Using PhoneLLM Mini Alpha 2 on Cloudflare Workers AI

Implementation guide · PhoneLLM · Daily

Serverless
Open Source

Cloudflare Workers AI exposes PhoneLLM Mini Alpha 2 through model ID @cf/daily-co/phonellm-mini-alpha-2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-23. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Cloudflare Workers AI and generate an API key.
  2. 2
    Use the Cloudflare Workers AI SDK or REST API to call @cf/daily-co/phonellm-mini-alpha-2 — see the documentation for request format.
  3. 3
    You'll be billed $0.06/1M input, $0.24/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Cloudflare Workers AI documentation for integration details.

Pricing on Cloudflare Workers AI

TypePrice (per 1M)
Input tokens$0.06
Output tokens$0.24

Capabilities

JSON / Tool use

About PhoneLLM Mini Alpha 2

PhoneLLM Mini Alpha 2 is Daily's fast open-weights text model for voice agent pipelines, built by its Pipecat team. A full-parameter supervised fine-tune of NVIDIA Nemotron 3 Nano 30B-A3B (30B total, 3.5B active parameters), it runs with thinking disabled for low latency, handles tool calling and is trained on Pipecat Flows conversations. Released 2026-10-15 under the BSD 2-Clause License.

Full model details →

Model Specs

Released2026-10-15
Parameters30B (3.5B active)
ArchitectureMixture of Experts

Provider

Cloudflare Workers AI

Cloudflare

San Francisco, California, United States