Sarvam AI
Sarvam

Sarvam 105B Conversations

Sarvam 105B tuned for natural conversation in voice and chat agents, in Indian languages and English.

  • Chat
  • Indian languages
Serverless

Best suited for

  1. 01

    Voice agents

    Generate natural conversational responses between speech-to-text and text-to-speech models in a voice agent stack.

  2. 02

    Customer support agents

    Use tool calls to connect customer conversations to support actions in your application.

  3. 03

    Code-mixed dialogue

    Handle conversations that move between Indian languages, romanised text and English.

API usage

Build with the Sarvam SDK

pip install --upgrade sarvamaiV1 · Sarvam SDK · Chat Completions
from sarvamai import SarvamAI​client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")​response = client.chat.completions(    model="sarvam-105b-conversations",    messages=[        {"role": "user", "content": "who are you?"}    ],    temperature=1,    top_p=1,    max_tokens=100,)​print(response.choices[0].message.content)
  1. 01 Install the Sarvam SDK

    Install sarvamai for Python or JavaScript. Store your key in SARVAM_API_KEY.

  2. 02 Choose your model

    Use model ID sarvam-105b-conversations. The SDK calls https://api.sarvam.ai/v1/chat/completions for this example.

    V1 Chat Completions. Thinking is disabled for this short reply.

    API reference
  3. 03 Validate your application

    Check output quality, supported parameters and tool behaviour on representative requests before moving production traffic.

Read API docs

Frequently asked questions

Explore other models

View catalogue

Build with frontier open-weight models. Served from India.