Simple pricing. No surprises.

Pay-as-you-go inference or a chat subscription. All on sovereign European infrastructure.

Top Up Credits Talk to Sales

Inference

Access 60+ open-weight models on a pay-as-you-go basis. No commitments, no minimums. Just top up credits and go.

Large Language Models

DeepSeek R1 0528
Input €0.65
Output €2.6
View Model
DeepSeek V3 0324
Input €0.3
Output €0.95
View Model
DeepSeek V3.1
Input €0.2
Output €0.8
View Model
DeepSeek V3.2
Input €0.3
Output €0.5
View Model
DeepSeek V4 Flash
Input €0.15
Output €0.3
View Model
DeepSeek V4 Pro
Input €1.65
Output €3.3
View Model
Gemma 3 27B IT
Input €0.25
Output €0.5
View Model
Gemma 4 26B A4B
Input €0.25
Output €0.5
View Model
Gemma 4 31B
Input €0.1
Output €0.3
View Model
Holo2 30B A3B
Input €0.3
Output €0.7
View Model
Llama 3.1 405B Instruct
Input €1.75
Output €1.75
View Model
Llama 3.1 8B Instruct
Input €0.1
Output €0.1
View Model
Llama 3.3 70B Instruct
Input €0.1
Output €0.3
View Model
MiniMax M2
Input €0.25
Output €1
View Model
MiniMax M2.1
Input €0.3
Output €2.4
View Model
MiniMax M2.5
Input €0.2
Output €1
View Model
MiniMax M2.7
Input €0.6
Output €2.4
View Model
MiniMax M3
Input €0.4
Output €2
View Model
Devstral 2 123B Instruct
Input €0.4
Output €2
View Model
Mistral Medium 3.5 128B
Input €1.5
Output €5
View Model
Mistral Small 3.2 24B Instruct
Input €0.1
Output €0.3
View Model
Mistral Small 4 119B Instruct
Input €0.15
Output €0.6
View Model
Pixtral 12B 2409
Input €0.2
Output €0.2
View Model
Voxtral Small 24B 2507
Input €0.15
Output €0.35
View Model
Kimi K2.5
Input €0.5
Output €2.6
View Model
Kimi K2.6
Input €0.7
Output €3.5
View Model
Kimi K2.7 Code
Input €0.7
Output €3.5
View Model
Nemotron 3 Nano 30B A3B
Input €0.06
Output €0.24
View Model
Nemotron 3 Super 120B A12B
Input €0.3
Output €0.9
View Model
Hermes 4 405B
Input €0.95
Output €2.85
View Model
Hermes 4 70B
Input €0.12
Output €0.4
View Model
GPT-OSS 120B
Input €0.04
Output €0.2
View Model
GPT-OSS 20B
Input €0.03
Output €0.13
View Model
INTELLECT-3
Input €0.2
Output €1.05
View Model
Qwen 3.6 27B
Input €0.2
Output €1.2
View Model
Qwen 3.6 35B A3B
Input €0.25
Output €1.5
View Model
Qwen2.5 VL 72B Instruct
Input €0.25
Output €0.75
View Model
Qwen3 235B A22B Instruct
Input €0.07
Output €0.45
View Model
Qwen3 30B A3B Instruct
Input €0.1
Output €0.3
View Model
Qwen3 32B
Input €0.08
Output €0.24
View Model
Qwen3 Coder 30B A3B Instruct
Input €0.06
Output €0.24
View Model
Qwen3 Coder Next
Input €0.17
Output €0.9
View Model
Qwen3 Next 80B A3B Thinking
Input €0.15
Output €1.2
View Model
Qwen3 VL 235B A22B Instruct
Input €0.2
Output €1.8
View Model
Qwen3.5 122B A10B
Input €0.1
Output €0.3
View Model
Qwen3.5 397B A17B
Input €0.6
Output €3.6
View Model
Qwen3.5 9B
Input €0.07
Output €0.2
View Model
GLM 5.1
Input €1.3
Output €4.1
View Model
GLM 5.2
Input €1.4
Output €4.4
View Model
GLM-4.6
Input €0.4
Output €1.65
View Model
GLM-4.7
Input €0.6
Output €2.05
View Model
GLM-5
Input €0.95
Output €2.95
View Model

Embedding Models

BGE Large EN V1.5
Input €0.02
View Model
BGE M3
Input €0.01
View Model
BGE Multilingual Gemma2
Input €0.01
View Model
Qwen3 Embedding 8B
Input €0.01
View Model
Paraphrase Multilingual MPNet
Input €0.01
View Model
Multilingual E5 Large
Input €0.03
View Model
Multilingual E5 Large Instruct
Input €0.03
View Model

Image Generation

FLUX.1 [dev]
Per Image €0.003
View Model
FLUX.1 [dev] LoRA
Per Image €0.006
View Model
FLUX.2 [dev]
Per Image €0.015
View Model
FLUX.2 [klein] 4B
Per Image €0.008
View Model
FLUX.2 [klein] 9B
Per Image €0.009
View Model
Qwen-Image
Per Image €0.015
View Model

Speech & Audio

Faster Whisper Large V3
Per Minute €0.009
View Model
Whisper Large V3
Per Minute €0.003
View Model
Whisper Large V3 (Verda)
Per Minute €0.022
View Model
Whisper Large V3 Turbo
Per Minute €0.001
View Model

Content Safety

Qwen3Guard Gen 0.6B
Input €0.03
Output €0.1
View Model
Qwen3Guard Gen 8B
Input €0.05
Output €0.2
View Model