AINewsnow

Sarvam AI Launches Token Factory, India-Hosted Inference for Open-Weight Models

This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.

Sarvam AI opened its Token Factory on November 16, 2026, serving eight open-weight models including Sarvam 105B, GLM 5.3, DeepSeek V4.1 Flash, Kimi K3.1 Pro and Gemma 4 31B from Indian GPU clusters via one OpenAI-compatible API.

Read the full story at AlphaSignal ↗

Timeline · 3 reports

  1. 2026-11-17 10:16 · Unite.AI
    Sarvam Opens India-Hosted Token Factory for Open-Weight Models
  2. 2026-11-17 09:51 · MarkTechPost
    Sarvam Launches Sarvam Token Factory: Bringing India-Hosted Inference to 8 Open Models
  3. 2026-11-16 13:37 · AlphaSignal
    Sarvam AI Launches Token Factory, Bringing Open-Model Inference to Indian GPUs

More stories

  1. Sarvam Launches India-Hosted Token Factory, Faces Backlash Over Chinese Model Offerings — Bloomberg AI
  2. DeepSeek vs Claude vs Kimi vs Codex vs Gemini: A 70-Call AI Ethics Test — DEV Community — AI
  3. Your eval set is the product. The prompt is just this week's implementation. — DEV Community — Machine Learning
  4. Alibaba's QwenWork Adds Third-Party Models From Kimi, GLM and DeepSeek — Pandaily
  5. Tencent launches Hy4 Flash at $0.07 per million tokens as AI price war intensifies — Business Insider AI
  6. AI Models Regularly Identify Civilians as Military Targets in Simulated Warfare Tests — Bloomberg AI
  7. Sarvam Prices Its 105B Model Below DeepSeek in New Token Factory — Forbes AI
  8. DeepSeek Removes Separate Fees for Model-Triggered Search and Web Fetch — Pandaily

Read the Daily Brief: the day's most important AI stories →