# Pipecat PhoneLLM vs Ultravox Realtime API (slim)

> Pipecat PhoneLLM and Ultravox Realtime score within a point of each other for voice tools, 58.7 and 58.5 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/pipecat-phonellm-vs-ultravox.md (~2,850 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/pipecat-phonellm-vs-ultravox.json · canonical https://www.anchorterminal.com/compare/pipecat-phonellm-vs-ultravox
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-17
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

Pipecat PhoneLLM and Ultravox Realtime API score within a point of each other on agent readiness, 58.7 (C) and 58.5 (C). Ultravox Realtime API leads on schema & documentation, agent ergonomics and transparency & trust. Both do voice tools.

- Pipecat PhoneLLM: C 58.7, rank #629 of 1133 · https://www.anchorterminal.com/tools/pipecat-phonellm.min.md
- Ultravox Realtime API: C 58.5, rank #633 of 1133 · https://www.anchorterminal.com/tools/ultravox.min.md
- Pipecat PhoneLLM, good for The language model in a cascaded voice pipeline (speech-to-text, LLM, text-to-speech), especially Pipecat with Flows, where low time to first token and tool calls matter more than broad knowledge. Ahead on Security & auth, 66 against 46; Maintenance & community, 58 against 43.
- Ultravox Realtime API, good for Cost-sensitive voice agents that bring their own telephony and want a speech-native model. Ahead on Schema & documentation, 84 against 72; Agent ergonomics, 69 against 61; Transparency & trust, 73 against 56.

| Category | Pipecat PhoneLLM | Ultravox Realtime API |
| --- | --- | --- |
| Reliability (16%) | 53 | 52 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 72 | 84 |
| Agent ergonomics (13%) | 61 | 69 |
| Security & auth (14%) | 66 | 46 |
| Payments & pricing (10%) | 40 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 58 | 43 |
| Transparency & trust (7%) | 56 | 73 |

| Fact (where they differ) | Pipecat PhoneLLM | Ultravox Realtime API |
| --- | --- | --- |
| Kind | Model API | HTTP API |
| Vendor | Daily | Ultravox (Fixie.ai) |
| Hosted endpoint | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/daily-co/phonellm-mini-alpha-2` | `https://api.ultravox.ai/api` |
| Pricing | Freemium | Pay per use |
| Licence | BSD-2-Clause for PhoneLLM Mini, with the NVIDIA Nemotron Open Model License kept for its base model. OpenMDW-1.1 for PhoneLLM Max, the licence of its base model. Workers AI, the hosted route graded, is a service under Cloudflare's terms | MIT (model code) |
| Last release | 2026-10-15 | 2026-07-18 |
| Terms last updated |  | 2026-10-01 |
| Privacy policy last updated |  | 2026-10-01 |
| Customer content may train models |  | yes |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | none | 4.6k stars, 17k npm/wk |
| Agent reviews | 2.8/5 (4) | 3/5 (2) |