specification: FinOps Framework
specificationVersion: '1.0'
schema: https://www.finops.org/framework/
provider: Exa
providerId: exa-ai
created: '2026-05-25'
modified: '2026-05-25'
reconciled: true
tags:
  - FinOps
  - Cost Management
  - FOCUS
  - AI
  - Search
description: FOCUS-aligned FinOps definition for the Exa API — request-based metering with per-result, per-page, per-enrichment, and per-effort-mode lanes. The Exa Team Management API exposes per-key usage so cost can be allocated by workload.
sources:
  - https://exa.ai/pricing
  - https://exa.ai/docs/reference/search-api-guide
  - https://exa.ai/docs/api-reference/openapi
alignedWith:
  framework: FinOps Foundation Framework
  frameworkUrl: https://www.finops.org/framework/
  dataSpec: FOCUS
  dataSpecVersion: '1.3'
  dataSpecUrl: https://focus.finops.org/focus-specification/v1-3/
publisherName: Exa
serviceCategory: AI and Machine Learning
billingModel:
  pricingCategory: Usage-Based
  billingFrequency: Monthly
  billingCurrency: USD
  chargeCategories:
    - Usage
    - Purchase
    - Credit
    - Adjustment
  primaryUnit: request
  secondaryUnits:
    - result
    - page
    - run
    - enrichment
    - call
focusColumns:
  ServiceName: Exa API
  ServiceCategory: AI and Machine Learning
  ProviderName: Exa
  PublisherName: Exa
  InvoiceIssuerName: Exa
  PricingCategory: Usage-Based
  PricingUnit: 1K requests
  BillingCurrency: USD
meters:
  - name: search_requests
    unit: request
    aggregation: sum
    dimensions:
      - api_key
      - endpoint
      - latency_tier
  - name: contents_pages
    unit: page
    aggregation: sum
    dimensions:
      - api_key
      - content_type
  - name: deep_search_requests
    unit: request
    aggregation: sum
    dimensions:
      - api_key
      - effort
  - name: research_tasks
    unit: task
    aggregation: sum
    dimensions:
      - api_key
      - depth
  - name: monitor_runs
    unit: run
    aggregation: sum
    dimensions:
      - api_key
      - monitor_id
  - name: agent_runs
    unit: run
    aggregation: sum
    dimensions:
      - api_key
      - effort
  - name: enrichments
    unit: enrichment
    aggregation: sum
    dimensions:
      - api_key
      - type
allocation:
  primaryKey: api_key
  secondaryKey: workspace/team
  notes: Exa exposes per-key budget and rate-limit settings via the Team Management API, enabling cost allocation per workload, agent, or environment.
exportApi:
  description: The Team Management API surfaces per-key usage via GET /api-keys/{id}/usage, providing aggregated request, content, and enrichment counts for FinOps ingestion.
  endpoint: https://admin-api.exa.ai/team-management/api-keys/{id}/usage
optimizationLevers:
  - Use `numResults` <= 10 to avoid the $1 per 1,000 additional-result charge
  - Prefer `highlights` over full page contents for token-efficient retrieval (~90% token reduction per Exa docs)
  - Choose the right latency tier — fast (180ms), auto (~1s), or deep (~10s)
  - Choose the lowest effective effort mode on Agent runs — low ($0.025) vs x-high ($2.00) is an 80x difference
  - Cache `findSimilar` and Contents results for repeated queries in agent workflows