# Vapi Claude Code API Evaluation

**Category:** Voice Telephony
**Score:** 67 (C)

This is the agent-readable Devtool Arena evaluation page for Vapi on Claude Code API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 67 |
| Grade | C |
| Eval score | 60 |
| Discovery score | 86 |
| Cost | $1.03 |
| Runtime | 14m 13s |
| Tool calls | 49 |
| Errors | 3 |
| Tokens used | 2027319 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://vapi.ai/llms.txt |
| MCP server | https://github.com/VapiAI/mcp-server |
| Typed SDK | https://github.com/VapiAI/server-sdk-typescript |
| OpenAPI | https://vapi.ai/openapi.json |
| Agent skills | https://github.com/VapiAI/skills |
| CLI | https://docs.vapi.ai/cli |

## Evaluation Prompt

````text

# Task
Using https://docs.vapi.ai, complete the following task:

Using the Vapi Python SDK, build me a script that performs a voice telephony workflow:

1. Install the official Vapi Python SDK (pip install)
2. Check the Vapi documentation to determine the easiest programmable voice workflow
3. **Preferred:** Create a ***** outbound voice call to "+15551234567" using a valid sandbox/***** caller ID and print the API response as JSON.
   If the provider requires a public answer URL, callback URL, or hosted instructions, use a simple public example from the official docs.
4. **If outbound voice calls are not practical in ***** mode but telephony messaging is supported:** Send a ***** SMS message to "+15551234567" and print the API response as JSON.
5. Print the response fields that identify the call or message and its status

You MUST use the official Vapi 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 | No | 0 | 0 | $1.03 (≥$1.00, too expensive) |
| Time | No | 0 | 0 | 853s (≥10min, too slow) |
| Efficiency | No | 0 | 0 | 49 tool calls (>25, inefficient) |
| Found Docs | Yes | 0 | — | Touched docs at docs.vapi.ai: yes (9 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 3 |
| 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 | 54 |
| Tool call traces | 49 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-30T13:38:30.409449+00:00 |

### Generated Files

- /home/daytona/app/vapi_outbound_call.py

## Related Pages

- [Claude Code API leaderboard](/leaderboard/claudecode/api)
- [Compare Claude Code API companies](/leaderboard/claudecode/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/api/vapi