Back to models
Sarvam AI
Sarvam-M
Open weightsapache-2.0Released Jun 13, 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.
ChatText completionFunction callingCode generationReasoningtext · code
Available from 2 providers
Cheapest
OpenRouter
$0.25 / $0.75
OpenRouter, Sarvam AI
Providers (2)
Sorted by total cost (input + output per 1M tokens). Select a row to view provider details.
| Provider | Pricing (per 1M) | Rate limits | Regions | Health | Latency |
|---|---|---|---|---|---|
| In: $0.25Out: $0.75 | 200 RPM / 200K TPM | us-east-1 | Healthy | 0ms |
| 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