{
  "data": {
    "a": {
      "slug": "deepgram-voice-agent",
      "name": "Deepgram Voice Agent API",
      "vendor": "Deepgram",
      "vendorUrl": "https://deepgram.com",
      "kind": "http-api",
      "category": "voice-agents",
      "summary": "One WebSocket that runs Deepgram STT (Flux or Nova-3), a managed or bring-your-own LLM and Deepgram or third-party TTS, with turn-taking, barge-in and function calling.",
      "url": "https://www.anchorterminal.com/tools/deepgram-voice-agent",
      "markdownUrl": "https://www.anchorterminal.com/tools/deepgram-voice-agent.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepgram-voice-agent.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepgram-voice-agent.json",
      "repo": "https://github.com/deepgram/deepgram-python-sdk",
      "license": "MIT (SDKs)",
      "transports": [
        "http",
        "streamable-http",
        "stdio",
        "sse"
      ],
      "remoteUrl": "https://agent.deepgram.com/v1/agent",
      "packages": [
        {
          "registry": "npm",
          "name": "@deepgram/sdk"
        },
        {
          "registry": "pypi",
          "name": "deepgram-sdk"
        },
        {
          "registry": "pypi",
          "name": "deepctl"
        }
      ],
      "auth": "api-key",
      "authNotes": "`Authorization: Token \u003ckey\u003e` header on REST and WebSocket calls. Short-lived JWTs (30-second TTL) from the token endpoint for browsers. The `dg` CLI MCP server uses `dg login` credentials or `DEEPGRAM_API_KEY`. The docs MCP needs no key. BYO LLM and TTS providers take their own keys in the `endpoint.headers` of the Settings message.",
      "pricing": "usage",
      "pricingNotes": "Billed per minute of WebSocket connection time. Standard $0.075 a minute pay as you go ($0.068 Growth), Standard with your own TTS $0.065, your own LLM and TTS $0.050 ($0.041 Growth). Advanced tier (larger LLMs such as GPT-5 or Claude Sonnet) $0.163, or $0.122 with your own TTS. $200 free credit with no card. Carrier costs are extra (https://deepgram.com/pricing).",
      "priceSummary": "Pay per use",
      "where": "both",
      "x402": {
        "level": "no",
        "evidence": "No x402 or machine payment in the docs or pricing. Card or prepaid credits only (checked 2026-09-30).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 468,
        "npmWeekly": 1123798,
        "pypiWeekly": 805026,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://developers.deepgram.com/docs/voice-agent",
      "llmsTxt": "https://developers.deepgram.com/llms.txt",
      "capabilities": [
        "voice.agent",
        "voice.pipeline",
        "voice.tools"
      ],
      "tags": [
        "hosted",
        "no-card",
        "closed-source",
        "python",
        "typescript",
        "llms-txt",
        "mcp",
        "streaming",
        "pipeline",
        "enterprise",
        "self-hosted"
      ],
      "lastRelease": "2026-09-30",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 68.4,
        "grade": "B",
        "agentReady": false,
        "rank": 126,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 3,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 67,
          "maintenance": 85,
          "payments": 40,
          "reliability": 55,
          "schema": 90,
          "security": 71,
          "transparency": 80
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": 0,
        "verdict": "$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card. No phone numbers or SIP, so you bridge Twilio or another carrier yourself.",
        "strengths": [
          "$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card",
          "AsyncAPI description of the agent socket plus a public OpenAPI file",
          "Role-based API keys with expiry and 30-second browser tokens",
          "SDKs in Python, JavaScript, Java, Go, C# and React, updated in September 2026",
          "Function-call hold that waits for a confirmed user turn before irreversible tools run"
        ],
        "weaknesses": [
          "No phone numbers or SIP, so you bridge Twilio or another carrier yourself",
          "Fifteen status incidents since July, four of them an hour or longer on parts the agent uses",
          "Call audio is kept for model improvement unless `mip_opt_out` is set",
          "No SLA terms on self-serve plans",
          "Sessions end at 2 hours"
        ],
        "agentNotes": [
          "Set `mip_opt_out` in the Settings message to keep call audio out of training",
          "Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed",
          "Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets",
