Your first phone number is on us — plus we pay 50% of your first week's vendor bill (up to $25).*
Claim your number→Know what every AI call really costs.
Your voice agent spends money across a dozen vendors on every call — carrier, speech-to-text, language model, voice, tools. Floe costs each call the moment it ends, ties it to the client and campaign, and shows your margin. Price contracts on real numbers, not a blended guess.
Plugs into Vapi, Retell, Bland, Pipecat, and LiveKit. No runtime. No orchestration. We don't touch your calls — we account for them.
AI vendor bills arrive late. So you know your blended margin. Some clients are underwater. You're funding them with the ones that aren't.
Floe costs every call as it happens, tagged to the client. Price on what each account actually costs. Inside Vapi, Retell, LiveKit, Pipecat, Bland, or BYOK.
Leave with a per-client margin table.
Book 15 minutes with the founders.
https://dev-dashboard.floelabs.xyz/
Read https://dev-dashboard.floelabs.xyz/agents.md and set up Floe for this project.One call. A dozen bills. None of them line up.
A single voice call touches 5+ paid vendors. Each one meters a different unit, on a different schedule.
From COGs per contract to month-end accruals to customer profitability, in four moves.
Read https://dev-dashboard.floelabs.xyz/agents.md and set up Floe for this project.Built for the people who own the margin.
Built for the people who own the margin.
Built for the people who own the margin.
One call. A dozen bills. None of them line up.
A single voice call touches 7 to 20 paid vendors. Each one meters a different unit, on a different schedule.
Read https://dev-dashboard.floelabs.xyz/agents.md and set up Floe for this project.Start with spend meter and budget gate.
floe-guard meters STT + TTS + LLM + telephony per call. Hard-stops the next turn before it crosses your ceiling. Run locally, no telemetry. MIT.
Running voice agents on Vapi, Retell, Bland, LiveKit or Pipecat?
15 minutes with the founders.
Every leg of the call. One key. One ledger.
A voice call spends across 7–20 vendors. Floe meters and caps all of them — keyless on the gateway catalog, or BYOK with your own provider keys. These are the verified services live today; anything not listed is one submission away.
The BYOK metered proxy prices any model OpenAI or Anthropic ships — pass the model id, bring your key, get metering and a server-side cap. If a provider sells it and Floe can price it, it's callable.
Sarvam's Indic chat, STT (Saaras), and TTS (Bulbul) run on the same key and ledger as the rest of your stack — regional-language agents without a separate vendor relationship.
Every service here is metered against the same balance and policies. When the cap is hit, the call is refused before any upstream spend — that's the whole point.
"Token and TTS usage varies every call, so true per-call COGs only exists by joining usage data across providers after the call. Floe gives us that in real time."
CEO
$5M ARR voice agency
1/4
"Getting the cost column is very difficult. I love that with Floe you can just plug it in."
Author, VAmoS Bench
Industry voice-agent benchmark
2/4
"We have different carriers, voice models, LLM and a lot of different components. Floe automates what takes finance team 10+ hours manually."
Finance Deployments Lead
Series B AI production application
3/4
"The problem Floe's solving is real. We hear some version of it from every team managing multi-model, multi-vendor agent stacks."
Startups Team
Z.ai
4/4
No. BYOK is live today: keep your own vendor accounts and keys — Floe accounts for, meters, joins, and caps on top of them, and your platform spend flows onto the same ledger via end-of-call webhooks. Keyless — Floe fronts the vendor, one key, welcome credits — is the fast lane for prototypes or net-new builds.
A voice call touches 5+ vendors billing separately, and token and TTS usage is variable every conversation — so true per-call COGS only exists by joining usage data across providers after each call.
Floe does that join in real time and enforces budgets on top: caps rejected before money moves where Floe is in the path, and a circuit breaker that denies the next call everywhere else. One ledger: per-call, per-agent, per-vendor, per-customer.
Yes — through the platforms' own documented extension points, with zero platform cooperation. Point the custom-LLM slot at Floe for pre-call enforcement on ~60% of call cost; connect the end-of-call webhook and every call lands on one ledger with a between-call circuit breaker.
