API key

Get started

Quickstart

Create an API key, make your first request and stream a response. About five minutes with any OpenAI-compatible client.

1. Get an API key

Sign in to the dashboard, open API keys and choose Create key. The key (sk_p9_…) is shown once, so copy it into your environment straight away:

export P9_API_KEY="sk_p9_…"

No account yet? Choose Request early access on the sign-in page. When your request is approved you'll get an email to set your password, and your organisation starts with Rs 1,000 of credit.

2. Make a request

Paranine speaks OpenAI's chat completions API, so the OpenAI SDKs work as they are: set the base URL and the key, and use a Paranine model id.

curl https://sovereign.paranine.com/v1/chat/completions \
  -H "Authorization: Bearer $P9_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paranine/gpt-oss-120b(Global)",
    "messages": [
      {"role": "user", "content": "Explain what an inference gateway does, in two sentences."}
    ]
  }'

The reply is in choices[0].message.content, and usage holds the token counts you're billed on:

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "paranine/gpt-oss-120b(Global)",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "An inference gateway sits between…" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 21, "completion_tokens": 58, "total_tokens": 79 }
}

3. Stream the response

Add "stream": true and the reply arrives token by token as server-sent events, ending with data: [DONE].

curl -N https://sovereign.paranine.com/v1/chat/completions \
  -H "Authorization: Bearer $P9_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paranine/gpt-oss-120b(Global)",
    "stream": true,
    "messages": [{"role": "user", "content": "Count to ten, slowly."}]
  }'

4. See what it cost

Open Request logs in the dashboard. Every request appears within seconds, with its status, latency, tokens and cost in rupees.

Next

  • Models: every model id and its price.
  • API keys: limits you can put on a key, and how to rotate it.
  • Errors and retries: the statuses you'll meet, and what to do about each.

Something unclear or wrong on this page? Tell us. Machine-readable copies: llms.txt.