          "Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026",
          "Mint browser tokens with `ttl_seconds`, not `ttl`, or they expire after 30 seconds"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 68.4
          }
        ],
        "editorialScores": {
          "ergonomics": 67,
          "maintenance": 85,
          "payments": 40,
          "reliability": 55,
          "schema": 90,
          "security": 71,
          "transparency": 70
        },
        "provenanceScore": 90
      },
      "connect": {
        "http": "curl https://agent.deepgram.com/v1/agent/settings/think/models \\\n  -H \"Authorization: Token $DEEPGRAM_API_KEY\"",
        "claudeCode": "claude mcp add deepgram-docs --transport http https://api.dx.deepgram.com/kapa/mcp",
        "config": {
          "mcpServers": {
            "deepgram": {
              "args": [
                "mcp"
              ],
              "command": "dg",
              "env": {
                "DEEPGRAM_API_KEY": "${DEEPGRAM_API_KEY}"
              }
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/voice.agent",
        "tool": "https://letme.dev/deepgram-voice-agent"
      },
      "sameCompany": [
        "deepgram-stt",
        "deepgram-tts"
      ],
      "area": "voice",
      "unitPrices": [
        {
          "item": "Standard",
          "unit": "call-minute",
          "usd": 0.075,
          "note": "pay as you go, Deepgram STT, managed LLM and TTS included, carrier extra"
        },
        {
          "item": "Standard with own TTS",
          "unit": "call-minute",
          "usd": 0.065
        },
        {
          "item": "Own LLM and TTS",
          "unit": "call-minute",
          "usd": 0.05,
          "note": "STT and orchestration only"
        },
        {
          "item": "Advanced",
          "unit": "call-minute",
          "usd": 0.163,
          "note": "larger LLMs, all-in except carrier"
        },
        {
          "item": "Advanced with own TTS",
          "unit": "call-minute",
          "usd": 0.122
        }
      ],
      "provenance": {
        "legalEntity": "Deepgram, Inc.",
        "domain": "deepgram.com",
        "domainRegistered": "2016-01-28",
        "endpointOnVendorDomain": true,
        "terms": "https://deepgram.com/terms",
        "privacy": "https://deepgram.com/privacy",
        "statusPage": "https://status.deepgram.com",
        "changelog": "https://developers.deepgram.com/changelog",
        "securityTxt": "none",
        "checked": "2026-09-30",
        "score": 90
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/deepgram-voice-agent.json",
      "live": {
        "slug": "deepgram-voice-agent",
        "probe": {
          "target": "https://agent.deepgram.com/v1/agent",
          "method": "get",
          "lastAt": "2026-10-05T01:43:36.300003942Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 575,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 571,
          "p95ms24h": 1595,
          "samples24h": 272,
          "samples30d": 1122,
          "days": [
            {
              "date": "2026-09-30",
              "probes": 35,
              "ok": 35
            },
            {
              "date": "2026-10-01",
              "probes": 276,
              "ok": 276
            },
            {
              "date": "2026-10-02",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-03",
              "probes": 271,
              "ok": 271
            },
            {
              "date": "2026-10-04",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-05",
              "probes": 20,
              "ok": 20
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.deepgram.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-05T01:46:28.094257561Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "deepgram/deepgram-python-sdk",
            "version": "v7.12.0",
            "released": "2026-10-02",
            "seenAt": "2026-10-04T16:25:23.342334431Z"
          },
          {
            "registry": "npm",
            "name": "@deepgram/sdk",
            "version": "5.14.0",
            "seenAt": "2026-10-04T16:25:21.087399088Z"
          },
          {
            "registry": "pypi",
            "name": "deepctl",
            "version": "0.3.1",
            "released": "2026-09-29",
            "seenAt": "2026-10-04T16:25:21.448203268Z"
          },
          {
            "registry": "pypi",
            "name": "deepgram-sdk",
            "version": "7.12.0",
            "released": "2026-10-02",
            "seenAt": "2026-10-04T16:25:21.33581967Z"
          }
        ],
        "githubStars": 468,
        "npmWeekly": 1147181,
        "pypiWeekly": 806541,
