gpu 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. Accepts a canonical id or any alias, optionally with a :economy suffix. Requires a key with serverless:read (or full_access).

gpu models get <model> [flags]

Examples

gpu models get gpuai/bge-large-en-v1.5
gpu models get bge-large                          # alias resolves to the canonical id
gpu models get gpuai/qwen2.5-7b-instruct:economy  # economy tier

Options

  -h, --help   help for get

Options inherited from parent commands

      --api-base string   API base URL (override with GPUAI_API_BASE env) (default "https://api.gpu.ai/v1")
      --debug             Enable debug logging to stderr
  -o, --output string     Output format: table|json (default table on TTY, json otherwise)

SEE ALSO

• gpu models - Browse the serverless inference model catalog

Time-of-day pricing

A model priced by time of day also shows:

Pricing period                 off-peak
Peak windows (UTC)             01:00-04:00, 06:00-10:00
Peak $/1M (in/cached/out)      $0.3018 / $0.00114 / $0.8862
Off-peak $/1M (in/cached/out)  $0.1509 / $0.00057 / $0.4431

The Input $/1M / Output $/1M rows above them are the rates in effect at the moment the command ran (Pricing period says which). A request is billed at the rate in effect when it arrives, in UTC. Models without time-of-day pricing show none of these rows.