No — by design. A dropped call is a worse failure than an expensive one. Enforcement is pre-call admission: where Floe is in the path (LLM, STT, TTS, Floe Phone), an over-budget call is denied before it starts. Where it isn't, Reconcile Mode meters the cost at call-end and the circuit breaker denies the next call.
Your coverage score shows exactly which of your spend sits in which bucket.
A per-agent number in your dashboard: the % of that agent's spend that is pre-call enforceable vs post-call reconciled vs dark — across every platform it runs on. No single platform can compute this about itself, because no platform sees spend outside its own runtime.
The score also tells you which leg to move to raise it.
Pick your lane. On a platform: one config field (custom-LLM slot) plus a webhook — no code. BYOK: point your OpenAI-compatible SDK at Floe's base URL with your Floe key; drop-in SDKs for AgentKit, LangChain, CrewAI, Vercel AI SDK, OpenAI Agents, and Claude (MCP). Keyless: paste one line into Claude Code or Cursor and your agent provisions itself. Or hit the REST API from anything that speaks HTTP.
Full quickstart: Agent Quickstart →
Alex Christian (DataMynt co-founder; payments, treasury, and compliance risk at Airwallex, Western Union, eBay) and Shivam Chaturvedi (DataMynt co-founder; CTO at Kado.money, acquired; founding engineer at Transak). Both shipped payments, compliance, and billing infrastructure at scale before Floe.
Every leg of the call. One key. One ledger.
These are the verified services live today; anything not listed is one submission away.
Sarvam's Indic chat, STT (Saaras), and TTS (Bulbul) run on the same key and ledger as the rest of your stack — regional-language agents without a separate vendor relationship.
"Token and TTS usage varies every call, so true per-call COGs only exists by joining usage data across providers after the call. Floe gives us that in real time."
CEO
$5M ARR voice agency
1/4
"Getting the cost column is very difficult. I love that with Floe you can just plug it in."
Author, VAmoS Bench
Industry voice-agent benchmark
2/4
"We have different carriers, voice models, LLM and a lot of different components. Floe automates what takes finance team 10+ hours manually."
Finance Deployments Lead
Series B AI production application
3/4
"The problem Floe's solving is real. We hear some version of it from every team managing multi-model, multi-vendor agent stacks."
Startups Team
Z.ai
4/4
"Token and TTS usage varies every call, so true per-call COGs only exists by joining usage data across providers after the call. Floe gives us that in real time."
CEO
$5M ARR voice agency
1/4
"Getting the cost column is very difficult. I love that with Floe you can just plug it in."
Author, VAmoS Bench
Industry voice-agent benchmark
2/4
"We have different carriers, voice models, LLM and a lot of different components. Floe automates what takes finance team 10+ hours manually."
Finance Deployments Lead
Series B AI production application
3/4
"The problem Floe's solving is real. We hear some version of it from every team managing multi-model, multi-vendor agent stacks."
Startups Team
Z.ai
4/4
Start free. Pay when it pays you.
Every tier is gated by the spend we track for you, so a two-person shop and a 200-agent operation never pay the same price.
- –Live ledger
- –Coverage Score
- –7-day history
- –Everything in Free
- –Cost per client, campaign, task
- –Fleet-wide budgets & hard stops
- –Alerts & exports
- –12-month history
- –Everything in Pro
- –Rate cards & markup engine
- –White-label invoices via your Stripe
- –Up to 30 billed clients
- –Everything in Agency
- –P&L and margin per contract
- –Multi-country, multi-carrier
- –SSO, audit, procurement
- –Dedicated support
Who's behind Floe
No. BYOK is live today: keep your own vendor accounts and keys — Floe accounts for, meters, joins, and caps on top of them, and your platform spend flows onto the same ledger via end-of-call webhooks. Keyless — Floe fronts the vendor, one key, welcome credits — is the fast lane for prototypes or net-new builds.
A voice call touches 5+ vendors billing separately, and token and TTS usage is variable every conversation — so true per-call COGS only exists by joining usage data across providers after each call.
