Build with Omni API

Quickstart

https://omniquasar.com/api/proxy/v1

curl -X POST https://omniquasar.com/api/proxy/v1/chat/completions \
  -H "Authorization: Bearer omni_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OpenAI SDK examples

Use your existing OpenAI SDK shape. Replace the base URL and use an Omni API key.

curl -X POST https://omniquasar.com/api/proxy/v1/chat/completions \
  -H "Authorization: Bearer $OMNI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Environment variables

Keep API keys out of source code and reuse the same base URL across local scripts, servers, and workers.

OMNI_API_KEY=omni_your_key_here
OMNI_BASE_URL=https://omniquasar.com/api/proxy/v1

Authentication

All API requests require an API key passed as a Bearer token in the Authorization header.

Authorization: Bearer omni_your_key_here

• API keys are prefixed with omni_.
• Create, rotate, and revoke keys from the dashboard.
• Never share or commit your API key to source control.

Models

Choose a model based on your quality and cost requirements.

Credits & Billing

Usage is shown as USD value and metered internally in credits based on billable tokens: input tokens and output tokens. If the upstream provider reports cache creation or cache read tokens separately, Omni folds them into input tokens before billing; they are not billed as a separate third token category.

Formula: usage value = billable-token tier base value × model multiplier

Tiered deduction by billable tokens

Usage value options

Compatibility

API Reference

POST https://omniquasar.com/api/proxy/v1/chat/completions

Request Parameters

Non-streaming example

curl -X POST https://omniquasar.com/api/proxy/v1/chat/completions \
  -H "Authorization: Bearer omni_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

{
  "id": "chatcmpl-xxx",
  "model": "omni-fast",
  "choices": [{
    "message": { "role": "assistant", "content": "Hello! How can I help?" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 10, "completion_tokens": 12 }
}

Streaming example

curl -X POST https://omniquasar.com/api/proxy/v1/chat/completions \
  -H "Authorization: Bearer omni_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"model":"omni-fast","messages":[{"role":"user","content":"Hello!"}],"stream":true}'

data: {"choices":[{"delta":{"content":"Hello"}}]}
data: {"choices":[{"delta":{"content":"!"}}]}
data: [DONE]

Note: Omni API is powered by a stack of Claude models working together. When streaming is enabled, the connection is kept alive with SSE heartbeats during processing.

Error Codes

Retryable upstream failures, including upstream 502 responses, are normalized to 429 by the proxy so clients can use one backoff path.

Error response shape

{
  "error": {
    "message": "Insufficient credits",
    "type": "invalid_request_error",
    "param": null,
    "code": "insufficient_credits"
  }
}

Every proxy response includes an x-request-id header. Include that value when contacting support.

Debugging and retries