Serverless

Access Abhigya models through an OpenAI-compatible API.

Run Abhigya models through an OpenAI-compatible API. Add credits, create an API key, and pay per token.

Get an API key

Connect

Setting	Value
Base URL	`https://api.abhigya.ai/v1`
Authentication	`Authorization: Bearer <YOUR_ABHIGYA_API_KEY>`

Send a request

curl -sS https://api.abhigya.ai/v1/chat/completions \
  -H "Authorization: Bearer $ABHIGYA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen2.5-7b-instruct",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 128
  }'

API

Serverless exposes one endpoint, Chat Completions: POST /v1/chat/completions. It supports streaming, tools, structured outputs, and reasoning.

To use an SDK, point the OpenAI SDK's base URL at https://api.abhigya.ai/v1 and pass your Abhigya API key.

Available models

List available models and their capabilities:

curl -sS https://api.abhigya.ai/v1/models \
  -H "Authorization: Bearer $ABHIGYA_API_KEY"

Use a model's id in your requests. See Models and Capabilities for context limits, per-API capability flags, and pricing.

Zero Data Retention

Zero Data Retention is enabled by default for every request. Request data is held only in memory and is deleted after the response is returned. See the Zero Data Retention page and Data privacy for details.

Reference

Errors and Rate Limits: error format, error codes, retries, and 429 handling.
Usage and Billing: token usage in responses, prompt caching, and billing.

Support

For help, contact contact@abhigya.ai. Include the request ID when you can. Never share your API key.