Choose the right tier for your needs.
From pay-as-you-go developer inference to fully dedicated sovereign GPU clusters — all on EU infrastructure with zero data retention.
Enterprise
Dedicated and Shared.
Enterprise-grade EU-sovereign GPU infrastructure with predictable pricing. Contact us for a custom quote.
Dedicated Sovereign Inference
Your own isolated GPUs. EU-sovereign. Zero data retention.
- Physically isolated GPU cluster
- Fixed monthly pricing — no usage surprises
- 30+ models with full customisation
- ISO 27001-ready & GDPR Article 44 compliant
- Enterprise SLA with dedicated support
- Dublin, Helsinki, and Paris regions
AI Developers
Pay only for what you use.
Pay only for what you use.
No monthly fees, no minimums.
Prices shown per 1 million tokens. Create an account, buy credits, and start running private inference instantly.
| Description | Context Window | ||||
|---|---|---|---|---|---|
|
chatterbox-turbo
|
High-performance AI model for general tasks | unknown | - | $5.00 | - |
deepseek/deepseek-chat-v3-0324
|
High-performance AI model for general tasks | deepseek | 163.8K | $0.30 | $1.00 |
|
deepseek/deepseek-chat-v3.1
|
High-performance AI model for general tasks | deepseek | 164K | $0.20 | $0.80 |
|
deepseek/deepseek-r1-0528
|
High-performance AI model for general tasks | deepseek | 164K | $0.66 | $2.60 |
|
deepseek/deepseek-v3.2
|
High-performance AI model for general tasks | deepseek | 163.8K | $0.30 | $0.50 |
meta-llama/llama-3.3-70b-instruct
|
High-performance AI model for general tasks | meta-llama | 131K | $0.10 | $0.31 |
|
meta-llama/llama-4-maverick
|
High-performance AI model for general tasks | meta-llama | 1050K | $0.14 | $0.68 |
minimax/minimax-m2
|
Cost-effective model with strong general reasoning and coding abilities | minimax | 196.6K | $0.25 | $1.00 |
|
minimax/minimax-m2.1
|
Enhanced version with superior coding and reasoning performance | minimax | 196.6K | $0.30 | $2.40 |
|
minimax/minimax-m2.5
|
- | minimax | 65.5K | $0.30 | $1.20 |
mistralai/mixtral-8x22b-instruct
|
Sparse Mixture-of-Experts model optimized for speed and performance | mistralai | 66K | $2.00 | $6.00 |
moonshotai/kimi-k2.5
|
- | moonshotai | 262.1K | $0.50 | $2.80 |
|
moonshotai/Kimi-K2.6
|
- | moonshotai | 262.1K | $1.00 | $4.00 |
nvidia/nemotron-3-super-120b-a12b
|
- | nvidia | 262.1K | $0.30 | $0.90 |
openai/gpt-oss-20b
|
High-performance AI model for general tasks | openai | 131K | $0.03 | $0.14 |
|
openai/gpt-oss-120b
|
High-performance AI model for general tasks | openai | 131K | $0.04 | $0.20 |
qwen/qwen-2.5-72b-instruct
|
High-performance AI model for general tasks | qwen | 33K | $0.07 | $0.26 |
|
qwen/qwen3-235b-a22b-2507
|
High-performance AI model for general tasks | qwen | 131K | $0.07 | $0.46 |
|
qwen/qwen3-coder-30b-a3b-instruct
|
Optimized for programming and software development tasks | qwen | 262K | $0.06 | $0.25 |
|
qwen/qwen3-embedding-8b
|
- | qwen | 32.8K | $0.01 | $0.00 |
|
qwen/qwen3-vl-235b-a22b-instruct
|
High-performance AI model for general tasks | qwen | 131K | $0.21 | $1.90 |
|
qwen/qwen3.5-9b
|
- | qwen | 262.1K | $0.15 | $0.20 |
|
qwen/qwen3.5-122b-a10b
|
- | qwen | 262.1K | $0.50 | $3.50 |
Systran/faster-whisper-large-v3
|
Specialized for audio processing (Speech-to-Text or Text-to-Speech) | systran | - | - | - |
z-ai/glm-4.6
|
High-performance AI model for general tasks | z-ai | 203K | $0.40 | $1.75 |
|
z-ai/glm-4.7
|
High-throughput model suitable for real-time applications and code completion | z-ai | 202.8K | $0.60 | $2.20 |
|
z-ai/glm-5
|
- | z-ai | 202.8K | $1.00 | $3.20 |
|
z-ai/glm-5.1
|
- | z-ai | 202.8K | $1.40 | $4.40 |
Prices per 1 million tokens · All inference is zero data retention
Maximize savings
with open models
Select a model, enter your monthly token usage, and see your estimated cost compared to OpenAI GPT-4o. All models run on EU-sovereign infrastructure with zero data retention.
- Drop-in OpenAI compatibility — one line of code
- Zero data retention on every request
- Instant account setup — no sales call required
0% Cheaper
vs. OpenAI GPT-4o at your usage level
≈ 750,000 words
≈ 375,000 words
Cost Comparison
OpenAI GPT-4o$0.00
Tensorix (-)$0.00
You save$0.00 / month