Text Generation Models
Model |
Status |
Input token |
Output token |
|
Gemma 4 31B |
Active |
0.15€/Mtok |
0.45€/Mtok |
|
GPT-OSS-120B |
Active |
0.18€/Mtok |
0.54€/Mtok |
|
Different versions of the Qwen model |
|
|
|
|
Different models of the Mistral |
|
|
|
|
Kimi K 2.5 |
|
Embedding Models
Model |
Status |
€/Mtok |
|
intfloat/multilingual-e5-large-instruct |
Active |
0.03€/Mtok |
Speech-to-text models
Model |
Status |
€/s |
|
OpenAI/Whisper |
Active |
0.006€/s |
Other pricing items
Product |
Price |
|
|
Dedicated Customer Environment
|
200€/month |
|
|
Disk Capacity of a Vector Database |
0.40€/GB |
RAG implementations use vector databases, which consume disk space |
Are you interested in our service? Request a quote easily right here!
Schedule a meeting with our team to review your current cloud solution and determine which sovereignty strategy is best suited for your organization.
Are you interested in our service? Request a quote easily right here!
Schedule a meeting with our team to review your current cloud solution and determine which sovereignty strategy is best suited for your organization.