        "securityTxt": {
          "url": "https://deepgram.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-04T15:16:00.338324598Z"
        },
        "llmsTxt": {
          "url": "https://developers.deepgram.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:17:33.829894005Z"
        },
        "domain": {
          "domain": "deepgram.com",
          "registered": "2016-01-28",
          "source": "https://rdap.verisign.com/com/v1/domain/deepgram.com",
          "checkedAt": "2026-10-04T13:03:28.939824686Z"
        },
        "updatedAt": "2026-10-05T01:46:28.094257561Z"
      }
    },
    "b": {
      "slug": "vapi",
      "name": "Vapi API + MCP",
      "vendor": "Vapi",
      "vendorUrl": "https://vapi.ai",
      "kind": "http-api",
      "category": "voice-agents",
      "summary": "Developer platform for phone and web voice agents.",
      "url": "https://www.anchorterminal.com/tools/vapi",
      "markdownUrl": "https://www.anchorterminal.com/tools/vapi.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vapi.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vapi.json",
      "repo": "https://github.com/VapiAI/mcp-server",
      "license": "MIT (MCP server)",
      "transports": [
        "http",
        "streamable-http",
        "stdio"
      ],
      "remoteUrl": "https://api.vapi.ai",
      "packages": [
        {
          "registry": "npm",
          "name": "@vapi-ai/server-sdk"
        },
        {
          "registry": "npm",
          "name": "@vapi-ai/web"
        },
        {
          "registry": "pypi",
          "name": "vapi_server_sdk"
        },
        {
          "registry": "npm",
          "name": "@vapi-ai/mcp-server"
        }
      ],
      "auth": "api-key",
      "authNotes": "Private API key as a bearer token for the REST API and the hosted MCP server at `https://mcp.vapi.ai/mcp` (an SSE endpoint also exists). A separate public key is for browser calls with the Web SDK. The local MCP server reads `VAPI_TOKEN`.",
      "pricing": "usage",
      "pricingNotes": "Usage only is $0.05 a minute Vapi hosting, plus transcriber, model, voice and telephony at provider cost, prepaid with $5 of free credits to start. Vapi telephony, SIP, WebSockets and WebRTC transport are free, Twilio inbound runs $0.008 a minute and outbound $0.014. Success Packages add support and limits on top of usage, Core $29 a month and Pro 10 per cent of the hosting fee with a $999 monthly minimum. Add-ons include HIPAA at $2,000 a month and extra concurrent lines at $10 a line a month. The vendor's calculator puts 1,000 minutes with Deepgram, OpenAI and ElevenLabs at roughly $0.08 to $0.13 a minute all in (https://vapi.ai/pricing).",
      "priceSummary": "$29 / mo",
      "where": "both",
      "x402": {
        "level": "no",
        "evidence": "No x402 support in the docs, pricing page or MCP docs (checked 2026-09-30).",
        "endpoints": []
      },
      "toolCount": 20,
      "popularity": {
        "githubStars": 57,
        "npmWeekly": 177088,
        "pypiWeekly": 42248,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://docs.vapi.ai",
      "llmsTxt": "https://docs.vapi.ai/llms.txt",
      "openapi": "https://api.vapi.ai/api-json",
      "capabilities": [
        "voice.agent",
        "voice.pipeline",
        "voice.speech-to-speech",
        "voice.tools",
        "voice.telephony"
      ],
      "tags": [
        "hosted",
        "closed-source",
        "no-card",
        "mcp",
        "llms-txt",
        "openapi",
        "typescript",
        "python",
        "webhooks",
        "streaming",
        "pipeline",
        "speech-to-speech",
        "enterprise"
      ],
      "lastRelease": "2026-09-21",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 63.7,
        "grade": "B",
        "agentReady": false,
        "rank": 198,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 5,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 64,
          "maintenance": 88,
          "payments": 35,
          "reliability": 70,
          "schema": 89,
          "security": 58,
          "transparency": 76
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": -4,
        "negativeNotes": [
          "2026-06-03. A compromised developer GitHub token was used to push malicious code to Vapi repositories and publish four malicious `@vapi-ai/server-sdk` versions (0.11.1, 0.11.2, 1.2.1, 1.2.2) to npm. Vapi says they were removed within about three hours with zero downloads and no customer data exposed, and it published a write-up. Fixed and documented, so we deduct 4 of a possible 15 (https://vapi.ai/blog/our-response-to-june-3-supply-chain-incident)."
