| What it does | Build Advanced Voice AI Agents
| Memory and continual learning for agents
|
|---|
| Stage | Established
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | usage-based
| freemium
|
|---|
| Pricing | Free tier with $5 credits included; Core plan at $29/month for early teams; Pro plan at $999/month minimum for scaling teams; Premier plan with custom pricing for enterprises. Per-minute costs range from $0.05 for Vapi hosting plus pass-through costs for transcription, LLM, and voice services.
| Free plan with $5 monthly credits. Pro ($19/month, $20 credits), Max ($100/month, $130 credits), Scale ($399/month, $600 credits). Enterprise with custom pricing. All plans use credit-based billing for API calls (memory, search, document processing).
|
|---|
| Key features | - Ultra low latency responses under 500ms
- Natural conversation with turn-taking and human-like voices
- Live call tool and data access with external integrations
- 200+ built-in model integrations and custom model support
- Telephony control with SIP, warm transfers, and voicemail detection
- Enterprise-grade uptime with model and network failure recovery
- Full API access and powerful UI for all users
- Multilingual support for 100+ languages
- Automated testing and hallucination detection
- A/B testing and continuous optimization
| - Memory graph with infer, update, and forget operations
- User profiles maintained automatically without search queries
- Hybrid semantic search with graph traversal
- Multimodal extraction and retrieval for PDFs, images, audio, video, and code
- Connectors for Google Drive, Gmail, Notion, OneDrive, GitHub, S3, and web crawler
- API, SDKs for TypeScript and Python, and MCP support
- Plugins for Claude Code, Cursor, CodeX, and other coding agents
- Local deployment as single open-source binary
- Advanced PDF extraction with OCR and figure descriptions on Scale and Enterprise
- SMFS virtual filesystem for agent interaction
|
|---|
| What makes it different | - API-native platform with no vendor lock-in
- Deploy from prompt to production in minutes
- Enterprise-grade security with SOC 2, HIPAA, and PCI compliance
- Sub-500ms latency for real-time conversation
- Support SLA with reserved capacity and dedicated engineers
| - Memory that improves over time through automatic inference and merging, not static embeddings
- Serves 100k+ organizations with over 1 trillion tokens per month in production
- Works with any model and any harness, not locked to specific providers
- Deploys anywhere: cloud, VPC, local laptop, or air-gapped environments
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 78 ● no change since last check | 67 ● no change since last check |
|---|
| Trust Flow (Majestic) | 30 | 29 |
|---|
| Citation Flow (Majestic) | 49 | 45 |
|---|
| Referring domains (Majestic) | 4101 | 1310 |
|---|