deeprelay usage

Show serverless inference usage (tokens and cost)

Synopsis

Shows inference token/cost rollups from GET /v1/usage. Scope the query with --modality and/or --model — at least one is required (without a filter the usage endpoint returns GPU-instance usage, which this command does not render). Requires a key with the billing:read scope.

Examples

# Chat token usage by day (default range: last 30 days)
deeprelay usage --modality chat

# A single model, monthly buckets
deeprelay usage --model deeprelay/deepseek-v4-flash --bucket month

# An explicit date range
deeprelay usage --modality chat --start 2026-05-01T00:00:00Z --end 2026-05-29T00:00:00Z

deeprelay usage [flags]

Options

      --bucket string     Aggregation bucket: hour | day | week | month (default "day")
      --end string        Range end (RFC3339)
  -h, --help              help for usage
      --modality string   Filter by modality: chat | image | video | embedding
      --model string      Filter by model id
      --start string      Range start (RFC3339)

Options inherited from parent commands

      --api-base string   API base URL (override with DEEPRELAY_API_BASE env) (default "https://api.deeprelay.ai/v1")
      --debug             Enable debug logging to stderr
      --no-preflight      Skip the plan/credit check before inference requests (override with DEEPRELAY_NO_PREFLIGHT env)
  -o, --output string     Output format: table|json (default table on TTY, json otherwise) (default "table")

SEE ALSO

• deeprelay - deeprelay command-line interface