explainx.ai350K+ learn from us
TrendingAI News TodayPathwaysSkills
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • TL;DR: what Token Factory is, in a table
  • Which models can you call?
  • What does it cost, and is the "80% cheaper" claim right?
  • How fast is it, according to Sarvam?
  • Why caching is the real story
  • What does this mean for what you build or pay?
  • How do you try it today?
  • What are the open questions?
  • Related reading
← Back to blog

explainx / blog

Sarvam Token Factory: India-Hosted Inference for Open-Weight Models, Priced in Rupees

Sarvam AI, AI Inference, Open Weights, India AI, AI Pricing

Part of Open-Weight Models

Sarvam Token Factory is live: Sarvam 105B at ₹10 per million input tokens, plus Gemma 4, GLM 5.3 and DeepSeek V4.1 on India GPUs. Prices and caveats.

Nov 16, 2026·9 min read·Yash Thakker
add explainx.ai
go deep
Sarvam Token Factory: India-Hosted Inference for Open-Weight Models, Priced in Rupees

Sarvam has opened Token Factory to everyone. It is a hosted inference API that serves Sarvam's own 105B model and several open-weight models from other labs on GPUs in India, billed in rupees. Sarvam announced it on November 16, 2026, and says it matches leading inference providers on performance and reliability. The cheapest chat model on the list, Sarvam 105B, costs ₹10 per million input tokens and ₹25 per million output tokens.

Every speed and cache figure below comes from Sarvam, not from an independent test. The prices come from Sarvam's own pricing page, which we read on the launch day. We could not open the signed-in Token Factory console, so we have not run a request through it ourselves.

TL;DR: what Token Factory is, in a table

table · 2 cols
QuestionAnswer
What is it?A managed API for open-weight LLMs, run on Sarvam's GPUs in India
Is it open to everyone?Yes, as of November 16, 2026
API shapeOpenAI-compatible, base URL https://api.sarvam.ai/v2
Cheapest chat modelSarvam 105B: ₹10 input, ₹0.25 cached input, ₹25 output per 1M tokens
Gemma 4 31B₹35 input, ₹10 cached, ₹90 output per 1M tokens
DeepSeek V4.1 Flash 1017₹14 input, ₹0.25 cached, ₹55 output (introductory, through end of 2026)
CurrencyIndian rupees
Rate limit on pay as you go50 requests per minute on gemma4, glm5.3, deepseekv4.1-flash-1017; 60 on Sarvam 105B
Who checked the speed claims?Sarvam only so far
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

Which models can you call?

Sarvam says the launch catalogue covers its own models and "the full range of best-in-class open-weight models." The docs list these model IDs.

table · 4 cols
ModelModel IDAccessNotes
Sarvam 105Bsarvam-105bServerlessIndian-language reasoning, coding, agents
Sarvam 105B Conversationssarvam-105b-conversationsServerlessTuned for real-time dialogue
GLM-5.3glm5.3Serverless₹126 in, ₹390 out
GLM-5.3 Flashglm5.3-flashServerlessImage input, ₹13.5 in, ₹45 out
Gemma 4 31Bgemma4ServerlessImages and low-latency answers
DeepSeek V4.1 Flash 1017deepseekv4.1-flash-1017ServerlessLong documents, cost-sensitive reasoning
DeepSeek V4.1 Flash 1017 Interactivedeepseekv4.1-flash-1017-interactiveServerless₹25 in, ₹105 out, aimed at coding agents
DeepSeek V4 Prodeepseekv4-proProvisioned throughputEnabled per organisation
Kimi K3.1 Prokimi-k3.1-proProvisioned throughput₹200 in, ₹950 out
Qwen 3.8 27Bqwen38-27bProvisioned throughputEnabled per organisation
Sarvam Prismsarvam-prismServerlessDecision model, called through POST /v2/systemone
Clef, EmbeddingGemma 2clef, embeddinggemma-2Provisioned throughputInput-only billing

Two notes on that table. The docs list Kimi K3.1 Pro, while the AlphaSignal launch report also lists Kimi K3, so check the live catalogue for the exact set. "Provisioned throughput" means the model is turned on per organisation, so you cannot call it from a fresh pay-as-you-go key.

What does it cost, and is the "80% cheaper" claim right?

