sarvam/sarvam-30bOpen WeightsEfficient Indian-language reasoning model for chat, coding, and multilingual work
Benchmark Pricing$0.02 / 1M in$0.10 / 1M out
Context: 128,000 tokens•Max Output: 128,000 tokens•Released: 2026-02-18
TECHNICAL SPECIFICATIONS
Context Window128,000128K tokens
Max Output128,000128K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ Sarvam 30B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.
MCP Context Window Recommendations
With a context capacity of 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.
API CALL INVOCATION EXAMPLE
// Example: Calling Sarvam 30B via OpenAI SDK
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.SARVAM_API_KEY,
});
const response = await client.chat.completions.create({
model: "sarvam/sarvam-30b",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
FastRoutersarvam/sarvam-30b
$0.02 / $0.10
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
MODEL RESOURCES
More Models by Sarvam AI
Alternative and family models from the same lab
Sarvam 105B
sarvam/sarvam-105b•Sarvam AI
Flagship Indian-language reasoning model for enterprise multilingual applications
131.1K out max
In: $0.16 • Out: $0.63
Sarvam AISarvam-M
sarvam/sarvam-m•Sarvam AI
Hybrid-reasoning multilingual model for Indian languages built on Mistral Small
32.8K out max
In: Free • Out: Free
Sarvam AI