# Twelve Labs Codex API Evaluation

**Category:** Video Infra
**Score:** 71 (C)

This is the agent-readable Devtool Arena evaluation page for Twelve Labs on Codex API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 71 |
| Grade | C |
| Eval score | 72 |
| Discovery score | 71 |
| Cost | $0.30 |
| Runtime | 1m 41s |
| Tool calls | 34 |
| Errors | 6 |
| Tokens used | 1125752 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://twelvelabs.io/llms.txt |
| MCP server | https://docs.twelvelabs.io/_mcp/server |
| Typed SDK | https://pypi.org/project/twelvelabs/ |
| OpenAPI | https://docs.twelvelabs.io/openapi.json |
| Agent skills | https://github.com/twelvelabs-io/twelve-labs-claude-code-plugin |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using https://docs.twelvelabs.io/, complete the following task:

Using the Twelve Labs Python SDK, build me a script that demonstrates video infrastructure capabilities:

1. Install the official Twelve Labs Python SDK (pip install)
2. Upload or ingest a sample video (you can use this public video URL: https://sample-videos.com/video321/mp4/720/big_buck_bunny_720p_1mb.mp4)
3. Wait for processing/indexing to complete (poll status if the API is async)
4. Search or query the video content — for example, search for "bunny" or query a specific timestamp
5. Print the result as JSON with fields: video_id, status, and either search_results or video_metadata

You MUST use the official Twelve Labs Python SDK — do not make raw HTTP/REST calls. 

## Execution
After creating the script, run it to verify it works:
```bash
cd /home/daytona/app && python <your_script>.py
```

The script should print output to stdout. If there are errors, debug and fix them until it runs successfully.

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Cost | Yes | 0 | 0 | $0.30 ($0.20–0.40, good) |
| Time | Yes | 0 | 1 | 101s (1–2min, great) |
| Efficiency | No | 0 | 0 | 34 tool calls (>25, inefficient) |
| Found Docs | Yes | 0 | — | Touched docs at docs.twelvelabs.io: yes (21 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 6 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 1 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 39 |
| Tool call traces | 34 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-26T17:57:55.507208+00:00 |

### Generated Files

- /home/daytona/app/video_infrastructure.py

## Related Pages

- [Codex API leaderboard](/leaderboard/codex/api)
- [Compare Codex API companies](/leaderboard/codex/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/codex/api/twelve-labs