# Pricing

URL: https://interfaze.ai/pricing

Simple token-based pricing. No minimums, no seat fees, no infrastructure add-ons. Pay only for the tokens you use.

## Interfaze token pricing

Input tokens

$1.50

/ MTok

Output tokens

$3.50

/ MTok

Infrastructure

Sandbox, Browser engine, etc. Included

Caching

Included

Observability & Logging

Coming soon

Support

Email, Discord, Slack

## Estimated costs for typical use cases

OCR a full document page (run-task)

~$0.002 - $0.004 / page (~$2 - $4 / 1K)

Extract structured fields from an ID or invoice

~$0.016 / doc (~$16 / 1K)

Transcribe audio (run-task)

~$0.006 / min

Scrape & structure a web page

~$0.03 - $0.08 / page

Classify or moderate a text snippet

~$0.006 / item (~$6 / 1K)

[

How does this compare to other models?

See Interfaze plotted against other models on quality vs. blended price per million tokens.

Compare price ->



](https://interfaze.ai/leaderboards/quality-vs-price)

## Enterprise/Custom plan

For teams running at scale or with compliance requirements.

Input/Output tokens

Volume discounts

Rate limiting

Unlimited

SLAs

Available

Self-hosted / VPC deployment

Available

SOC2 & HIPAA Compliance agreement

Available

Support

Priority 24×7×365 and private support channel

Custom development

Available

[More questions? Contact sales teams ->](https://interfaze.ai/sales)

## FAQs

What are the rate limits?

You can make 50 requests per second. If you need more, please contact us at support@interfaze.ai

Do you charge for infrastructure usage like Sandbox containers, Browser engine, etc.?

We don't have a separate charge for infrastructure usage. Infrastructure usage is converted to tokens and added to both input and output tokens. For example, for a code execution, we'll add input tokens for the code inputted and output tokens for the output generated by the sandbox regardless for how long it took to execute.

Do you charge for caching?

We don't charge for caching, if a specific token is cached, it won't be counted towards your usage.

How do you count tokens for media and binary data?

Images, pdf, audio, etc are converted to binary data and are counted as input tokens. The best way to estimate the tokens is to run a test request and see the token count based on your media.

How do I track my usage?

You can track your usage on the dashboard. We'll be adding more detailed metrics and analytics in the future.

How can I reduce my overall cost?

You can reduce your cost by activating only the required parts of the model by using the 'run task' feature which generates a pre-defined structure output as your result and significantly reducing the intermediary token count.

What does my input token count increase more than the input I gave it?

The interfaze architecture runs a chain of multipass pre-processing steps which increase the input context leading to a higher deterministic output and lower output token cost.

If I need to run interfaze on my own infrastructure, can you provide a self-hosted solution?

Yes, we can provide a self-hosted solution. Please contact us at support@interfaze.ai for more details.

### Start building with Interfaze

Pay only for the tokens you use.  
Get started for free, no credit card required.

[Build now ->](https://interfaze.ai/dashboard/playground)[Talk to sales ->](https://interfaze.ai/sales)

Setup with agents