        ],
        "verdict": "Voice agents can combine supported transcription, model and voice providers, including customer-supplied endpoints. Per-minute cost depends on the selected providers.",
        "strengths": [
          "Any mix of transcriber, model and voice provider, or your own keys and endpoints",
          "OpenAPI file, llms.txt and a weekly changelog",
          "Public keys limited to allowed origins and assistants",
          "99 per cent uptime SLA on the Pro package, 99.9 per cent on Premier",
          "Versioned assistants and tools with draft and publish since August 2026"
        ],
        "weaknesses": [
          "Real per-minute cost depends on provider choices",
          "Usage only has 4 concurrent lines and 14 days of retention",
          "MCP tools that place calls or buy numbers carry no annotations",
          "No request rate limits or Retry-After guidance found",
          "Malicious SDK versions reached npm for about three hours on 3 June 2026"
        ],
        "agentNotes": [
          "Read `subscriptionLimits.concurrencyBlocked` in the `POST /call` response, a full account queues the call rather than failing",
          "Confirm with a person before `vapi_create_call` or `vapi_buy_phone_number`, the server won't ask",
          "Pin transcriber, model and voice and set fallback plans so one provider outage doesn't drop calls",
          "Read the call log's cost breakdown to see what each provider charged",
          "Check `@vapi-ai/server-sdk` isn't pinned to 0.11.1, 0.11.2, 1.2.1 or 1.2.2"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 2.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 63.7
          }
        ],
        "editorialScores": {
          "ergonomics": 64,
          "maintenance": 88,
          "payments": 35,
          "reliability": 70,
          "schema": 89,
          "security": 58,
          "transparency": 70
        },
        "provenanceScore": 82
      },
      "connect": {
        "http": "curl https://api.vapi.ai/call -H \"Authorization: Bearer $VAPI_API_KEY\" \\\n  -H \"content-type: application/json\" \\\n  -d '{\"assistantId\":\"\u003cassistant-id\u003e\",\"phoneNumberId\":\"\u003cphone-number-id\u003e\",\"customer\":{\"number\":\"+15551234567\"}}'",
        "claudeCode": "claude mcp add --transport http vapi https://mcp.vapi.ai/mcp --header \"Authorization: Bearer $VAPI_API_KEY\"",
        "config": {
          "mcpServers": {
            "vapi": {
              "args": [
                "-y",
                "@vapi-ai/mcp-server"
              ],
              "command": "npx",
              "env": {
                "VAPI_TOKEN": "${VAPI_API_KEY}"
              }
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/voice.agent",
        "tool": "https://letme.dev/vapi"
      },
      "area": "voice",
      "unitPrices": [
        {
          "item": "Vapi hosting",
          "unit": "call-minute",
          "usd": 0.05,
          "note": "platform fee only, transcriber, model, voice and telephony billed on top at cost"
        },
        {
          "item": "Twilio outbound transport",
          "unit": "call-minute",
          "usd": 0.014,
          "note": "US, passed through"
        },
        {
          "item": "Twilio inbound transport",
          "unit": "call-minute",
          "usd": 0.008,
          "note": "US, passed through"
        },
        {
          "item": "Core Success Package",
          "unit": "month",
          "usd": 29
        },
        {
          "item": "Pro Success Package minimum",
          "unit": "month",
          "usd": 999,
          "note": "10 per cent of hosting fees, $999 minimum"
        },
        {
          "item": "Extra concurrent call line",
          "unit": "month",
          "usd": 10
        },
        {
          "item": "HIPAA add-on",
          "unit": "month",
          "usd": 2000
        }
      ],
      "provenance": {
        "legalEntity": "Vapi Inc.",
        "domain": "vapi.ai",
        "domainRegistered": "2023-08-22",
        "endpointOnVendorDomain": true,
        "terms": "https://vapi.ai/terms-of-service",
        "privacy": "https://vapi.ai/privacy",
        "statusPage": "https://status.vapi.ai",
        "changelog": "https://docs.vapi.ai/changelog",
        "securityTxt": "none",
        "checked": "2026-10-01",
        "notes": [
          "The terms name Vapi Inc., a Delaware corporation."
