Chat Completions — Sarvam AI

Live in-chat completion → [sarvam-mcp](../sarvam-mcp) (sarvamtoolsllm_complete). This skill = SDK code.

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

Models

The fixed-context variants (sarvam-105b-32k, sarvam-30b-16k) are retired — base models serve their full context window directly.

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

Full Docs

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

• https://docs.sarvam.ai/llms.txt — comprehensive docs index
• Chat Completion Guide
• Model Specs
• Rate Limits