> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vlm.run/llms.txt
> Use this file to discover all available pages before exploring further.

# Completions

> Review model completions, token usage, and response quality on the VLM Run platform

Track chat completion requests made to the VLM Run platform, with details like model, token usage, status, and credit cost. Review outputs to understand how your visual agents are responding.

<div className="platform-figure">
  <img src="https://mintcdn.com/autonomiai/31N4NFzIelpYJkPB/images/platform-completions-group11.png?fit=max&auto=format&n=31N4NFzIelpYJkPB&q=85&s=6232c3e824cc36e238d1fc90d8b649ab" alt="Completions detail view" width="2712" height="1512" data-path="images/platform-completions-group11.png" />
</div>

<Tip>Everything you see here is also available through the API. See the [Chat Completions API reference](/api-reference/v1/post-chat-completions) to query completions programmatically.</Tip>

## Completion details

Click on any completion to see the full chain of inputs and outputs rendered in a clean, easy-to-read view - useful for both reviewing results and debugging issues.

## Completions table

<div className="platform-figure">
  <img src="https://mintcdn.com/autonomiai/31N4NFzIelpYJkPB/images/platform-completions-group10.png?fit=max&auto=format&n=31N4NFzIelpYJkPB&q=85&s=588f4cee7006cb1f3ae297f61736470f" alt="Completions table view" width="2712" height="1506" data-path="images/platform-completions-group10.png" />
</div>

Each row represents one completion with:

| 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 to narrow results.

## Completion detail

Click any row to inspect the full completion:

* **Messages**: The complete message history (system, user, assistant) that produced this completion
* **Structured output**: The JSON output if a skill or schema was applied
* **Raw response**: The unprocessed model output, including any tool calls or intermediate reasoning
* **Token breakdown**: Input tokens (prompt + images/files) vs. output tokens (response)
* **Timing**: Time to first token (TTFT) and total generation time
* **Feedback**: Submit quality ratings to build a feedback loop for model improvement

## What to look for

<AccordionGroup>
  <Accordion title="Output quality" icon="star">
    Review the structured output against expectations. Are fields populated correctly? Are there hallucinations or missing data? Use the feedback button to flag issues.
  </Accordion>

  <Accordion title="Token efficiency" icon="gauge">
    Compare input and output token counts across completions. If a skill is generating unexpectedly large outputs, the schema or prompt may need tightening.
  </Accordion>

  <Accordion title="Model comparison" icon="scale-balanced">
    Filter by model to compare how different models handle the same skill. Look at output quality, latency, and cost to choose the best model for your use case.
  </Accordion>

  <Accordion title="Latency patterns" icon="clock">
    Sort by latency to identify slow completions. Cross-reference with token counts. High token completions naturally take longer, but unexpectedly slow low-token completions may indicate an issue.
  </Accordion>
</AccordionGroup>

## Related Pages

<CardGroup cols={2}>
  <Card title="Observe Overview" icon="chart-line" href="/platform/observe/overview">
    Return to the observability dashboard.
  </Card>

  <Card title="Requests" icon="arrow-right-arrow-left" href="/platform/observe/requests">
    View the underlying API requests for each completion.
  </Card>

  <Card title="Chat Completions API" icon="server" href="/api-reference/v1/post-chat-completions">
    Reference for the chat completions endpoint.
  </Card>

  <Card title="Feedback" icon="thumbs-up" href="/guides/feedback">
    Learn how feedback improves model outputs over time.
  </Card>
</CardGroup>