TensorX
EU-sovereign inference API with 42+ open-source models and zero data retention
TensorX is an inference API platform running open-source LLMs on EU infrastructure in Dublin and Helsinki. It provides an OpenAI SDK-compatible endpoint, so existing code works by swapping the base URL. Models include Kimi K3, Qwen 3.8, GLM-5.2, DeepSeek V4, and MiniMax M3, with pay-as-you-go pricing and no data retention.
Pricing: Pay-as-you-go, from $0.02/M input tokens
Choosing an inference API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing an inference API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
TensorX prices by model
Per 1M tokens, read off TensorX's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.50 | $0.13 | $1.50 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
| GLM 5.3 | $1.75 | $0.44 | $4.50 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
| GLM 5.3 Flash | $0.20 | $0.05 | $0.50 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
| Kimi K3 | $3.00 | $0.75 | $15.00 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
| MiniMax M3 | $0.40 | $0.10 | $2.00 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
| Qwen3.8 2.4T A95B | $2.50 | $0.63 | $6.00 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
| Qwen3.8 27B | $0.40 | $0.10 | $2.40 | 15 Oct 2026 | Currency shown as $ (assumed USD); VAT not stated. |
TensorX Alternatives
Explore 149 products in the Inference APIs category. View all TensorX alternatives.
Heabsy
EU inference API on its own GPUs in the EEA, with zero data retention and OpenAI- and Anthropic-compatible endpoints.
DeepInfra
Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.
LibertAI
Decentralized, privacy-first inference API running open-source LLMs in trusted execution environments
Work on TensorX? Feature it at the top of Inference APIs.
Is your product missing?