        ],
        "score": 82
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/vapi.json",
      "live": {
        "slug": "vapi",
        "probe": {
          "target": "https://api.vapi.ai",
          "method": "get",
          "lastAt": "2026-10-05T01:43:47.533868254Z",
          "lastOk": true,
          "lastStatus": 200,
          "lastMs": 184,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 190,
          "p95ms24h": 551,
          "samples24h": 272,
          "samples30d": 1122,
          "days": [
            {
              "date": "2026-09-30",
              "probes": 35,
              "ok": 35
            },
            {
              "date": "2026-10-01",
              "probes": 276,
              "ok": 276
            },
            {
              "date": "2026-10-02",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-03",
              "probes": 271,
              "ok": 271
            },
            {
              "date": "2026-10-04",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-05",
              "probes": 20,
              "ok": 20
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.vapi.ai",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-10-04T21:40:32.91562276Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "VapiAI/mcp-server",
            "version": "v0.0.11",
            "released": "2026-08-14",
            "seenAt": "2026-10-04T16:43:12.477208468Z"
          },
          {
            "registry": "npm",
            "name": "@vapi-ai/mcp-server",
            "version": "0.0.11",
            "seenAt": "2026-10-04T16:43:10.657227109Z"
          },
          {
            "registry": "npm",
            "name": "@vapi-ai/server-sdk",
            "version": "2.0.1",
            "seenAt": "2026-10-04T16:43:06.847289486Z"
          },
          {
            "registry": "npm",
            "name": "@vapi-ai/web",
            "version": "2.7.1",
            "seenAt": "2026-10-04T16:43:09.259416721Z"
          },
          {
            "registry": "pypi",
            "name": "vapi_server_sdk",
            "version": "1.11.1",
            "released": "2026-05-20",
            "seenAt": "2026-10-04T16:43:10.468923211Z"
          }
        ],
        "githubStars": 57,
        "npmWeekly": 205182,
        "pypiWeekly": 39699,
        "securityTxt": {
          "url": "https://vapi.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-04T15:15:46.43020372Z"
        },
        "llmsTxt": {
          "url": "https://docs.vapi.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:18:23.657652287Z"
        },
        "domain": {
          "domain": "vapi.ai",
          "registered": "2023-08-22",
          "source": "https://rdap.identitydigital.services/rdap/domain/vapi.ai",
          "checkedAt": "2026-10-04T13:10:12.103273987Z"
        },
        "pages": [
          {
            "url": "https://docs.vapi.ai/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-04T15:44:13.606342765Z",
            "changedAt": "2026-10-03T15:32:20.588337898Z",
            "fingerprint": "ec991822798a"
          },
          {
            "url": "https://docs.vapi.ai/whats-new",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-01T13:13:04.652536748Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "8b20b96ab7a4"
          },
          {
            "url": "https://docs.vapi.ai/workflows/legacy-migration",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-10-04T15:44:25.802628589Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "9f62a32477a4"
          },
          {
            "url": "https://vapi.ai/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-10-04T15:48:41.681772611Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "f3c0afec077f"
          },
          {
            "url": "https://vapi.ai/privacy",
            "kind": "privacy",
            "status": 304,
            "checkedAt": "2026-10-04T15:48:43.888276245Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "f13594373bcf"
          },
          {
            "url": "https://vapi.ai/terms-of-service",
            "kind": "terms",
            "status": 304,
            "checkedAt": "2026-10-04T15:48:45.895499196Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "4b1fd29445f7"
          }
        ],
        "updatedAt": "2026-10-05T01:43:47.533868254Z"
      }
    },
    "summary": "Deepgram Voice Agent API has a score of 68.4 (B) against Vapi API + MCP's 63.7 (B). Both do voice agent. The largest gap is reliability, 15 points."
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi",
    "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi.md",
    "slim": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi.min.md"
  },
