Close Menu
NCIJ Network NCIJ Network
    What's Hot

    Video shows German police at pro-Palestine protest, not Swiss ‘burqa ban’ enforcement – Full Fact

    November 17, 2026

    Democrats Promised Lower Prices. What Can They Actually Do?

    November 17, 2026

    Ed Miliband announces first sanctions on Israeli firms working in West Bank | West Bank

    November 17, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Video shows German police at pro-Palestine protest, not Swiss ‘burqa ban’ enforcement – Full Fact
    • Democrats Promised Lower Prices. What Can They Actually Do?
    • Ed Miliband announces first sanctions on Israeli firms working in West Bank | West Bank
    • How Revolut raises ambition without lowering the bar
    • An ancient virus may help explain what makes the human brain different
    • The power of the paddy: Japan looks to rice fields to help mitigate flooding
    • Fugro completes ultra-deepwater survey offshore Angola
    • Democrats in Congress Want to Ban Data Centers on Federally Managed Public Lands — ProPublica
    • About
      • Our Team
      • Editorial Policy
      • Editorial Independence
      • International Support
    • Trust & Standards
      • AI Usage Policy
      • Conflict of Interest Policy
      • Corrections Policy
      • Ethics Policy
      • Fact-Checking Policy
      • Source Protection
    • Get Involved
      • Guide for Sources
      • Support Independent Journalism
    • Legal
      • Cookie Policy
      • Privacy Policy
      • Terms of Use
    Facebook X (Twitter) Instagram
    NCIJ Network NCIJ Network
    Tuesday, November 17
    • Home
    • World
    • Ai
    • Business
    • Politics
    • Health
    • Crypto
    • Science
    • Technology
    • Cybersecurity
    • Defense & Security
    • Economy
    • Energy
    • Europe
    • More
      • Fact Check
      • Investigations
      • Opinion & Analysis
      • Environment
    NCIJ Network NCIJ Network
    Home»Artificial Intelligence

    Sarvam Launches Sarvam Token Factory: Bringing India-Hosted Inference to 8 Open Models

    NCIJ NETWNCIJ NETWORKBy NCIJ NETWNCIJ NETWORKNovember 17, 2026 Artificial Intelligence No Comments3 Mins Read
    Share
    Facebook Twitter LinkedIn Pinterest Email

    Sarvam has opened Sarvam Token Factory to everyone. Sarvam Token Factory is an inference platform from Sarvam that serves its own models and open-weight models from GPU clusters in India. Developers reach every model through one OpenAI-compatible API. For India-based teams, this means low-latency tokens without sending traffic to overseas clouds. You can check the deployment options and specs here through our GPULeaderboard.com chrome extension.

    TL;DR

    • Size: 8 models listed at launch, including Sarvam 105B (105B total, 9B active, 128K context), GLM 5.3, DeepSeek V4.1 Flash 1017, Kimi K3.1 Pro and Gemma 4 31B.
    • Runs on: NVIDIA B200 clusters in India. Sarvam 105B now fits on 1 B200 per replica. On-premise deployment is offered to enterprises.
    • Performance: Fastest first token from Mumbai on most tested cases, per Sarvam’s own measurements.
    • Best: Kimi K3.1 Pro at 6,177 tokens/s per GPU vs 3,213 for InferenceX, at 70 tokens/s per user (1.9x).

    What is Sarvam Token Factory?

    It is a managed inference stack, not a single model. Sarvam first previewed it as Sarvam Inference at its Epoch event. The launch post lists 8 models: Sarvam 105B, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro, Kimi K3, Kimi K3.1 Pro and Gemma 4 31B.

    The docs split them into 2 groups. Pay-as-you-go models run on shared endpoints. DeepSeek V4 Pro, Kimi K3.1 Pro, Qwen 3.8 27B, Clef and EmbeddingGemma 2 need Provisioned Throughput, enabled per organisation.

    How does it work?

    The stack has 3 layers around a shared cache:

    • Control plane: a cache-aware router, admission control and a planner.
    • Inference engine: separate GPU pools for prefill and decode.
    • Cache: GPU memory plus a shared G3 store built on Mooncake.

    It builds on vLLM, SGLang, Dynamo, Mooncake, NIXL, DeepEP, DeepGEMM and FlashInfer. An orchestrator agent proposes experiments, and an engineer approves each deployment.

    Caching drives most of the gains. DeepSeek V4.1 Flash serves 450B+ tokens per day, with 95.7% of prompt tokens served from cache. On GLM 5.3, the planner cut prefill GPU-hours from 32.3 to 17.1 under the same replayed load.

    For Sarvam 105B, MXFP8 weights plus speculative decoding raised output throughput about 2.2x. That cut each replica from 2 B200s to 1. Sarvam says none of these changes reduced accuracy.

    How fast is it? Benchmarks

    All numbers below come from Sarvam’s launch post. They are self-reported.

