chat

Generate multilingual chat completions via Sarvam AI's OpenAI-compatible API.

Updated Jun 18, 2026
One-click install
npx skills add https://github.com/abhishekmmgn/didactic-invention --skill chat-abhishekmmgn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chat
Source: https://github.com/abhishekmmgn/didactic-invention/tree/main/.agents/skills/chat
Command: npx skills add https://github.com/abhishekmmgn/didactic-invention --skill chat-abhishekmmgn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Chat completions using Sarvam AI LLMs (Sarvam-105B, Sarvam-30B). Handles AI chat, text generation, reasoning, coding, and multilingual conversations in Indian languages. OpenAI-compatible API. Use when building chatbots, Q&A systems, agents, or any LLM feature targeting Indian users.

Core Features & Use Cases

  • Models: sarvam-105b (128K context) for complex reasoning and agentic workflows, sarvam-30b (64K) for real-time chat and conversational AI, sarvam-105b-32k (32K) for cost-efficient deployments, sarvam-30b-16k (16K) for lightweight use.
  • OpenAI-compatible API surface with header-based authentication using api-subscription-key and base URL: https://api.sarvam.ai/v1
  • Streaming support and multilingual conversations across Indian languages.
  • Use cases include building chatbots, Q&A systems, agents, or any LLM-powered conversational feature for Indian users.

Quick Start

Call the Sarvam API's chat.completions with model sarvam-30b and a user message to obtain a reply.

Frequently Asked Questions about chat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate multilingual chat completions for Indian languages using an OpenAI-compatible API?

You can implement multilingual chat completions for Indian languages by calling the Sarvam AI API at https://api.sarvam.ai/v1. This OpenAI-compatible endpoint uses header-based authentication with an api-subscription-key to process conversational AI requests.

Which Sarvam AI models should I use for real-time chat versus complex reasoning tasks?

For complex reasoning and agentic workflows, use the sarvam-105b model with its 128K context window. For real-time chat and conversational AI, sarvam-30b with a 64K context is recommended, while sarvam-30b-16k suits lightweight deployments.

Can I use streaming support with Sarvam AI LLMs for live chatbot responses?

Yes, streaming support is available when using Sarvam AI LLMs for chat completions. This allows you to stream live conversational AI responses directly through the OpenAI-compatible API surface to your chatbot or Q&A system.

Does the Sarvam AI chat completions API require any specific dependencies or component installations?

No specific dependencies or components are required to use the Sarvam AI chat completions API. You simply need to authenticate via the api-subscription-key header and direct your requests to the base URL to generate multilingual text.

What is the most cost-efficient way to deploy Sarvam AI models for lightweight conversational features?

The most cost-efficient approach for lightweight conversational features is using the sarvam-30b-16k model with its 16K context window. Alternatively, sarvam-105b-32k offers a 32K context for cost-efficient deployments requiring more capacity.

How do I authenticate API requests when building Q&A systems with Sarvam AI?

You authenticate API requests for Q&A systems by including the api-subscription-key in your HTTP headers. This header-based authentication method secures your calls to the Sarvam AI base URL for generating chat completions.