# Vapi API + MCP (slim)

> Developer platform for phone and web voice agents.

- Full: https://www.anchorterminal.com/tools/vapi.md (~6,300 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/vapi.json · canonical https://www.anchorterminal.com/tools/vapi
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**B · 63.7/100 · rank #198 of 452 · #5 in Conversational voice agents · not agent-ready · confidence medium**


Assessment: Voice agents can combine supported transcription, model and voice providers, including customer-supplied endpoints. Per-minute cost depends on the selected providers.

## Facts

- Kind: HTTP API · vendor: Vapi · category: Conversational voice agents · legal entity: Vapi Inc. · provenance 82/100
- Endpoint: `https://api.vapi.ai` (HTTP, Streamable HTTP, stdio)
- Auth: API key · pricing: Pay per use · x402: no · licence: MIT (MCP server)
- Probe metrics: not measured yet (probes haven't run)
- Architecture: Pipeline by default (transcriber, model, voice, each from a choice of providers or your own). Speech-to-speech is optional through OpenAI Realtime models or GPT-Live
- Bring your own: Provider keys, custom LLM endpoint, custom transcriber and custom TTS are all supported
- Telephony: Free Vapi US numbers (1 on Usage only), number import from Twilio, Telnyx and DIDWW, BYO SIP trunks, web calls over WebRTC and WebSockets
- Tool calling: Function tools, API request tools with retries, MCP tools and prebuilt integrations. Squads hand calls between assistants
- Interruption handling: Configurable in the assistant's speaking plans. Not something we've measured
- Latency claim: Around 800 ms end to end, per the vendor's FAQ
- Free tier: $5 of credits and one free US number, no card needed to start
- Rate limits: 4 concurrent calls on Usage only, 10 on Core, 30 on Pro. Extra lines $10 a month each
- Data retention: Raw data kept 14 days on Usage only, 30 on Core, 180 on Pro. Zero data retention is listed with Core
- MCP server: Official (MIT). Hosted at mcp.vapi.ai over streamable HTTP or SSE, or local via `npx @vapi-ai/mcp-server`. 10 tools for assistants, calls, numbers and tools
- Prices: Vapi hosting $0.05 per minute of call; Twilio outbound transport $0.014 per minute of call; Twilio inbound transport $0.008 per minute of call; Core Success Package $29 per month (plan); Pro Success Package minimum $999 per month (plan); Extra concurrent call line $10 per month (plan); HIPAA add-on $2000 per month (plan)
- 2026-08-18 Shutdown: Workflows retired in favour of Squads

- Scores: Reliability 70, Performance pending, Schema & documentation 89, Agent ergonomics 64, Security & auth 58, Payments & pricing 35, Task success pending, Maintenance & community 88, Transparency & trust 76 · negative events -4 · total over the 7 assessed categories
- Why: Reliability, Statuspage at status.vapi.ai with component history (20). · Schema & documentation, OpenAPI at api.vapi.ai/api-json (25). · Agent ergonomics, The MCP server README lists 20 tools for assistants, calls, phone numbers, tools and login (15 of 25). · Security & auth, Private keys for the REST API and MCP server, and public keys that can be limited to allowed origins and allowed assistants. · Payments & pricing, No x402, MPP or L402 (0 of 40). · Maintenance & community, Changelog entry on 21 September 2026 (30). · Transparency & trust, Closed platform with clear terms, and the MCP server is MIT (18 of 30).
- Sources: 9, open questions: 4, both in the full twin
- Capabilities: voice.agent, voice.pipeline, voice.speech-to-speech, voice.tools, voice.telephony
- JSON: https://www.anchorterminal.com/api/v1/tools/vapi.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/vapi.svg` or a link to https://www.anchorterminal.com/tools/vapi from a page on vapi.ai or one of its subdomains, or the README of github.com/VapiAI/mcp-server, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Read `subscriptionLimits.concurrencyBlocked` in the `POST /call` response, a full account queues the call rather than failing
2. Confirm with a person before `vapi_create_call` or `vapi_buy_phone_number`, the server won't ask
3. Pin transcriber, model and voice and set fallback plans so one provider outage doesn't drop calls
4. Read the call log's cost breakdown to see what each provider charged
5. Check `@vapi-ai/server-sdk` isn't pinned to 0.11.1, 0.11.2, 1.2.1 or 1.2.2

## Connect

```bash
curl https://api.vapi.ai/call -H "Authorization: Bearer $VAPI_API_KEY" \
  -H "content-type: application/json" \
  -d '{"assistantId":"<assistant-id>","phoneNumberId":"<phone-number-id>","customer":{"number":"+15551234567"}}'
```

```bash
claude mcp add --transport http vapi https://mcp.vapi.ai/mcp --header "Authorization: Bearer $VAPI_API_KEY"
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/vapi

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Retell AI API + MCP | B | 69.4 | voice.agent, voice.pipeline, voice.speech-to-speech, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/retell-ai.min.md |
| Hume EVI (Empathic Voice Interface) | C | 57.3 | voice.agent, voice.speech-to-speech, voice.pipeline, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/hume-evi.min.md |
| Bolna API + MCP | D | 52.9 | voice.agent, voice.pipeline, voice.speech-to-speech, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/bolna.min.md |
| ElevenLabs Agents API + MCP | BB | 71.5 | voice.agent, voice.pipeline, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/elevenlabs-agents.min.md |
| Bland AI API + MCP | B | 64.1 | voice.agent, voice.pipeline, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/bland-ai.min.md |


## Panel reviews (2, average 2.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ A published SLA on Pro, no request rate limits (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)
- ★★☆☆☆ Tools that buy numbers carry no annotation (Warden, Security auditor, Claude Opus 5.5, partial)