Sarvam 105B

Sarvam AIMCP Tool CallReasoning
sarvam/sarvam-105bOpen Weights

Flagship Indian-language reasoning model for enterprise multilingual applications

Benchmark Pricing$0.16 / 1M in$0.63 / 1M out$0.05 cache read
Context: 131,072 tokens•Max Output: 131,072 tokens•Released: 2026-02-18

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens
Max Output131,072131.1K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Sarvam 105B 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 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Sarvam 105B 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-105b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

3 providers
Sarvam AIsarvam-105b
$0.16 / $0.63$0.05 cache
NanoGPTsarvam-105b
$0.05 / $0.21$0.03 cache
FastRoutersarvam/sarvam-105b
$0.04 / $0.16$0.03 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.05 / 1M tokens, saving up to 67% on repetitive MCP tool definitions and system instructions.