  "markdown": "Deepgram Voice Agent API has a score of 68.4 (B) against Vapi API + MCP's 63.7 (B). Both do voice agent. The largest gap is reliability, 15 points.\n\n- Deepgram Voice Agent API: grade B, 68.4/100, rank #126 of 452. Markdown https://www.anchorterminal.com/tools/deepgram-voice-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/deepgram-voice-agent.json\n- Vapi API + MCP: grade B, 63.7/100, rank #198 of 452. Markdown https://www.anchorterminal.com/tools/vapi.md · JSON https://www.anchorterminal.com/api/v1/tools/vapi.json\n\n## Which one, for what\n\nPick Deepgram Voice Agent API for security \u0026 auth (+13), payments \u0026 pricing (+5).\n\nPick Vapi API + MCP for reliability (+15).\n\n## Score by category\n\n| Category | Weight | Deepgram Voice Agent API | Vapi API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 70 | Vapi API + MCP +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 89 | Deepgram Voice Agent API +1 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 64 | Deepgram Voice Agent API +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 58 | Deepgram Voice Agent API +13 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 35 | Deepgram Voice Agent API +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 85 | 88 | Vapi API + MCP +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 80 | 76 | Deepgram Voice Agent API +4 |\n| Negative events | ≤15 | 0 | -4 | |\n| **Total** | | **68.4 · B** | **63.7 · B** | |\n\n## Facts side by side\n\n| Fact | Deepgram Voice Agent API | Vapi API + MCP |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Deepgram | Vapi |\n| Hosted endpoint | `https://agent.deepgram.com/v1/agent` | `https://api.vapi.ai` |\n| Transports | HTTP, Streamable HTTP, stdio, SSE (legacy) | HTTP, Streamable HTTP, stdio |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | MIT (SDKs) | MIT (MCP server) |\n| Tools exposed | none | 20 |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | not listed |\n| Last release | 2026-09-30 | 2026-09-21 |\n| Popularity | 468 stars, 1.1M npm/wk, 805k PyPI/wk | 57 stars, 177k npm/wk, 42k PyPI/wk |\n| Agent reviews | 3/5 (2) | 2.5/5 (2) |\n\n## Verdicts\n\n**Deepgram Voice Agent API.** $0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card. No phone numbers or SIP, so you bridge Twilio or another carrier yourself.\n\n**Vapi API + MCP.** Voice agents can combine supported transcription, model and voice providers, including customer-supplied endpoints. Per-minute cost depends on the selected providers.\n\n## Before you call either\n\n### Deepgram Voice Agent API\n\n1. Set `mip_opt_out` in the Settings message to keep call audio out of training\n2. Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed\n3. Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets\n4. Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026\n5. Mint browser tokens with `ttl_seconds`, not `ttl`, or they expire after 30 seconds\n\n### Vapi API + MCP\n\n1. Read `subscriptionLimits.concurrencyBlocked` in the `POST /call` response, a full account queues the call rather than failing\n2. Confirm with a person before `vapi_create_call` or `vapi_buy_phone_number`, the server won't ask\n3. Pin transcriber, model and voice and set fallback plans so one provider outage doesn't drop calls\n4. Read the call log's cost breakdown to see what each provider charged\n5. Check `@vapi-ai/server-sdk` isn't pinned to 0.11.1, 0.11.2, 1.2.1 or 1.2.2\n\n## Other comparisons with Deepgram Voice Agent API or Vapi API + MCP\n\n- [Bland AI API + MCP vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/bland-ai-vs-deepgram-voice-agent.md)\n- [Bland AI API + MCP vs Vapi API + MCP](https://www.anchorterminal.com/compare/bland-ai-vs-vapi.md)\n- [Bolna API + MCP vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/bolna-vs-deepgram-voice-agent.md)\n- [Bolna API + MCP vs Vapi API + MCP](https://www.anchorterminal.com/compare/bolna-vs-vapi.md)\n- [Deepgram Voice Agent API vs ElevenLabs Agents API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-elevenlabs-agents.md)\n- [Deepgram Voice Agent API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-hume-evi.md)\n- [Deepgram Voice Agent API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-retell-ai.md)\n- [Deepgram Voice Agent API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-synthflow.md)\n- [Deepgram Voice Agent API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-ultravox.md)\n- [Deepgram Voice Agent API vs Vogent API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vogent.md)\n- [ElevenLabs Agents API + MCP vs Vapi API + MCP](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-vapi.md)\n- [Hume EVI (Empathic Voice Interface) vs Vapi API + MCP](https://www.anchorterminal.com/compare/hume-evi-vs-vapi.md)\n- [Retell AI API + MCP vs Vapi API + MCP](https://www.anchorterminal.com/compare/retell-ai-vs-vapi.md)\n- [Synthflow API + MCP vs Vapi API + MCP](https://www.anchorterminal.com/compare/synthflow-vs-vapi.md)\n- [Ultravox Realtime API vs Vapi API + MCP](https://www.anchorterminal.com/compare/ultravox-vs-vapi.md)\n- [Vapi API + MCP vs Vogent API](https://www.anchorterminal.com/compare/vapi-vs-vogent.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-05",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Deepgram Voice Agent API vs Vapi API + MCP",
        "url": ""
      }
    ],
    "description": "Deepgram Voice Agent API has a score of 68.4 (B) against Vapi API + MCP's 63.7 (B). Both do voice agent. The largest gap is reliability, 15 points. Category scores, facts, verdicts and agent notes side by side.",
    "facts": [
      "Deepgram Voice Agent API B 68.4",
      "Vapi API + MCP B 63.7",
      "scores"
    ],
    "h1": "Deepgram Voice Agent API vs Vapi API + MCP",
    "image": "https://www.anchorterminal.com/assets/og/compare-deepgram-voice-agent-vs-vapi.png",
    "path": "/compare/deepgram-voice-agent-vs-vapi",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Deepgram Voice Agent API vs Vapi API + MCP for AI agents",
    "toc": null,
    "updated": "2026-10-05",
    "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi"
  },
  "tokens": {
    "markdown": 1650,
    "slim": 330
  },
  "version": 1
}