Unified AI Infrastructure

One API.
Every model.

One OpenAI-compatible gateway. Cloud providers and local inference. Automatic routing and failover across everything you connect. One API key. One balance. No unnecessary complexity.

Live catalog

Models

Every model served by this gateway, pulled live from the backend. Local models run on your own hardware at $0.

Pricing

Prepaid credits. Per-token billing.

Credits are consumed at retail rate per token and checked before every request — if you run out, you get a 402 and a top-up link. No subscription, no surprise bills.

Starter
$5 credit
Try the gateway. Enough for light experimentation and small workloads across cloud models.
Credits apply to any cloud model.
Scale
$100 credit
For busy production systems that want one balance and automatic failover without thinking about it.
Volume convenience on the same gateway.
Local
$0 forever
Run supported self-hosted models through the same API at zero cost. Local models run on your Ollama/local host — not on Clarity's cloud — so there is no cloud billing for local traffic.
Set up local
Local models are billed at $0.
Credentials

Get your API key

One key for every model. Create it, store it safely, top it up when you want cloud inference.

Checking signup availability…
Your API key
Shown once. Store it somewhere safe — it is the only credential you need. It is masked by default.
Never share this key or commit it to a repository. It is never stored in your browser or written to logs.
Starts at $0. Local models are free when you bring your own Ollama; cloud models need a top-up. Set up local →
Playground

Inference console

Real requests against the live gateway. Pick any model from the catalog and run it. Results come straight from the provider — nothing here is simulated.

Request

Run local models free (bring your own Ollama)
  1. Install Ollama on your machine (see ollama.com).
  2. Pull a model, e.g. ollama pull llama3.1:8b.
  3. Point Clarity at your Ollama host (set the local base URL in the gateway config).
  4. Pick a Local model above and run it. Billed at $0 — no cloud key needed.

Local inference runs on your hardware, not on Clarity's servers.

Response

Run a request to see the response here.
API

OpenAI compatible

Swap your base URL and key. That's it — works with the OpenAI SDK, LangChain, curl, anything that speaks the protocol.

OpenAI Compatible
# base URL is shown below — your live gateway
import openai

client = openai.OpenAI(
    base_url=,
    api_key="gw_…",
)
r = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "hi"}],
)
print(r.choices[0].message.content)
Local · $0

Bring your own local models

Local models run on your machine via Ollama (or any OpenAI-compatible local server) — not on Clarity's cloud. They are billed at $0 through the same API key, with no cloud credentials required.

1
Install Ollama on your own machine. This is the engine that runs the models locally.
2
Pull a model — e.g. ollama pull llama3.1:8b. Any model your Ollama supports works.
3
Connect it — point the gateway at your Ollama base URL (set the local base URL in the gateway config so Clarity can route to it).
4
Run it — pick a LOCAL · $0 model in the Playground and send a request. Billed at $0.

Because inference happens on your hardware, speed and availability depend on your machine — Clarity only routes and meters the request.

Local Models

Checking local Ollama…

Local Runtime

Checking local Ollama runtime…

Round-trip is measured by Clarity around the local upstream request; it is not Ollama model-eval time.

Status

Gateway health

Derived live from the backend — nothing here is hard-coded.

Gateway
checked via /health
Models
available via /v1/models
Local
billed at $0
Cloud routes
providers behind the gateway
Reference

Endpoints

EndpointAuthPurpose
POST /v1/chat/completionscustomer keyOpenAI chat completions (streaming supported)
GET /v1/modelspubliclist available canonical models
GET /v1/usagecustomer keytokens, cost, remaining balance
POST /v1/signuppubliccreate a new customer key
POST /v1/checkoutcustomer keyStripe checkout URL to top up credits
GET /healthliveness
Status

Live gateway status

Pulled live from GET /v1/statusreachable and probe_latency_ms come from a real, zero-cost network probe (any HTTP/TLS response counts, including 401/403). Nothing is hard-coded, estimated, or invented. Latency reflects the probe only; it is not a model inference time.

Gateway
status · active keys · balance
Providers reachable
live probe · configured behind the gateway
Last checked
UTC
ProviderConfiguredCreds setReachableLatency (ms)Models

Diagnostics

System diagnostics

Read-only, zero-inference. Aggregated from local discovery and the local runtime — nothing here is hard-coded.

Current build
Commit
Frozen checkpoint
Tag
SHA
Clarity process
Status
Local discovery
Status
Models discovered
Local runtime
Status
Models loaded
Last local request
Measured

Frozen checkpoint is the recovery baseline; the current build may contain newer validated changes. This panel never runs inference and does not claim production readiness.