Plans and pricing

Plan comparison#

Annual billing is 20% below paying the monthly price twelve times. Launch and Operate begin with a seven-day free trial with no credit card; add a card after day 7 to keep the agent live. Scale begins billing immediately and has no trial. When a card is needed, checkout shows the exact price, renewal period, tax, and terms before purchase.

Launch is a working embed agent this week. Operate is the step up once customers are actually talking — live voice, a fuller widget, and messaging channels. Scale is the full studio: every Look control, team roles, and your own provider keys.

Feature ladder#

We do not sell or attach customer domains. Embed the agent on the website you already have.

Included on every plan#

All current plans include:

• An embed on the website you already have (embed.js + data-agent).
• Text chat, voice messages, stock voices, knowledge retrieval, structured FAQs/products, and lead capture.
• Website embedding with exact origin controls.
• Public API access with scoped keys, OAuth for reviewed apps, OpenAPI, and plan-scaled rate limits.
• Analytics, conversations, usage tracking, and the ability to buy credit packs.

Launch's Public API allowance is 120 requests per API key per minute, Operate's is 600, and Scale's is 1,800. These request limits do not replace resource entitlements, credit checks, idempotency, or provider-specific limits. See Rate limits.

Understand credits#

Credits pay for metered AI work such as generation, agent turns, knowledge embeddings, transcription, speech synthesis, and cloning. They are not a fixed number of messages: provider, model, input/output length, media duration, and operation type change the cost.

Monthly plan credits refill each billing period. Unused monthly allowance rolls over for one extra cycle, then expires. Purchased top-up credits do not expire while a subscription is active. A positive credit balance does not unlock a plan-only feature such as live calls, extra sites, cloning, or badge removal.

Bring-your-own-provider keys can create separate charges from OpenAI, Anthropic, Google, Deepgram, or ElevenLabs. Saving a new key is Scale-only; keys already stored keep working. BYOK does not convert provider invoices into Make Agent Fast credits or eliminate platform entitlement checks. See AI provider keys.

Voice entitlements#

Voice messages are included on all plans but their transcription, model, and speech work can consume credits. Live real-time voice uses a separate monthly minute allowance: none on Launch, 30 minutes on Operate, and 90 minutes on Scale.

Voice cloning is Operate/Scale only. Operate includes one workspace clone; Scale supports multiple under fair use. Re-cloning a site that already owns a clone replaces it rather than consuming a new slot. Cloning also requires explicit consent, provider availability, and enough credits for the operation.

Agents and branding#

Launch supports one customer-facing agent and Operate supports up to three. Scale's unlimited-agents description is subject to fair use rather than an invitation to create abusive or automated tenant volume. An agent includes its knowledge, embed configuration, connectors, analytics, and conversation data. Leftover hosted demo pages still render at subdomains; new agents do not get a hosted marketing page.

The “Made with Make Agent Fast” referral badge remains on Launch. Operate and Scale owners can remove it from entitled published sites.

Credit packs#

Top-ups add usage capacity only. They do not increase site count, API request limits, live minutes, clone count, or branding permissions.

Trials, renewal, and cancellation#

The Launch/Operate free trial does not convert automatically: on day 7 the agent pauses until you add a card. After a card is on file, canceling or a failed renewal can remove active access after the applicable provider period/status transition. Embeds, connectors, API clients, and voice calls may stop even though stored workspace data remains.

Choose a plan#

• Choose Launch for one embedded agent with text, voice messages, and a basic widget.
• Choose Operate when customers start talking: live calls, messaging channels, a custom widget, two languages, or badge removal.
• Choose Scale when several agents are in production: every widget control, four languages, team roles, and your own API keys.

Estimate from real acceptance tests rather than message count alone. Publish one representative agent, measure text/voice/knowledge usage, then project the traffic and add headroom for retries, connectors, automation, and launch peaks.

Billing source of truth#

The live checkout and billing dashboard are the source of truth for a specific purchase. Taxes, currency presentation, payment methods, trial eligibility, and provider wording can vary by location and account state. If a checkout differs from this page, stop and use the checkout terms or contact support before paying.