Sarvam Launches Token Factory for Localized Open-Source Model Inference in India
11/17/2026 — 11/17, 19:19·1 sources (all)·1 reports (all)
Key takeaways
- Sarvam has launched Token Factory, offering an OpenAI-compatible API powered by local GPU clusters in India. The service provides localized…
Background & analysis
On November 17, 2026, MarkTechPost reported that Sarvam has formally launched Sarvam Token Factory and opened it up to the general public. The service delivers inference through GPU clusters located in India, exposing a single, OpenAI-compatible API as the unified access point for open models.
In terms of model coverage, Sarvam Token Factory currently supports eight open models. The ones explicitly named are Sarvam 105B, GLM 5.3, DeepSeek V4.1 Flash, Kimi K3.1 Pro, and Gemma 4 31B, while the names of the remaining models are not provided in the available material. As far as the verifiable facts show, the situation now stands at the point where Sarvam Token Factory is publicly live and offering India-hosted inference for those eight open models, with no further details in the source material on access procedures, pricing, or what may follow. No additional parties, timelines, or statements about the service appear in the report, so no conclusions can be drawn beyond the launch itself.
AI-generated from 1 reports · updated 11 hours ago
- Heat index
- 69
- All sources
- 1
- All reports
- 1
- First seen
- 13 hours ago
Reports on this story headlines open the original
According to MarkTechPost, Sarvam has officially launched Sarvam Token Factory, making it open to everyone. Powered by GPU clusters hosted in India, it serves 8 open models including Sarvam 105B, GLM 5.3, DeepSeek V4.1 Flash, Kimi K3.1 Pro, and Gemma 4 31B through a single OpenAI-compatible API.
MarkTechPostAI score 71
Other stories people are talking about
- Heat index 1331Nvidia board establishes national security and export control committee25 sources
- Heat index 1027California Sues OpenAI Over Agent Intrusion Into Hugging Face19 sources
- Heat index 1006NewGPT-6.2 Astra and Sol Now Available on ChatGPT, API and Perplexity11 sources
- Heat index 934SurgeJensen Huang says he would return as Nvidia CEO and agrees to testify on Capitol Hill11 sources
- Heat index 852Anthropic guides IPO pricing at top of range or higher, with trading set for November 1911 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

