Sarvam AI Opens Sarvam Token Factory to All Developers

Sarvam AI's Token Factory runs its own and open-weight AI models on GPU clusters in India through one API.

Sarvam Token Factory: Sarvam AI logo with co-founders Vivek Raghavan and Pratyush Kumar over a server rack photo

Key Takeaways

  • Sarvam AI opened Sarvam Token Factory to all developers and enterprises on November 16, 2026.
  • It runs Sarvam 105B and open-weight models such as DeepSeek V4.1 Flash, Kimi K3.1 Pro and Gemma 4 31B on GPUs in India.
  • DeepSeek V4.1 Flash Standard has an introductory price of Rs 14 per million input tokens and Rs 55 per million output tokens.
  • The DeepSeek V4.1 Flash Interactive endpoint, built for coding agents, costs Rs 25 per million input tokens and Rs 105 per million output tokens.
  • Sarvam says prompts stay on GPUs in India.
Table of Contents 7 sections
  1. Sarvam Token Factory at a glance
  2. Sarvam Token Factory keeps prompts on GPUs in India
  3. How Sarvam AI got to Token Factory
  4. Sarvam's prices for DeepSeek V4.1 Flash on Token Factory
  5. Sarvam on building an AI stack without lock-in
  6. Where Sarvam Token Factory stands after launch
  7. FAQs

Sarvam AI launched Sarvam Token Factory for everyone on November 16, 2026, opening its India-hosted AI inference platform to all developers and enterprises. The service runs Sarvam's own models and open-weight models from other AI labs on GPU clusters in India, through one OpenAI-compatible API.

The models on offer include Sarvam 105B, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, Kimi K3.1 Pro and Google's Gemma 4 31B. Customers can choose dedicated GPU capacity.

Sarvam Token Factory at a glance

DetailValue
CompanySarvam AI, Bengaluru
ProductSarvam Token Factory, an AI inference service
Open to everyone fromNovember 16, 2026
Where models runGPU clusters in India
How developers connectOne OpenAI-compatible API
Models includeSarvam 105B, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, Kimi K3.1 Pro, Gemma 4 31B
GPU capacityDedicated
DeepSeek V4.1 Flash Standard, introductory priceRs 14 per million input tokens, Rs 55 per million output tokens

Sarvam Token Factory keeps prompts on GPUs in India

Sarvam says prompts sent to Token Factory run on GPUs in India and are not passed on to the overseas APIs of the companies that built the models. It also runs the same inference stack on premises for what it calls critical institutions, and offers that option to enterprises.

How Sarvam AI got to Token Factory

WhenWhat happened
2023Vivek Raghavan and Pratyush Kumar founded Sarvam AI in Bengaluru
November 2026Sashikumar Sreedharan joins Sarvam as President and Chief Business Officer
November 16, 2026Sarvam launches Sarvam Token Factory for everyone

Sarvam's prices for DeepSeek V4.1 Flash on Token Factory

DeepSeek V4.1 Flash comes through two endpoints. Sarvam says the Interactive endpoint, built for coding agents, runs at about 200 tokens per second per user and costs Rs 25 per million input tokens and Rs 105 per million output tokens. The Standard endpoint, for background and batch work, has an introductory price of Rs 14 for input and Rs 55 for output per million tokens.

Sarvam on building an AI stack without lock-in

"Today, we are launching Sarvam Token Factory for everyone."

Sarvam AI, in its launch post

"Teams can choose the models that fit their workloads and build an AI stack they own, without lock-in."

Sarvam AI, in its launch post

Where Sarvam Token Factory stands after launch

Sarvam Token Factory is now open to all developers and enterprises, with Sarvam 105B and open-weight models from DeepSeek, Kimi, GLM and Gemma served from GPUs in India. Customers can choose dedicated GPU capacity.

More news

Join Us Add as preferred source
Share

Frequently Asked Questions

What is Sarvam Token Factory?

Sarvam Token Factory is Sarvam AI's inference service that runs Sarvam's own models and open-weight models from other labs on GPU clusters in India, through one OpenAI-compatible API.

When did Sarvam Token Factory open to everyone?

Sarvam AI launched Sarvam Token Factory for all developers and enterprises on November 16, 2026.

Which models can developers use on Sarvam Token Factory?

Sarvam Token Factory offers models including Sarvam 105B, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, Kimi K3.1 Pro and Gemma 4 31B.

How do developers connect to Sarvam Token Factory?

Developers reach every model on Sarvam Token Factory through one OpenAI-compatible API.

How much does DeepSeek V4.1 Flash cost on Sarvam Token Factory?

On Sarvam Token Factory, the DeepSeek V4.1 Flash Standard endpoint has an introductory price of Rs 14 per million input tokens and Rs 55 per million output tokens, and the Interactive endpoint costs Rs 25 and Rs 105.

Where does Sarvam Token Factory process prompts?

Sarvam says Sarvam Token Factory runs prompts on GPUs in India rather than passing them to the model developers' overseas APIs.

Does Sarvam Token Factory send prompts abroad?

Sarvam says prompts sent to Sarvam Token Factory run on GPUs in India and are not passed to the model developers' overseas APIs.

Can enterprises run Sarvam Token Factory's stack on premises?

Sarvam runs the Sarvam Token Factory inference stack on premises for what it calls critical institutions and offers that option to enterprises.

Who founded Sarvam AI, the company behind Sarvam Token Factory?

Sarvam AI, the Bengaluru company behind Sarvam Token Factory, was founded by Vivek Raghavan and Pratyush Kumar in 2023.

How can customers buy GPU capacity on Sarvam Token Factory?

Sarvam Token Factory customers can choose dedicated GPU capacity.

What is Sarvam's Standard endpoint for DeepSeek V4.1 Flash used for?

Sarvam says the Standard endpoint for DeepSeek V4.1 Flash on Sarvam Token Factory is for background and batch work.

Who joined Sarvam AI as President in November 2026?

Sashikumar Sreedharan joined Sarvam AI, the company behind Sarvam Token Factory, as President and Chief Business Officer in November 2026.

More in AI