDGET_ALERT_DIMENSION_TOKENS securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.