    • Sarvam 105B: 0.2 s first token and 330 tokens/s for a single user.
    • Gemma 4 31B (10K prompt, Mumbai): 0.40 s first token and 308 tokens/s, vs 2.00 s and 193 tokens/s at the only other provider.
    • Kimi K3.1 Pro (16 B200s): 6,177 vs 3,213 tokens/s per GPU against InferenceX at 70 tokens/s per user.
    • Heavy agent load (72 sessions): median first token 0.8 s vs 11.6 s for InferenceX.
    • GLM 5.3 Flash (64 sessions): p99 first token 3.2 s vs 14.1 s for stock vLLM and Dynamo.

    The results are not a clean sweep. On DeepSeek V4.1 Flash with a 10K prompt, Together posts 0.71 s first token vs Sarvam’s 0.90 s. Together also streams faster, at 278 tokens/s vs 130 on Sarvam Standard.

    ‘}).join(”);requestAnimationFrame(function(){setTimeout(function(){el.querySelectorAll(‘i’).forEach(function(i){i.style.width=i.dataset.w+’%’})},30)})}
    var TN={d1:’DeepSeek V4.1 Flash, 1K prompt’,d10:’DeepSeek V4.1 Flash, 10K prompt’,g1:’GLM 5.3, 1K prompt’,g10:’GLM 5.3, 10K prompt’};function ttft(k){cur=k;document.getElementById(‘stf-th’).textContent=”Time to first token from Mumbai, “+TN[k]+’ (lower is better)’;bars(document.getElementById(‘stf-ttft’),D[k],2.3,’ s’)}
    R.querySelectorAll(‘[data-k]’).forEach(function(b){b.onclick=function(){R.querySelectorAll(‘[data-k]’).forEach(function(x){x.classList.remove(‘on’)});b.classList.add(‘on’);ttft(b.dataset.k)}});
    function tp(){bars(document.getElementById(‘stf-tp’),[[‘Sarvam Interactive’,200],[‘Sarvam Standard’,130],[‘Together’,278],[‘Fireworks’,193],[‘Baseten’,165],[‘DeepSeek API’,60]],290,”)}
    R.querySelectorAll(‘.cd’).forEach(function(c){c.onclick=function(){c.classList.toggle(‘op’);setTimeout(post,350)}});
    var P=[[‘Sarvam 105B’,10,25],[‘DeepSeek V4.1 Flash 1017’,14,55],[‘GLM 5.3 Flash’,13.5,45],[‘Gemma 4 31B’,35,90],[‘GLM 5.3’,126,390]];
    function price(){var a=+document.getElementById(‘stf-in’).value,b=+document.getElementById(‘stf-out’).value;document.getElementById(‘stf-iv’).textContent=a;document.getElementById(‘stf-ov’).textContent=b;
    document.getElementById(‘stf-pt’).innerHTML=P.map(function(p){return ‘

    ‘+p[0]+’ ₹’+p[1]+’ / ₹’+p[2]+’ ₹’+Math.round(a*p[1]+b*p[2]).toLocaleString(‘en-IN’)+’

    ‘}).join(”)}
    document.getElementById(‘stf-in’).oninput=price;document.getElementById(‘stf-out’).oninput=price;price();
    ttft(‘d1’);
    window.addEventListener(‘load’,post);window.addEventListener(‘resize’,post);setTimeout(post,300);
    })();

    bringing factory IndiaHosted Inference Launches models open Sarvam token
    NCIJ NETWNCIJ NETWORK
    • Website

    Keep Reading

    How Revolut raises ambition without lowering the bar

    The King’s Trust and OpenAI launch £1m partnership

    Our first phase of embedded assessments

    Broadening access to AI for scientists

    Trump Says He’s Open to Reinstatement of Jensen Huang as Nvidia Chief

    Hark Releases Handoff², a 2x Faster Computer-Use Agent for Hark Pro

    Add A Comment
    Leave A Reply Cancel Reply

    Editors Picks

    Video shows German police at pro-Palestine protest, not Swiss ‘burqa ban’ enforcement – Full Fact

    November 17, 2026

    Democrats Promised Lower Prices. What Can They Actually Do?

    November 17, 2026

    Ed Miliband announces first sanctions on Israeli firms working in West Bank | West Bank

    November 17, 2026

    How Revolut raises ambition without lowering the bar

    November 17, 2026
    Latest Posts

    FCC officially decides gigabit speeds are too good for you

    August 20, 2026

    Reform UK hates ‘Mickey Mouse’ degrees – apprenticeships in dodgy crypto, anyone? | John Crace

    August 20, 2026

    Belgian car salesman becomes prince after royal parentage confirmed

    August 20, 2026

    Subscribe to News

    Get the latest sports news from NewsSite about world, sports and politics.

    NCIJ Network is an independent digital news platform delivering trusted investigative journalism, European and global news, in-depth analysis, and fact-based reporting with accuracy, transparency, and integrity.

    Facebook X (Twitter) Instagram Pinterest YouTube

    Video shows German police at pro-Palestine protest, not Swiss ‘burqa ban’ enforcement – Full Fact

    November 17, 2026

    Democrats Promised Lower Prices. What Can They Actually Do?

    November 17, 2026

    Ed Miliband announces first sanctions on Israeli firms working in West Bank | West Bank

    November 17, 2026

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    Type above and press Enter to search. Press Esc to cancel.