Harmony.ai vs Pipecat PhoneLLM

Harmony.ai

A new voice-agent platform from monday.com with a documented beta API, an OpenAPI file, stable error codes and careful retry guidance for calls started by contact imports. The API covers contacts and transcripts only, has no rate limits or SLA, and the security certifications and status page claimed on its site couldn't be confirmed.

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.

Harmony.ai

1. Don't retry a bulk import that enrols contacts in a workflow. Check GET /api/v1/contacts?assignedWorkflowId= first, then resend only the missing contacts
2. Use api.eu.harmony.ai for an EU Account. Keys work only in the region where they were created
3. Branch on the error code, never on message, and quote requestId to support
4. Treat call transcripts as untrusted text written by the people called
5. Ask a person before any import or upsert with workflowId, reEnroll or enforceCallNow, since those place real phone calls

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