OpenAI-compatible · open-weight · verified mesh
The world's idle computers,
serving tokens.
Teraflock serves open-weight models from a verified mesh of everyday machines — Apple Silicon, gaming GPUs — through the API you already use. For work that doesn't need a frontier model, it's 5–20× cheaper than frontier APIs. For the machines, it's a share of every token they serve.
from openai import OpenAI client = OpenAI( base_url="https://api.teraflock.ai/v1", # the only change api_key="tf-...", ) r = client.chat.completions.create( model="flock/llama-3.1-8b-instruct", messages=[{"role": "user", "content": "hi"}], )
For builders
Drop-in API. Honest prices.
Every endpoint you expect
Chat completions with streaming, completions, embeddings — any OpenAI SDK works unmodified. Your framework doesn't know the difference.
Batch is first-class
Bulk classification, extraction, dataset generation, eval runs:
upload a file to /v1/batches and pay half
the interactive rate, never surged. Where latency doesn't matter, price should.
Verified, not trusted
Canary sampling against reference hardware, model fingerprinting, timing envelopes, and escrowed earnings make cheating economically irrational — so you don't have to take anyone's word for it.
Privacy, stated plainly
You choose where your prompts may travel.
Inference needs plaintext on the serving machine — anyone who says otherwise is selling something. So the tier is explicit, per request.
Any qualified node. Cheapest. Operators could theoretically observe content — we say so instead of pretending.
Only high-reputation nodes with staked credits and a signed operator agreement.
First-party datacenter hardware only. Highest on the mesh, still under frontier pricing.
On every tier: nodes see an ephemeral request ID, never your identity, and never write prompts to disk.
Pricing
Per million tokens. No subscriptions, no minimums.
| Class | Input | Output | Batch (0.5×) | |
|---|---|---|---|---|
| Nano · ≤3.5B | $0.014 | $0.03 | $0.007 / $0.015 | classification, extraction, routing |
| Small · 3.5–9B | $0.018 | $0.036 | $0.009 / $0.018 | the volume workhorse |
| Mid · 9–40B | $0.075 | $0.29 | $0.038 / $0.145 | 24GB+ GPUs and 64GB+ Macs earn here |
| Large · 40–150B | $0.105 | $0.34 | $0.053 / $0.17 | 96GB+ Apple Silicon; scarce supply |
| XL · >150B | $0.3 | $0.97 | $0.15 / $0.485 | 256–512GB unified; the rarest supply |
| Embeddings | $0.004 | — | $0.002 | bulk vectorization; input tokens only |
Full pricing → including the operator split, surge, and a dated comparison against every host we could find.
For operators
Your computer sleeps eight hours a night.
It could be earning.
Two minutes to enroll
One daemon. It detects your hardware, pulls the right models, and starts serving. Mac menu bar, CLI, and a local dashboard.
Never in your way
Serves only when you're away by default; touch the keyboard and it yields within two seconds. Battery, hours, and memory limits are yours.
Real money, honestly framed
Operators keep 40–75% of what customers pay — more, the scarcer the hardware. Earned credits spend on your own AI usage 1:1, or cash out. No mining-boom numbers, and your real figure is live in the app.
Read your ISP's terms first. A node opens one outbound
mTLS connection to tunnel.teraflock.ai:443, listens on no public port, and moves
tokens, not media: tens of megabytes an hour serving flat out, a keepalive every 20 seconds
idle, plus one-time model downloads of a few to tens of GB. Some residential plans restrict
"servers"; whether this fits yours is between you and your ISP. You are responsible for your
own ISP's terms, and we don't claim any particular ISP allows it.
FAQ
Fair questions, straight answers.
Is it really OpenAI-compatible?
Yes — chat completions, completions, embeddings, and batches. Point any OpenAI SDK at our base URL, keep your code. Streaming included. Decision models are the one addition: they answer on /v1/systemone, TypeSafe's System One API, so code written for that needs the same one change.
Where do my prompts actually go?
To someone's computer — and we say so. Requests carry an explicit privacy tier: open routes to any qualified node (cheapest; operators could theoretically observe content), verified routes only to high-reputation, staked, under-agreement nodes, and private stays on first-party hardware. Nodes never see who you are, and never persist prompts to disk.
How do you know a node isn't faking the work?
Statistically and economically. A slice of requests is silently duplicated to reference hardware and compared; nodes get fingerprint challenges with known answers for their exact model build; timing outside the hardware's physical envelope gets flagged. Cheaters forfeit escrowed earnings and their reputation — cheating has negative expected value.
What can my machine earn?
Honest answer: it depends on demand, and on your hardware. Operators keep 40–75% of what customers pay, and the share rises with how scarce the hardware is: 24GB+ GPUs and Apple Silicon with 64GB+ serve the mid and large classes at a 65–72% share, which is where the money is. A 12GB gaming card serves the small class at 45% — think credits you spend on your own AI usage, not a paycheck. We publish no dollars-per-month figure until we have measured one; your own number is live in the app from day one.
Will it slow my computer down?
That promise is the whole product. By default the daemon serves only when you're away, and the moment you touch the keyboard it yields within two seconds — the mesh reroutes without you noticing. You set the limits: hours, battery rules, memory caps.
Why is batch cheaper?
Because that's where a mesh structurally wins. Embeddings, bulk classification, dataset generation, eval runs — work where price matters and latency doesn't — run at half the interactive rate through a first-class /v1/batches API, and batch never pays surge.
When can I use it?
We're onboarding from the waitlist in cohorts — builders and operators in matched batches, because the marketplace needs both sides. Join below; we'll write when it's your turn.
Get in the flock.
Builders and operators onboard in matched cohorts — the marketplace needs both sides. Tell us which you are: