# NeevCloud | Indian inference provider profile and prices

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

![NeevCloud logo](/logos/neevcloud.png)

Verified

NeevCloud Model API offers Indian-hosted inference for open models, with daily free tokens and MeitY-empanelled compliance.

Indian-owned India hosting Inference cloud

[Visit website ↗](https://neevcloud.com) [API docs ↗](https://inference.ai.neevcloud.com/v1)

Overview Models Pricing Infrastructure Access Compliance Benchmarks Performance

## At a glance

Record

Legal entity

NeevAI SuperCloud Private Limited

Headquarters

Indore, Madhya Pradesh, India

Hosting region

India (Indore)

Group

Inference cloud

SLA

99.9%

Website

[neevcloud.com](https://neevcloud.com)

## Summary

Scope

NeevCloud Model API offers Indian-hosted inference for open models, with daily free tokens and MeitY-empanelled compliance.

Prices are set in INR and exclude 18% GST.

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

### API access

OpenAI-compatible

Bearer

### Billing

200,000 tokens per day plus 10,000 requests free.

### KYC

Business account

### Compliance

MeitYISO 27001SOC 2

## Key models

12 listed

Gemma 4 31B 256K · per 1M tokens Multimodal ₹18.97 / ₹56.9 per 1M tokens

Kimi K3 1M · per 1M tokens Multimodal ₹284.5 / ₹1422.48 per 1M tokens

GLM 5.2 1M · per 1M tokens LLM ₹88.19 / ₹284.5 per 1M tokens

MiniMax-M3 1M · per 1M tokens Multimodal ₹57.97 / ₹231.89 per 1M tokens

MiniMax-M2.7 205K · per 1M tokens LLM ₹28.99 / ₹115.95 per 1M tokens

MiniMax-M2.7-highspeed 205K · per 1M tokens LLM ₹57.97 / ₹231.89 per 1M tokens

DeepSeek-V3.2 128K · per 1M tokens LLM ₹27.05 / ₹40.58 per 1M tokens

Llama 3.3 70B 131K · per 1M tokens LLM ₹57.01 / ₹76.33 per 1M tokens

Llama 3.1 8B Instant 131K · per 1M tokens LLM ₹4.83 / ₹7.73 per 1M tokens

GPT OSS 20B 131K · per 1M tokens LLM ₹7.25 / ₹28.99 per 1M tokens

GLM-4.7 200K · per 1M tokens LLM ₹57.97 / ₹212.57 per 1M tokens

GPT OSS 120B 128K · per 1M tokens LLM ₹9.66 / ₹48.31 per 1M tokens

## Pricing

List rates · local currency · GST excluded

Model Type Input price Caching price Output price

Gemma 4 31B256K · per 1M tokens Multimodal ₹18.97 \- ₹56.9

Kimi K31M · per 1M tokens Multimodal ₹284.5 \- ₹1422.48

GLM 5.21M · per 1M tokens LLM ₹88.19 \- ₹284.5

MiniMax-M31M · per 1M tokens Multimodal ₹57.97 \- ₹231.89

MiniMax-M2.7205K · per 1M tokens LLM ₹28.99 \- ₹115.95

MiniMax-M2.7-highspeed205K · per 1M tokens LLM ₹57.97 \- ₹231.89

DeepSeek-V3.2128K · per 1M tokens LLM ₹27.05 \- ₹40.58

Llama 3.3 70B131K · per 1M tokens LLM ₹57.01 \- ₹76.33

Llama 3.1 8B Instant131K · per 1M tokens LLM ₹4.83 \- ₹7.73

GPT OSS 20B131K · per 1M tokens LLM ₹7.25 \- ₹28.99

GLM-4.7200K · per 1M tokens LLM ₹57.97 \- ₹212.57

GPT OSS 120B128K · per 1M tokens LLM ₹9.66 \- ₹48.31

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Prices exclude 18% GST where applicable. 200,000 tokens per day plus 10,000 requests free.

## Infrastructure

Source-backed

Region**India**

Cities**Indore**

SLA**99.9%**

API base**https://inference.ai.neevcloud.com/v1**

Auth**Bearer**

Rate limit**Free tier: 200K tokens per day and 10K requests.**

## Access

Billing & API

API base**https://inference.ai.neevcloud.com/v1**

Auth**Bearer**

Rate limit**Free tier: 200K tokens per day and 10K requests.**

SLA**99.9%**

200,000 tokens per day plus 10,000 requests free.

## Compliance

Source-backed

DPA**Not published**

ZDR**not\_published**

Training**product page: not used for training**

Retention**Not published; the product page says customer data is not used for training.**

DPO**dpo@neevcloud.com**

Certifications

MeitY empanelledSOC 2 Type IIISO 9001ISO 27001ISO 27017ISO 27018ISO 20000-1

Subprocessors

third-party providers (unnamed)

## 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.

[PreviousE2E Networks Blaze](/india/providers/e2e-networks) [NextKrutrim](/india/providers/krutrim)