AI Credits
About AI credits
Every plan in Relay.app comes with a generous number of free AI credits. AI credits are a single pool of credits that are consumed when running steps that use AI-related features, including:
Prompting AI models
Audio transcription and text-to-speech
Website scraping
The free AI credits that come with all our subscriptions are good for reasonable usage—see the tables below for more details and examples.
If you run out of AI credits in Relay.app, purchase more in your billing settings, or contact [email protected] for help. Alternatively, if you already pay for credits with a AI service provider, connect that account to Relay.app and switch your AI automations to use that connected model.
Free monthly AI credits per plan
Free
Professional
Team
When the AI credits included in your plan aren't enough, it's easy to add more via the billing page. Note that you need to be on a paid plan in order to be able to add additional AI credits. If you're on a Free plan, upgrade to Professional or Team first.
What can I do with 1 AI Credit?
It depends! Different models and operations require different numbers of credits. A detailed conversion table is below, but here some concrete examples:
Summarizing an email will typically uses about 1 AI Credit (but may be much less)
Scraping text from a website uses about 2 AI Credits
Transcribing a minute of audio uses about 10 AI Credits
AI Credits conversion chart
Updated: 2025-06-11
Web scraping: Scraping pages, taking screenshots
2 AI credits per website scraped
Web scraping: Use advanced stealth proxy
10 AI credits per website scraped
Web scraping: Search
2 AI credits per Google Search performed"}
Web scraping: Amazon, Zillow, Indeed
2 AI credits per number of Profiles/Pages requested
Web scraping: LinkedIn
7 AI credits per request
Web scraping: Youtube (video metadata or transcript)
17 AI credits per video
Google Maps: Geocode address
3 addresses resolved
X (Twitter): Search tweets
3 tweets retrieved
Convert file
28 AI credits per file conversion. In case of very long conversions (>1 min) can take up to 249 AI credits (rare)
Enrich email address or name with Linkedin data
467 AI credits per request
Search LinkedIn for roles / job-functions
17 AI credits per request
Text-to-speech (OpenAI TTS)
40 characters of text per AI credit
Text-to-speech (GPT-4o mini)
3 seconds of audio per AI credit
Text-to-speech (ElevenLabs)
1 characters of text per AI credit
Transcription: AssemblyAI (nano)
6 seconds of audio per AI credit
Transcription: AssemblyAI (best)
4 seconds of audio per AI credit
Transcription: ElevenLabs (scribe)
4 seconds of audio per AI credit
Transcription: (Groq - Whisper)
17 seconds of audio per AI credit
Transcription: OpenAI Whisper
6 seconds of audio per AI credit
Transcription: GPT-4o
6 seconds of audio per AI credit
Transcription: GPT-4o-mini
12 seconds of audio per AI credit
Image generation: Imagen 3
50 AI credits per image
Image generation: DALL-E 3
HD, wide: 200 AI credits per image HD: 140 AI credits per image Basic quality, large: 140 AI credits per image Basic quality: 70 AI credits per image
Image generation: GPT-1
Perplexity Deep Research
Perplexity Deep Research
Track your AI credit usage
This content has moved to a dedicated page.
About tokens
The definition of a token differs slightly by model provider. Additionally, input and output tokens are also differentiated from a cost/consumption perspective. We suggest reading the short FAQs from each model provider to learn more:
Unfortunately, it's not trivial to predict how many tokens an AI step will consume upfront, although the articles linked above will give you a better understanding.
For AI steps in Relay.app, token usage is primarily influenced by these factors:
Context included in the prompt The more and larger the attached context, the more tokens will be used every time your step is executed. For example:
An email can easily increase token usage by a few thousand
A PDF can go way beyond that, depending on the size\
Whether the step is given Internet access All text on the websites that the model needs to visit for your prompt is included as context, including user-hidden HTML. This can be anywhere between a few hundred to tens of thousands of tokens used per step execution, depending on how many websites the model needs to visit and how large they are.
Last updated
Was this helpful?