deeprelay models get

Show details for one model (id or alias, optionally :economy)

Synopsis

Shows the full record for a single model — id, modality, tier, context length, per-1M-token pricing (input, cached input where the model publishes a cache-hit rate, and output), aliases, supported parameters, and status. A model the flat subscription tier covers also carries a Plan row (plan_covered in JSON); models without it bill pay-as-you-go only. Accepts a canonical id or any alias (plus a :economy suffix for a model that lists an economy tier; none does today). Requires a key with serverless:read (or full_access).

A chat model whose open weights the latest public fingerprint run verified also shows Weights verified (the date and the weights repo) and Verification run (the public GitHub Actions run behind the finding); an unverified model has neither row, and -o json carries the object as weights_verification only when present.

Examples

deeprelay models get deeprelay/qwen3-embedding-8b
deeprelay models get bge-large                          # alias resolves to the canonical id

deeprelay models get <model> [flags]

Options

  -h, --help   help for get

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 models - Browse the serverless inference model catalog