CH·02CLI reference

deeprelay models list

List inference models

Synopsis

Lists the serverless inference catalog. Each model appears once per available tier: serverless models use the bare id, economy models the :economy-suffixed id. Filter by modality (chat, image, video) or tier (serverless, economy). Requires a key with serverless:read (or full_access).

The table shows each chat model's per-1M-token rates: IN $/1M, CACHED $/1M (the discounted rate for the cache-hit part of a prompt — - when the model publishes no cached rate, in which case every prompt token bills at the input rate) and OUT $/1M. The PLAN column marks models the flat subscription tier covers (yes — requests can draw on a subscriber's monthly allowance; - — pay-as-you-go only). JSON output carries the exact figures (cached_input_per_1m_tokens_microcents, plan_covered).

Examples

# All models
deeprelay models list

# Just image models
deeprelay models list --modality image

# Economy-tier rows only
deeprelay models list --tier economy

# JSON for jq
deeprelay models list --modality chat --output json | jq '.[].id'

deeprelay models list [flags]

Options

  -h, --help              help for list
      --modality string   Filter by modality: chat | image | video | embedding
      --tier string       Filter by tier: serverless | economy

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")

Synopsis

Examples

Options

Options inherited from parent commands

SEE ALSO