Skip to main content
Early accessGnani Evon v3.5 is now available as an API to early access registrants.

Overview

The Gnani Evon API generates text. You send a conversation, and the model writes the next message. Use it to answer questions, summarise, translate, classify, extract details, or hold a conversation. You can write prompts and get replies in Indian languages as well as English; see Indian languages. It follows OpenAI’s Chat Completions API. If your code already uses OpenAI’s SDK or API, you change the base URL and the API key, and it works.

Make your first request

cURL

Quickstart

Get a key, send your first request in cURL, Python or JavaScript, and read the reply.
The model thinks before it answers, by default. Its thinking is returned in message.reasoning, apart from the answer in message.content, and it counts as output tokens. For quick answers, send "reasoning_effort": "none" to turn thinking off. See Thinking.

How a conversation works

The API does not remember earlier requests. Each request carries the whole conversation, oldest message first, and the model answers the last one. To continue a chat, add the model’s reply and the user’s next message to messages and send it all again.
Every message needs content. The only exception is an assistant message that carries tool_calls.

Using OpenAI’s SDKs and tools

Point any OpenAI-compatible client at Gnani with two settings: Parameters that OpenAI’s SDKs do not know, such as top_k or enable_thinking, go in extra_body (Python) or straight into the request object (JavaScript):
What is different from OpenAI is listed in Migrating from OpenAI.

Gnani Python SDK

For Python, gnani-vachana has a sync client (GnaniLLMClient) and an async client (AsyncGnaniLLMClient). They are built on OpenAI’s SDK, so they are called the same way, and they set the base URL and read GNANI_API_KEY for you. Gnani-only parameters go in extra_body, as above.
See Python SDK: LLM.

Explore the docs

Quickstart

Send your first request in a few minutes.

Chat Completions reference

Every request parameter, the response objects, and a playground.

Python SDK

Sync and async clients, with install steps.

Guides

Streaming

Show the reply word by word while the model writes it.

Thinking

How the model reasons before answering, and when to turn it off.

Tool calling

Let the model call your functions and APIs.

JSON output

Get replies your code can parse.

Web search

Answer with up-to-date information from the web, with sources.

Indian languages

Prompt and reply in Indian languages, and control the reply language.

Migrating from OpenAI

What works as in OpenAI, what differs, and Gnani-only options.

Recipes

Voice agent

Speech to text, Evon and text to speech in one loop.

Support bot

Answer order questions with tool calling.

Intent classification

Classify Hindi and Kannada messages into JSON.

Web search Q&A

Answer with current information and cited sources.

Reference

Safety and privacy

What the safety filters refuse, and how personal data is masked.

Limits

Context size, rate limits and the daily token quota.

Errors

Every error, what it means, and when to retry.

Changelog

What changed in the API and the docs.