Sarvam AI

Sarvam-M

Open Weightsapache-2.0Released Jun 2026

Sarvam AI's 24B-parameter instruction-tuned model derived from Mistral-Small-3.1-24B, post-trained on English plus eleven major Indic languages (bn, hi, kn, gu, mr, ml, or, pa, ta, te). Delivers large relative gains on Indian-language, math, and programming benchmarks over its base model, with a hybrid reasoning mode for complex tasks.

Capabilities

chatcompletionfunction-callingcode-generationreasoning

Modalities

textcode

Context Window

131K tokens

Providers

available

Available from 2 providers

Cheapest

OpenRouter

$1.00/1M tokens

OpenRouter, Sarvam AI

Providers (2)

Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.

Provider	Pricing (per 1M)	Rate Limits	Regions	Health	Latency
OpenRouter	In: $0.25Out: $0.75	200 RPM / 200K TPM	us-east-1	Healthy	0ms
Sarvam AI	In: $0.50Out: $1.50	120 RPM / 200K TPM	ap-south-1	Healthy	0ms

Quick Start

Use this model via OpenRouter with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "sarvamai/sarvam-m",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

console.log(response.choices[0].message.content);

Using OpenRouter API • OpenAI-compatible SDK