RRunToken
Sign inGet started free

One API. Every model.

The unified LLM token
gateway & marketplace

Reach many models and providers through one OpenAI-compatible API. RunToken routes, proxies, meters, prices and settles every request for you.

Start free →
OpenAI CompatibleStreaming SSEPrepaid Billing
request.sh
curl https://api.ontosphere.ai/v1/chat/completions \
  -H Authorization: Bearer rt-... \
  -H Content-Type: application/json \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{
      "role": "user",
      "content": "Hello, RunToken"
    }],
    "stream": true
  }'
200 routed · metered · streaming

END-TO-END PIPELINE

One path, from capacity to settlement

Every token is produced and moved through a process you can see, control and audit.

01◈

Token Production

Upstream capacity

02⌁

Routing

Pick the deployment

03⇄

Proxy

Translate the protocol

04⌘

Aggregation

One model catalog

05◇

Reseller

Referrals and commission

06◎

Settlement

Billing and payout

BUILT FOR SCALE

Build the product, not the plumbing

01

One API

Integrate once and reach a catalog that spans vendors. Your application code does not change when a provider does.

02

Multi-provider routing

Send each request to a deployment that is enabled, priced and available — cheapest, fastest or balanced.

03

Metering and prepaid credit

Token usage and cost are recorded as they happen, and a prepaid balance keeps spending where you put it.

04

Pricing and markup

Input price, output price and platform markup live in one place, each with the period it applies to.

05

Resellers and commission

Referral attribution, accrued commission and payouts are built in, so channel partners grow with you.

06

OpenAI-compatible, with SSE

Keep the SDK and the request shape you already use, streaming included. Migrating costs you a base URL.

QUICK START

Your first call, in minutes

Every public endpoint lives under /v1. The API base is https://api.ontosphere.ai/v1. Create an API key and call it with curl or the OpenAI SDK.

Read the full API reference → Gateway health
Chat completionPOST
curl https://api.ontosphere.ai/v1/chat/completions \
  -H "Authorization: Bearer rt-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4o",
       "messages":[{"role":"user","content":"Hello"}]}'
List modelsGET
curl https://api.ontosphere.ai/v1/models \
  -H "Authorization: Bearer rt-..."