Simple, transparent pricing

Pricing plans

Pay as you go plan

Pay as you go

Perfect for experimentation

$1

/ 1 credits

Total price: $1

1
Partners plan

Partners

For agencies and solution providers

$1,000

/ 1100 credits

+10%

Priority support

No rate limit

Enterprise plan

Enterprise

Use our high performance inference on your own infrastructure with support from our Forward Deployed Engineers (FDE)

Explore available models and their usage costs

Qwen 3.6 35B

$0.1

$0.14

Input - Per 1M tokens

$0.558

$1.00

Output - Per 1M tokens

Gemma 4 26B-A4B

$0.14

Input - Per 1M tokens

$0.4

Output - Per 1M tokens

You got questions? We got answers

Frequently Asked Questions

How does Netra Runtime pricing work?

Netra Runtime uses prepaid credits. You top up credits, then your balance is used as you run supported models and workloads on the platform.

What payment gateway do you use?

Can I see model usage costs before paying?

Do you support enterprise deployments?

Is my payment data stored by Netra?

Ready to own your AI?