OpenKBS Pricing

Choose the perfect plan for your AI agent development needs. Start free and scale as you grow.

Developer

Free
  • Monthly Credits:
  • Agents:50*
  • Knowledge Base:100MB
  • File Storage:1GB
  • Users:1

* Not for production use

Starter

19 €/month
  • Monthly Credits:1,900
  • Agents:2
  • Knowledge Base:200MB
  • File Storage:5GB
  • Users:3
Most Popular

Pro

99 €/month
  • Monthly Credits:10,000
  • Agents:10
  • Knowledge Base:2GB
  • File Storage:50GB
  • Users:15

Business

499 €/month
  • Monthly Credits:50,000
  • Agents:50
  • Knowledge Base:10GB
  • File Storage:500GB
  • Users:50

Enterprise

Custom
  • Monthly Credits:Custom
  • Agents:Custom
  • Knowledge Base:Custom
  • File Storage:Custom
  • Users:Custom

Contact: sales@openkbs.com

Additional Credits

Need more credits beyond your monthly plan? Purchase additional credits on-demand: 2,000 credits for €20

Service Pricing Details

All usage pricing is shown in credits. These services are billed based on actual usage.

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. For streaming APIs, see the TOS for token consumption differences.

Service NameVendorText InputText OutputImage InputContext Size
OpenAI o1openai1500 credits / 1M6000 credits / 1M0.75 credits / image128K
OpenAI o3-miniopenai200 credits / 1M600 credits / 1M200K
GPT 4 Omniopenai500 credits / 1M1500 credits / 1M0.75 credits / image128K
GPT 4.1 Miniopenai50 credits / 1M200 credits / 1M0.75 credits / image900K
GPT 4.1openai200 credits / 1M1000 credits / 1M0.75 credits / image900K
GPT 3.5 Turboopenai50 credits / 1M150 credits / 1M16K
Claude 3.7 Sonnetanthropic400 credits / 1M2000 credits / 1M0.5 credits / image200K
Claude 4 Sonnetanthropic400 credits / 1M2000 credits / 1M0.5 credits / image200K
Claude 3 Opusanthropic1500 credits / 1M7500 credits / 1M200K
Claude 3 Sonnetanthropic300 credits / 1M1500 credits / 1M200K
Claude 3.5 Haikuanthropic100 credits / 1M500 credits / 1M0.5 credits / image200K
Llama 3.1 405Bmeta500 credits / 1M1600 credits / 1M120K
Llama 3.1 70Bmeta99 credits / 1M99 credits / 1M120K
Gemini 2.5 Progoogle150 credits / 1M1200 credits / 1M200K
Qwen-Maxalibaba300 credits / 1M900 credits / 1M120K
Llama 3.1 405Bmeta600 credits / 1M1200 credits / 1M120K
Llama 3.1 70Bmeta60 credits / 1M60 credits / 1M120K
Llama 3.1 8Bmeta10 credits / 1M10 credits / 1M120K
Mistral Largemistral800 credits / 1M2400 credits / 1M32K
Mixtral-8x7bmistral45 credits / 1M70 credits / 1M32K
Mistral 7bmistral15 credits / 1M20 credits / 1M32K

Image Generation

Diffusion models, which convert text descriptions into images, are priced on a per-request basis. These models leverage advanced algorithms to interpret textual prompts and generate corresponding visual content. Pricing is standardized per request, ensuring straightforward and consistent pricing. Pricing is shown in credits.

Service NameVendorPriceDescription
FLUX1.1 probfl4 credits / requestImage generation model by Black Forest Labs
Stable Image Ultrastability8 credits / requestImage generation model by Stability AI
Stable Diffusion 3.5 Large2 credits / requestImage generation model by Stability AI
Stable Diffusion 3 Medium1 credits / requestImage generation model by Stability AI
Stable Diffusion XL 1.00.2 credits / requestImage generation model by Stability AI
Animagine XL 3.00.4 credits / requestGenerates high-quality anime images from textual prompts
Diffusers SDXL Inpaint0.4 credits / requestA latent text-to-image diffusion model
Runwayml SDXL Inpaint0.4 credits / requestA latent text-to-image diffusion model
Stable Diffusion XL Inpaint0.4 credits / requestA latent text-to-image diffusion model
Stable Diffusion Upscaler x40.8 credits / requestUpscaler model

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 NameVendorText InputContext Size
OpenAI Text Embedding v3 largeopenai13 credits / 1M8K
OpenAI Text Embedding v3 smallopenai2 credits / 1M8K

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 NameVendorPriceDescription
Google Search0.6 credits / requestRetrieves search results from Google
Read Webpage0.48 credits / minuteExtracts text from web pages
Send Mail5 credits / requestSend Mail
GCP Text Detection0.15 credits / requestExtracts text from images
Document To Text0.24 credits / minuteExtracts text from documents
Translate Text0.003 credits / characterProvides 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 NameVendorPriceDescription
Whisper Large v30.6 credits / minuteExtracts text from speech
GCP Text To Speech0.003 credits / characterConverts text into natural-sounding speech

Serverless NoSQL Database

The serverless NoSQL database service is fully managed, scalable, and high-performance. Pricing is based on data storage and read/write operations. Read costs are measured in Read Units (RUs), with one RU covering items up to 4 KB. Write costs are measured in Write Units (WUs), with one WU covering items up to 1 KB. Pricing is shown in credits.

Service NameReadWriteStorageDescription
NoSQL service150 credits / 1M Read Units150 credits / 1M Write Units100 credits / GB/monthFully managed NoSQL database providing low latency at any scale
IndexedDB0 credits / 1M Read Units0 credits / 1M Write Units0 credits / GB/monthIn-browser database engine providing free high-performance vector search when combined with NoSQL service
VectorDB service500 credits / 1M Read Units500 credits / 1M Write Units1000 credits / GB/monthHigh performance vector database engine

Code Execution

The Code Execution service provides a secure and managed environment for running code without managing infrastructure. Pricing is per event handler - if you have both onRequest and onResponse handlers (default setup), you'll be charged 0.6 credits per interaction (0.3 credits × 2 handlers). Pricing is shown in credits.

Service NameVendorPriceDescription
nodejs200.3 credits / requestNodeJS code execution service