Sarvam's launch thread says Sarvam 105B is "80% cheaper than Gemma 4 31B." We ran the arithmetic on the list prices from the pricing page.

table · 4 cols
WorkloadSarvam 105BGemma 4 31BSaving
1M input tokens₹10₹3571%
1M output tokens₹25₹9072%
1M input + 200K output₹15₹5372%
1M cached input₹0.25₹1098%

The saving is large, but on uncached list prices it lands near 72%, not 80%. The thread does not show how Sarvam reached 80%. A workload with heavy cache hits would push the gap higher, because cached input on Sarvam 105B is only ₹0.25. If you rely on that number for a budget, run your own token mix instead.

The price is also an introductory price. Sarvam says introductory pricing on some models runs through the end of 2026. Plan for the rate to change.

What do the plans change?

Language model prices are the same on every plan. The plans change limits and support:

  • Pay as you go: no monthly fee, 50 to 60 requests per minute.
  • Pro: ₹9,999 per month, 200 requests per minute.
  • Growth: ₹49,999 per month, up to 1,000 requests per minute on default models.
  • Business: ₹1,99,999 per month, includes ₹1,99,999 of credits.
  • Enterprise: custom.

The pricing page does not publish rate limits for every model or for Business and Enterprise.

How fast is it, according to Sarvam?

Sarvam published several speed claims in its thread. They are vendor numbers.

  • Sarvam 105B: first token in 200 ms, with single-user throughput of 330 tokens per second. Sarvam says it optimised kernels, trained custom draft models and served the model in prefill and decode disaggregated mode, for a 2.86x throughput gain over its bf16 version.
  • Gemma 4 31B: first token 5x sooner and 1.6x more tokens per second than the only other provider serving it. AlphaSignal reports 0.40 s to first token on a 10,000-token prompt and 308 against 193 tokens per second. Sarvam says it already serves 150 billion tokens per day of this model. For a different speed claim on the same model, see our Gemma 4 31B on Cerebras post.
  • DeepSeek V4.1 Flash 1017: an Interactive endpoint at 200 tokens per second per user for coding agents, and a cheaper Standard endpoint for background and batch work. For earlier context on this family, read DeepSeek V4 Flash with Codex and the Responses API.
  • GLM 5.3 Flash and Kimi K3.1 Pro: up to 2.1x sooner first token on GLM 5.3 Flash than the stock open-source stack, and up to 1.9x more tokens per GPU on Kimi K3.1 Pro against the best open stack Sarvam compared.

A cache fast lane beside a slow road, showing how prefix caching cuts latency on Sarvam Token FactoryA cache fast lane beside a slow road, showing how prefix caching cuts latency on Sarvam Token Factory

Why caching is the real story

The cheapest token is the one you do not recompute. Sarvam says it runs a three-tier cache that keeps context across requests, and that its router and admission layer account for the distributed cache. On DeepSeek V4.1 Flash, 95.7% of prompt tokens are served from cache across more than 450 billion tokens a day.

This matters most for coding agents. Agent prompts repeat the same long prefix on every turn. AlphaSignal reports that GLM 5.3 agent prompts average 131,000 tokens. When the prefix is cached, you pay the cached input rate: ₹0.25 per million on DeepSeek V4.1 Flash, against ₹14 uncached. That is a 98% cut on the repeated part.

Sarvam also describes the engineering behind its numbers, per the AlphaSignal summary:

  • A skipped clamping step in a GLM 5.3 Flash kernel pushed output deviations to 165%. A fused replacement kernel fixed it and ran about 40% faster.
  • Moving GLM 5.3 from FP8 on SGLang to MXFP8 on vLLM raised uncached prefill from 3,700 to 7,600 tokens per second per GPU and halved p95 time to first token. Sarvam's thread puts it as "halves time to first token and doubles throughput."
  • Aligning cache block sizes on DeepSeek V4.1 Flash 1017 lifted the cold-cache hit rate from 37.1% to 99.8%.

These are good signs of real operations work. They are still self-reported, and none of them tells you what your own prompts will see.

What does this mean for what you build or pay?

If you build in India, or serve Indian users, three things change.

  1. You can pay in rupees. Many Indian teams pay foreign inference vendors in dollars and carry exchange and card fees. A rupee invoice is simpler for finance teams.
  2. Latency can drop. A call that stays in India skips an overseas round trip. For voice and chat, the first-token time Sarvam quotes is what users feel. Test it from your own region.
  3. Data stays closer to home. Sarvam says requests run on Sarvam-operated GPUs in India, that zero data retention is available on request, that the managed service carries a 99.95% uptime SLA, and that regulated customers can deploy on-premises. Treat those as claims to confirm in a contract. The API docs page we read does not state residency terms.

