Service Pricing Details
Database Services
NoSQL database is included with every active agent. VectorDB is optional for agents requiring semantic search capabilities.
NoSQL Database (Included)
Stores agent instructions, memory, and structured data. Fast key-based access.
VectorDB (Optional Service)
Semantic search for RAG applications and contextual AI memory.
Code Execution Service
Enterprise-grade serverless code execution platform. Deploy custom business logic, integrate APIs, and build sophisticated agent workflows with your own code.
0.6 credits per message — includes 2 processing events (onRequest + onResponse)
| Service Name | Vendor | Price | Description |
|---|---|---|---|
| nodejs20 | 0.6 credits / interaction | NodeJS code execution service |
Chat Models
AI chat models are priced based on the usage of input and output tokens, calculated per 1 million tokens. A token can be a word, part of a word, or punctuation, serving as the basic unit the model processes. Input tokens are the text prompts given to the model, while output tokens are the responses generated by the model. Pricing is shown in credits. Credits are available on-demand at €0.01 per credit.
| Service Name | Vendor | Text Input | Text Output | Image Input | Context Size |
|---|---|---|---|---|---|
| OpenAI o1 | openai | 1500 credits / 1M | 6000 credits / 1M | 0.75 credits / image | 128K |
| OpenAI o3-mini | openai | 200 credits / 1M | 600 credits / 1M | 200K | |
| GPT 4 Omni | openai | 500 credits / 1M | 1500 credits / 1M | 0.75 credits / image | 128K |
| GPT 5 Mini | openai | 40 credits / 1M | 250 credits / 1M | 0.5 credits / image | 400K |
| GPT 5.1 | openai | 150 credits / 1M | 1200 credits / 1M | 0.75 credits / image | 400K |
| GPT 5 | openai | 150 credits / 1M | 1200 credits / 1M | 0.75 credits / image | 400K |
| Claude 4.5 Sonnet | anthropic | 400 credits / 1M | 2000 credits / 1M | 0.75 credits / image | 200K |
| Claude 4.5 Haiku | anthropic | 120 credits / 1M | 600 credits / 1M | 0.75 credits / image | 200K |
| Gemini 3.0 Pro | 250 credits / 1M | 1500 credits / 1M | 900K | ||
| Llama 3.1 70B | meta | 99 credits / 1M | 99 credits / 1M | 120K | |
| Gemini 2.5 Pro | 150 credits / 1M | 1200 credits / 1M | 200K | ||
| Qwen-Max | alibaba | 300 credits / 1M | 900 credits / 1M | 120K | |
| Llama 3.1 405B | meta | 600 credits / 1M | 1200 credits / 1M | 120K | |
| Qwen-3-235b-a22b-instruct | alibaba | 80 credits / 1M | 150 credits / 1M | 60K |
Image and Video Generation
Image and video generation models convert text descriptions into visual content. Image models are priced per request or per image, while video models are priced per second of generated content. Pricing is shown in credits.
| Service Name | Vendor | Price | Description |
|---|---|---|---|
| GPT Image | openai | Input: 1.5 credits / 1K tokens Output: 6 credits / 1K tokens | Advanced image generation model from OpenAI |
| Sora | openai | sora-2: 720x1280: 12.5 credits/sec 1280x720: 12.5 credits/sec sora-2-pro: 720x1280: 40 credits/sec 1280x720: 40 credits/sec 1024x1792: 60 credits/sec 1792x1024: 60 credits/sec | AI-powered video generation model from OpenAI |
| Gemini 2.5 Flash Image | 7 credits / image | Fast image generation from Google Gemini |
Embedding Models
Embeddings models are priced based on the usage of input tokens, calculated per 1 million tokens. A token can be a word, part of a word, or punctuation, serving as the basic unit the model processes. Input tokens are the text data provided to the model for generating embeddings. Pricing is shown in credits.
| Service Name | Vendor | Text Input | Context Size |
|---|---|---|---|
| OpenAI Text Embedding v3 large | openai | 13 credits / 1M | 8K |
| OpenAI Text Embedding v3 small | openai | 2 credits / 1M | 8K |
Web Tools
Web tools encompass a range of services designed to interact with web content, including search engines, webpage readers, and more. These tools are priced based on the complexity and the computational resources required for each request. Pricing is shown in credits.
| Service Name | Vendor | Price | Description |
|---|---|---|---|
| Google Search | 0.6 credits / request | Retrieves search results from Google | |
| Read Webpage | 0.48 credits / minute | Extracts text from web pages | |
| Send Mail | 2.7 credits / request | Send Mail | |
| Check VAT | 2.7 credits / request | Check VAT | |
| Exchange Rates | 1 credits / request | Exchange Rates | |
| Text Detection | 1 credits / request | Extracts text from images | |
| Document To Text | 0.24 credits / minute | Extracts text from documents | |
| Translate Text | 0.002 credits / character | Provides text translation and detection |
Audio Models
Audio models offer capabilities ranging from speech-to-text conversion to generating synthetic speech. Pricing varies based on the model's complexity and the length of the audio processed. Pricing is shown in credits.
| Service Name | Vendor | Price | Description |
|---|---|---|---|
| Whisper Large v3 | 0.6 credits / minute | Extracts text from speech | |
| Text To Speech | 0.003 credits / character | Converts text into natural-sounding speech |
Research Services
AI-powered research agents that autonomously search and analyze information across the web.
Important: Minimum Upfront Charge
Research services require a minimum upfront charge of 50 credits (~€0.50) to start a research session. This covers approximately 100K input tokens. If actual usage exceeds this amount, the difference is charged upon completion. If usage is lower, no refund is issued for the prepaid amount.
| Service Name | Vendor | Text Input | Text Output | Min. Upfront | Description |
|---|---|---|---|---|---|
| Deep Research | 500 credits / 1M | 2000 credits / 1M | 50 credits | AI-powered deep research agent that searches and analyzes information across the web. Minimum upfront charge of 50credits is required to start a research session. Additional usage is charged based on actual token consumption. |