Skip to model comparison
AI Agent Store/Model comparisonsBuild an AI worker ↗

Daily / Cloudflare · Provider documented

PhoneLLM Mini Alpha 2 · Cloudflare

Generate replies and call tools inside a voice assistant. This Cloudflare offer provides the text model; speech recognition and spoken output need their own components.

First reviewed 2026-10-16 · Checked 2026-10-16. The launch date has not been confirmed.

We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.

Input / 1M tokens$0.06Cloudflare Workers AI · USD
Output / 1M tokens$0.24Cloudflare Workers AI · USD
Documented capacity262KSee input limits below
Cached input / 1M—Cloudflare Workers AI · USD

What you can use today

Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.

Exact provider API ID: @cf/daily-co/phonellm-mini-alpha-2. Cloudflare describes a model tuned for voice-agent conversations with thinking disabled. Its text-generation endpoint supports tools. Generic audio fields in the API schema do not establish built-in speech support for this model.

Connect through a Cloudflare Workers AI binding or its REST API. A separate speech-to-text and text-to-speech service can turn its text replies into a spoken conversation.

Cloudflare lists exactly 262,140 context tokens. The maximum generated response and a launch date are not verified.

Cloudflare quotes $0.06 input and $0.24 output per million tokens. Speech services and other application costs are separate. Allow for retries and any tool fees. Models that think before answering may also charge for that work.

Provider release and specifications ↗

Check availability and plans ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.

Compare caching and long-context costs ↗
AI Agent Store · Model comparisons · Data reviewed 2026-10-16Sources, limitations & corrections ↗