chat

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.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "chat" with this command: npx skills add sarvamai/skills/sarvamai-skills-chat

Chat Completions — Sarvam AI

[!IMPORTANT] Auth: api-subscription-key header — NOT Authorization: Bearer. Base URL: https://api.sarvam.ai/v1

Models

ModelContextBest For
sarvam-105b128KComplex reasoning, coding, agentic workflows
sarvam-30b64KReal-time chat, voice agents, conversational AI
sarvam-105b-32k32KCost-efficient 105B
sarvam-30b-16k16KCost-efficient 30B

Quick Start (Python)

from sarvamai import SarvamAI
client = SarvamAI()

response = client.chat.completions(
    model="sarvam-30b",
    messages=[{"role": "user", "content": "भारत की राजधानी क्या है?"}]
)
print(response.choices[0].message.content)

Streaming (Python)

for chunk in client.chat.completions(
    model="sarvam-30b",
    messages=[{"role": "user", "content": "Write a poem about India"}],
    stream=True
):
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Quick Start (JavaScript/TypeScript)

import { SarvamAIClient } from "sarvamai";

const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY" });

const response = await client.chat.completions({
    model: "sarvam-30b",
    messages: [{ role: "user", content: "भारत की राजधानी क्या है?" }]
});
console.log(response.choices[0].message.content);

OpenAI-Compatible (both languages)

from openai import OpenAI
client = OpenAI(api_key="your-key", base_url="https://api.sarvam.ai/v1")
response = client.chat.completions.create(model="sarvam-30b", messages=[...])

Gotchas

GotchaDetail
SDK methodPython: client.chat.completions(...), JS: client.chat.completions({...}) — no .create() in either. OpenAI SDK uses .create() as usual.
JS constructornew SarvamAIClient({ apiSubscriptionKey: "..." }) — NOT SarvamAI(). Key is passed explicitly.
content can be NoneModels produce reasoning_content before content. If max_tokens is too low, reasoning consumes the budget and content is None. Omit max_tokens or set 500+. Check reasoning_content as fallback.
reasoning_effortreasoning_effort="low"|"medium"|"high" for thinking mode. NOT thinking=True.

Full Docs

Fetch detailed parameters, tool calling, streaming, and examples from:

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Agent Network

Decentralized AI agent platform for discovering, connecting, chatting, trading skills with point-based system and leaderboard, featuring P2P networking and d...

Registry SourceRecently Updated
3650Profile unavailable
Automation

voice-agents

No summary provided by upstream source.

Repository SourceNeeds Review
General

speech-to-text

No summary provided by upstream source.

Repository SourceNeeds Review
General

translate

No summary provided by upstream source.

Repository SourceNeeds Review