Starter
Prototype your first pipeline, no commitment required.
Free
Discovery
- 1 organization, 2 users
- 3 active pipelines
- 5,000 credits included ($0.50)
- Channels: webhook, schedule, terminal
- BYOK required (OpenAI, Anthropic, Ollama)
- Community support
Pricing
Transparent pricing,based on actual usage.
1 credit = $0.0001. You only pay for what executes. Native BYOK: LLM costs go through your provider, never through us.
Recommended
Business
The full platform, with SLA and all channels.
Custom quote
Production
- Multi-user, fine-grained roles
- Unlimited pipelines & exchanges
- Auto-reload credits, budget alerts
- All channels (voice, email, web, messaging)
- Sub-pipelines, code steps, OAuth2 connectors
- BYOK + betool managed models
- Priority support (SLA 8 business hours)
- 12-month execution history
Enterprise
Dedicated deployment, SSO, audits, private models.
Custom
Regulated / sovereign
- Everything in Business, plus:
- Private cloud / on-premise / air-gapped
- SSO (OIDC, SAML) + SCIM
- Private LLM models (Ollama, vLLM)
- Security audit, shared pentests
- Full GDPR documentation, dedicated DPA
- Onboarding & training
All plans include GDPR compliance, TLS/at-rest encryption, and execution logging.
Metering
Exactly what you pay for.
All unit costs are visible per execution. The figures below are indicative (vary by underlying provider).
| Resource | Indicative rate | Note |
|---|---|---|
| LLM (input) | ≈ 30 credits / 1 K tokens | Varies by model. Included with BYOK: provider billing pass-through. |
| LLM (output) | ≈ 90 credits / 1 K tokens | Typical 3:1 ratio for a conversational agent. |
| Inbound voice (ASR) | ≈ 10 credits / second | Real-time streaming (Deepgram, OpenAI Whisper, etc.). |
| Outbound voice (TTS) | ≈ 30 credits / 100 characters | ElevenLabs, OpenAI TTS, Azure TTS. Guaranteed real-time latency. |
| Phone minutes | ≈ 200 credits / minute | LiveKit SIP + operator trunk. Varies by destination. |
| HTTP / DB operators | Included | Not metered. You pay only for LLM / voice resources. |
Definitive per-provider rates are available on request. Orchestration is not metered: HTTP operators, DB, transform, compute, code steps, and sub-pipeline calls are included. You pay only for the LLM and voice resources consumed.
FAQ
Frequently asked questions.
How does the credit system work? ▾
1 credit = $0.0001 (one ten-thousandth of a dollar). You top up your balance in advance, and each execution debits the corresponding cost — visible to the second. No surprises at the end of the month.
BYOK: what exactly is it? ▾
Bring Your Own Key. You enter your OpenAI, Anthropic, Mistral API keys, or point to a private Ollama / vLLM instance. LLM costs are then billed directly by your provider, never by us. We only bill for our orchestration.
What if I want private models on my own infrastructure? ▾
On Enterprise, we support Ollama and vLLM with multi-GPU. Your prompts and completions never leave your perimeter. This is the preferred mode for regulated sectors.
What happens if my balance reaches zero? ▾
Executions are refused pre-call (before any debit) with an explicit message. You can configure auto-reload or budget alerts per organization.
Do you offer on-premise deployment? ▾
Yes, exclusively on the Enterprise plan. We provide containerized images, installation assistance, updates via a validated channel, and compliance onboarding support.
Can I reuse a pipeline or inject custom logic? ▾
Yes. A pipeline can call another as a function (sub-pipelines), including cross-organization with audit. And for logic too specific for the built-in operators, a code step runs in a sandbox — locked by human review. These building blocks are part of orchestration and are not metered.
Can I start on Starter and then migrate? ▾
Yes, without disruption. Your organizations, pipelines, history, and secrets are preserved. Plan upgrades are done from the administration panel.
A specific case? Let's talk.
Atypical volumes, sovereign deployment, custom integrations — we'll build the plan that fits.