generated: '2026-07-19'
method: searched
source: https://glio.io/docs/getting-started
derived_from: openapi/glio-openapi-original.json
authentication:
  style: bearer
  header: 'Authorization: Bearer <api-key-or-jwt>'
  ref: authentication/glio-authentication.yml
async_workflow:
  pattern: create-job-poll-get-result
  create: POST /v1/jobs returns 202 with an id and status pending
  poll: GET /v1/jobs/{job_id} every 10-15 seconds until status is completed or failed
  terminal_states: [completed, failed]
pagination:
  style: offset
  params: [limit, offset]
  filters: [status]
  applies_to: GET /v1/jobs
idempotency:
  supported: false
  note: >-
    No idempotency-key header or parameter is documented in the OpenAPI or the
    docs. Job creation is not declared idempotent. No Idempotency pointer is
    wired for this provider.
versioning:
  scheme: uri-path
  current: v1
  ref: lifecycle/glio-lifecycle.yml
rate_limiting:
  signal: >-
    A 429 (rate limit exceeded) is defined for the synchronous LLM endpoints
    (/v1/chat/completions, /v1/embeddings). No numeric limits or rate-limit
    response headers are documented.
error_envelope:
  content_type: application/json
  rfc9457: false
  ref: errors/glio-problem-types.yml
openai_compatibility:
  note: >-
    /v1/chat/completions and /v1/embeddings follow the OpenAI request/response
    shape, so OpenAI SDKs can target api.glio.io by swapping the base URL and key.
billing:
  unit: GL token
  rate: 1 GL = $0.01 USD
  model: pay-per-use, no subscription, no minimum