Back to Models

Sarvam 105B (high)

![Sarvam](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fsarvam_small.png&w=32&q=75)Sarvam
18/ 57

Intelligence Score

Intelligence

18

#131 of 203 (top 65%)

Speed

130 tok/s

#53 of 131

Price

Free

per M tokens

Context Window

128K

tokens

Latency: 2ms (#85)

Score Breakdown

Quality Score30%
Speed Score19%
Cost Score100%

Similar Models

Llama 3.3 Nemotron Super 49B

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA

18intelligence

Llama 4 Maverick

![Meta](https://artificialanalysis.ai/img/logos/meta_small.svg)Meta

18intelligence

Magistral Small 1.2

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral

18intelligence

Nova 2.0 Lite

![Amazon](https://artificialanalysis.ai/img/logos/aws_small.svg)Amazon

18intelligence

Devstral Small 2

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral

19intelligence

Use This Model

Claude Code

claude --model sarvam-105b

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "sarvam-105b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("sarvam-105b"),
  prompt: "Hello",
});
Back to Models