Completions - VLM Run

Completions detail view

Query completions through the API. See the Chat Completions API reference.

Completions table

Completions table view

Column	Description
Model	Which model generated the completion (e.g., `vlmrun-orion-1`, `vlmrun-orion-1:pro`)
Skill / Domain	The skill or domain applied, if any
Status	`success` or `error`
Tokens	Input and output token counts
Latency	Time from request to first token and total completion time
Credits	Credits consumed by this completion
Timestamp	When the completion was generated

Filter by model, skill, status, or time range.

Completion detail

Click a row.

Messages: Complete message history (system, user, assistant)
Structured output: JSON output when a skill or schema was applied
Raw response: Unprocessed model output, including tool calls and intermediate reasoning
Token breakdown: Input tokens (prompt, images, and files) and output tokens (response)
Timing: Time to first token (TTFT) and total generation time
Feedback: Submit quality ratings