Data crossing a boundary, showing why India-hosted LLM inference matters for data residencyData crossing a boundary, showing why India-hosted LLM inference matters for data residency

Language cost matters too. Hindi and other Indian languages often need more tokens per sentence than English, as we showed in our tokenizer tax analysis. A lower per-token price helps most on those workloads. A model tuned for Indian languages may also need fewer tokens for the same text, but you should measure that on your own data.

How do you try it today?

Sarvam says you switch from OpenAI by changing the base URL and API key and setting the model field. A minimal call looks like this. It follows Sarvam's description of the API, and we have not run it ourselves.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.sarvam.ai/v2",
    api_key="YOUR_SARVAM_API_KEY",
)

resp = client.chat.completions.create(
    model="sarvam-105b",
    messages=[{"role": "user", "content": "Explain UPI in two lines, in Hindi."}],
    stream=True,
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")

The docs also show a cURL option that uses an api-subscription-key header, and a Sarvam SDK path. Token Factory uses the same API key and credits as the other Sarvam APIs. The login page for the console is gated, so you need an account first. Sarvam links migration guides for moving from OpenRouter, Fireworks AI and Together AI.

A short test plan, in order:

  1. Pick one real workload, such as a support-chat prompt or a coding-agent loop.
  2. Run 200 requests on your current provider and on sarvam-105b, with the same prompts.
  3. Record first-token time, tokens per second, cache-hit share and cost in rupees.
  4. Compare output quality on a held-out sample you can score.
  5. Only then move traffic.

What are the open questions?

  • Independent benchmarks. Sarvam compares itself with Together, Fireworks, Baseten, DeepInfra and InferenceX. We have not seen outside replication.
  • The 80% figure. It does not match the list prices we read. Ask Sarvam for the method.
  • Introductory pricing. It can rise after 2026.
  • Provisioned models. DeepSeek V4 Pro, Kimi K3.1 Pro and Qwen 3.8 27B need per-organisation enablement.
  • Residency terms. Get the data-processing wording in writing before you send regulated data.
  • Model quality. Cheaper tokens do not help if the model fails your task. Evaluate first.

For the model side of this story, read our coverage of Sarvam Prism, which is also served on Token Factory. For the bigger picture of Indian AI, see the Sarvam Epoch recap, the Sarvam models and API guide and the IndiaAI Mission status report. If you compare Asian open-weight models on price, our OpenRouter token share analysis gives the market context.

Related reading

  • Sarvam Prism decision model
  • Sarvam Epoch 2026 announcements
  • Sarvam AI models and API guide
  • India sovereign AI status
  • Tokenizer tax for non-English languages
  • Gemma 4 31B on Cerebras
  • DeepSeek V4 Flash with Codex
  • Asia AI models on OpenRouter

Official sources: Token Factory docs, Sarvam pricing and rate limits and Sarvam's launch thread on X.

Prices, limits and model lists reflect Sarvam's documentation and launch thread on November 16, 2026. Introductory pricing and model availability may change.

Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Nov 3, 2026

Sarvam Prism: Open-Weights Decision Model Built on Sarvam 105B Answers in 44 ms

Sarvam released Prism, a System One decision model built on its 105B base. It scores options in one forward pass, claims the best score under 100 ms, and ships with open weights under Apache 2.0.

Nov 16, 2026

Tencent Hy4 Flash Launches: 224B MoE at 1/20 the Cost of Hy4 for Office Work

On November 16, 2026, Tencent Hunyuan introduced Hy4 flash, its first Flash-tier model: 224 billion parameters with 12 billion active per token, multimodal inputs, and a 1 million token window. Tencent says per-task cost on internal WorkIndex runs is one-twentieth of full Hy4 for everyday office work.

Sep 22, 2026

Startups Are Switching to Open-Weight Models to Save Money

A pattern surfaced in Brex's own customer payments data on September 21, 2026: early-stage companies test with closed models like OpenAI's, then switch to fine-tuned open-weight versions as they scale, recovering margin and getting better performance SLAs. Harvey, the legal AI company, went from negative margins to profitability this way. Here's the pattern, the named examples, and what it means if you're deciding where to run production inference today.