Bland AI API + MCP vs Pipecat PhoneLLM

Bland AI API + MCP

One per-minute rate covering STT, LLM, TTS and telephony, $0.14 on Start and $0.12 on Build. No OpenAPI document.

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.

Bland AI API + MCP

1. Call wait_for_call (it waits up to 45 seconds) instead of polling get_call_log
2. Send destructive MCP tools a second time with the confirmation argument
3. Space calls to the same number at least 10 seconds apart or expect a 429
4. Budget $0.015 for every outbound attempt, including ones that never connect
5. Run validate_pathway before saving a pathway graph

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