# JarvisLabs | Indian inference provider profile and prices

[Directories](/directories/) › [Indian Inference](/india/) › JarvisLabs

![JarvisLabs logo](/logos/jarvislabs.png)

Verified

JarvisLabs Token Factory serves open models from Indian data centres with OpenAI-compatible chat completions and INR pricing.

Indian-owned India hosting Token factory

[Visit website ↗](https://jarvislabs.ai) [API docs ↗](https://models.jarvislabs.net/v1)

Overview Models Pricing Infrastructure Access Compliance Benchmarks Performance

## At a glance

Record

Legal entity

Jarvislabs (Indian entity; offices New Delhi)

Headquarters

New Delhi, India

Hosting region

India (New Delhi)

Group

Token factory

SLA

Not published

Website

[jarvislabs.ai](https://jarvislabs.ai)

## Summary

Scope

JarvisLabs Token Factory serves open models from Indian data centres with OpenAI-compatible chat completions and INR pricing.

No Responses API. Reasoning is billed as output. No cache-write fee.

[Source: jarvislabs.ai ↗](https://jarvislabs.ai) · Updated Nov 4, 2026

### API access

OpenAI chat completions only

Bearer

### Billing

Prices shown in INR. ₹474 minimum top-up. Non-refundable.

### KYC

Business account

### Compliance

No trainingPrompts not stored

## Key models

9 listed

DeepSeek V4 Flash 1M · per 1M tokens LLM ₹12.32 / ₹24.64 per 1M tokens

GLM-5.3 230K · per 1M tokens LLM ₹114.65 / ₹365.74 per 1M tokens

DeepSeek V4.1 Flash 1M · per 1M tokens Multimodal ₹6.63 / ₹46.43 per 1M tokens

DeepSeek V4.1 Flash Cyber 1M · per 1M tokens Multimodal ₹28.43 / ₹94.75 per 1M tokens

Gemma 4 26B A4B IT 256K · per 1M tokens Multimodal ₹10.42 / ₹35.06 per 1M tokens

Gemma 4 31B IT 256K · per 1M tokens Multimodal ₹13.27 / ₹37.9 per 1M tokens

GLM-5.3 Flash 1M · per 1M tokens Multimodal ₹13.27 / ₹42.64 per 1M tokens

Nemotron 3.5 Super VL 120B A12B 1M · per 1M tokens Multimodal ₹14.21 / ₹47.38 per 1M tokens

Qwen 3.8 27B 256K · per 1M tokens Multimodal ₹28.43 / ₹222.66 per 1M tokens

## Pricing

List rates · local currency · GST excluded

Model Type Input price Caching price Output price

DeepSeek V4 Flash1M · per 1M tokens LLM ₹12.32 ₹2.84 ₹24.64

GLM-5.3230K · per 1M tokens LLM ₹114.65 ₹20.85 ₹365.74

DeepSeek V4.1 Flash1M · per 1M tokens Multimodal ₹6.63 ₹0.28 ₹46.43

DeepSeek V4.1 Flash Cyber1M · per 1M tokens Multimodal ₹28.43 ₹0.57 ₹94.75

Gemma 4 26B A4B IT256K · per 1M tokens Multimodal ₹10.42 ₹4.74 ₹35.06

Gemma 4 31B IT256K · per 1M tokens Multimodal ₹13.27 ₹4.74 ₹37.9

GLM-5.3 Flash1M · per 1M tokens Multimodal ₹13.27 ₹2.84 ₹42.64

Nemotron 3.5 Super VL 120B A12B1M · per 1M tokens Multimodal ₹14.21 ₹1.89 ₹47.38

Qwen 3.8 27B256K · per 1M tokens Multimodal ₹28.43 ₹7.58 ₹222.66

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Prices exclude 18% GST where applicable. Prices shown in INR. ₹474 minimum top-up. Non-refundable.

## Infrastructure

Source-backed

Region**India**

Cities**New Delhi**

SLA**Not published**

API base**https://models.jarvislabs.net/v1**

Auth**Bearer**

Rate limit**Not published.**

## Access

Billing & API

API base**https://models.jarvislabs.net/v1**

Auth**Bearer**

Rate limit**Not published.**

SLA**Not published**

Prices shown in INR. ₹474 minimum top-up. Non-refundable.

## Compliance

Source-backed

DPA**Not published**

ZDR**token\_factory\_prompts\_not\_stored**

Training**no**

Retention**Token Factory prompts are not stored; retention is not published.**

DPO**support@jarvislabs.ai**

Certifications

None published

Subprocessors

Stripe (payments)

## Benchmarks

Coming soon

Coming soon.

## Performance

Coming soon

Latency

### Time to first token

Median and p95 response times for short and long prompts, measured from repeatable probes rather than vendor claims.

Coming soon

Throughput

### Tokens per second

Streaming output rate and request throughput under steady load, with concurrency and context length recorded.

Coming soon

Efficiency

### Cost per workload

Blended cost for a fixed workload, including cache reads and output tokens, so speed and price can be compared together.

Coming soon

Independent performance probes are being added. Vendor-reported numbers are not mixed into this section.

[NextSarvam AI](/india/providers/sarvam-ai)