Pipecat PhoneLLM vs Vogent API

Pipecat PhoneLLM

PhoneLLM Mini is callable per token on Workers AI at $0.06 input and $0.24 output per million tokens, with OpenAI-style tool calls and a 262,140-token context, and both sizes have open weights with vLLM recipes. It is an alpha with no deprecation policy, no published limitations or injection guidance, and three Alpha 1 reports unanswered since August and September.

Vogent API

IVR detection and navigation models for outbound calls. No public changelog and no release found since January 2026.

Pipecat PhoneLLM

1. Send temperature: 0 on every call. The repositories' generation_config.json samples by default, and Max's sets temperature 1.0
2. For Max, serve with --reasoning-parser nemotron_v3 and send chat_template_kwargs with enable_thinking: true on every request, or the reply lands in reasoning
3. For Mini, serve without a reasoning parser and keep enable_thinking false, as Cloudflare and the card say, or tool calls can be filed under reasoning
4. Confirm bookings, payments and transfers in your own handler before acting on a tool call, since caller speech reaches the model directly
5. Pin the model ID including alpha-2. Daily states no notice period, and a later alpha may replace it

Vogent API

1. Send an idempotencyKey on POST /dials, a reused key returns 409
2. Create a call with callAgentId, plus toNumber and fromNumberId for phone calls
3. Tell the model when to emit <|transfer|>, since transfers fire on that tag
4. Verify webhooks with the HMAC in X-Elto-Signature
5. Expect new dials to fail at the workspace's concurrent dial limit until calls end