Floe does that join in real time and enforces budgets on top: caps rejected before money moves where Floe is in the path, and a circuit breaker that denies the next call everywhere else. One ledger: per-call, per-agent, per-vendor, per-customer.
Yes — through the platforms' own documented extension points, with zero platform cooperation. Point the custom-LLM slot at Floe for pre-call enforcement on ~60% of call cost; connect the end-of-call webhook and every call lands on one ledger with a between-call circuit breaker.
No — by design. A dropped call is a worse failure than an expensive one. Enforcement is pre-call admission: where Floe is in the path (LLM, STT, TTS, Floe Phone), an over-budget call is denied before it starts. Where it isn't, Reconcile Mode meters the cost at call-end and the circuit breaker denies the next call.
Your coverage score shows exactly which of your spend sits in which bucket.
A per-agent number in your dashboard: the % of that agent's spend that is pre-call enforceable vs post-call reconciled vs dark — across every platform it runs on. No single platform can compute this about itself, because no platform sees spend outside its own runtime.
The score also tells you which leg to move to raise it.
Pick your lane. On a platform: one config field (custom-LLM slot) plus a webhook — no code. BYOK: point your OpenAI-compatible SDK at Floe's base URL with your Floe key; drop-in SDKs for AgentKit, LangChain, CrewAI, Vercel AI SDK, OpenAI Agents, and Claude (MCP). Keyless: paste one line into Claude Code or Cursor and your agent provisions itself. Or hit the REST API from anything that speaks HTTP.
Full quickstart: Agent Quickstart →
Alex Christian (DataMynt co-founder; payments, treasury, and compliance risk at Airwallex, Western Union, eBay) and Shivam Chaturvedi (DataMynt co-founder; CTO at Kado.money, acquired; founding engineer at Transak). Both shipped payments, compliance, and billing infrastructure at scale before Floe.
No. BYOK is live today: keep your own vendor accounts and keys — Floe accounts for, meters, joins, and caps on top of them, and your platform spend flows onto the same ledger via end-of-call webhooks. Keyless — Floe fronts the vendor, one key, welcome credits — is the fast lane for prototypes or net-new builds.
A voice call touches 5+ vendors billing separately, and token and TTS usage is variable every conversation — so true per-call COGS only exists by joining usage data across providers after each call.
Floe does that join in real time and enforces budgets on top: caps rejected before money moves where Floe is in the path, and a circuit breaker that denies the next call everywhere else. One ledger: per-call, per-agent, per-vendor, per-customer.
Yes — through the platforms' own documented extension points, with zero platform cooperation. Point the custom-LLM slot at Floe for pre-call enforcement on ~60% of call cost; connect the end-of-call webhook and every call lands on one ledger with a between-call circuit breaker.
No — by design. A dropped call is a worse failure than an expensive one. Enforcement is pre-call admission: where Floe is in the path (LLM, STT, TTS, Floe Phone), an over-budget call is denied before it starts. Where it isn't, Reconcile Mode meters the cost at call-end and the circuit breaker denies the next call.
Your coverage score shows exactly which of your spend sits in which bucket.
A per-agent number in your dashboard: the % of that agent's spend that is pre-call enforceable vs post-call reconciled vs dark — across every platform it runs on. No single platform can compute this about itself, because no platform sees spend outside its own runtime.
The score also tells you which leg to move to raise it.
Pick your lane. On a platform: one config field (custom-LLM slot) plus a webhook — no code. BYOK: point your OpenAI-compatible SDK at Floe's base URL with your Floe key; drop-in SDKs for AgentKit, LangChain, CrewAI, Vercel AI SDK, OpenAI Agents, and Claude (MCP). Keyless: paste one line into Claude Code or Cursor and your agent provisions itself. Or hit the REST API from anything that speaks HTTP.
Full quickstart: Agent Quickstart →
Alex Christian (DataMynt co-founder; payments, treasury, and compliance risk at Airwallex, Western Union, eBay) and Shivam Chaturvedi (DataMynt co-founder; CTO at Kado.money, acquired; founding engineer at Transak). Both shipped payments, compliance, and billing infrastructure at scale before Floe.