Sarvam launches Token Factory: Indian GPU inference for open frontier models
itsOmSarraf_ · x · 2026-11-22
Indian AI company Sarvam launched Token Factory, an inference service running leading open models on its own GPUs in India — pitched as keeping data in-country, with rupee pricing, shared or dedicated capacity, and zero data retention on request.
Key details:
- OpenAI-compatible API (chat.completionsv2) for minimal-change model switching
- Hosted models include GLM 5.3, DeepSeek V4.1 Flash, and Gemma 4 31B
- 99.95% uptime backed by SLA, with autoscaling, active health checks, staged rollouts and rollbacks
- Claims faster time-to-first-token and output speed across its serving fleet
More from Infra
- Moore Threads rumored 64GB consumer GPU "Lushan" would double RTX 5090 VRAM — CeFurkan · 2026-11-22
- Researchers find cheap AI inference providers stealing keys and snooping on user requests — The Decoder · 2026-11-22
- Inkling Mini on a 5090: vLLM+DSPark+FP8 KV hits 300-350 tok/s — willcb · 2026-11-22
- Musk: Tesla's data is so vast it keeps less than a millionth of it — Scobleizer · 2026-11-22
- MLX beats llama.cpp 2x on M5 Pro for Inkling Mini, NVFP4 fallback to blame — xlr8harder · 2026-11-22
- Sovereign AI scorecard: Google Cloud tops index at 3.45, Alibaba Cloud last at 1.21 — aftahi_ai · 2026-11-22