TensorX Ltd. Models
Irish-registered EU-sovereign inference provider. Operates a zero data retention architecture: prompts and completions are processed in ephemeral enclaves and never stored, logged, or persisted. Does not share data with model providers. Requesty routes to 5 TensorX Ltd. models starting at $0.15 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
glm-5.2Intelligence Index
51.1
Coding Index
68.8
GPQA Diamond
89.5%
Terminal-Bench Hard
50.8%
All TensorX Ltd. models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
glm-5.2 | 1.0M | 1.0M | $1.50 | $4.50 | 🧠🔧⚡ | 69 |
kimi-k2.7-code | 262K | 262K | $1.25 | $4.50 | 👁🧠🔧⚡ | 61 |
deepseek-v4-pro | 1.0M | 1.0M | $1.75 | $3.50 | 🧠🔧⚡ | 59 |
deepseek-v4-flash | 1.0M | 1.0M | $0.15 | $0.30 | 🧠🔧⚡ | 56 |
minimax-m3 | 1.0M | 1.0M | $0.40 | $2.00 | 👁🧠🔧⚡ | 59 |
About TensorX Ltd. on Requesty
How many TensorX Ltd. models are available through Requesty?
Requesty routes to 5 TensorX Ltd. models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest TensorX Ltd. model?
The cheapest TensorX Ltd. model starts at $0.15 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on TensorX Ltd. pricing?
No. Requesty passes through exactly what TensorX Ltd. charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train TensorX Ltd. models?
TensorX Ltd.'s terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are TensorX Ltd. models hosted?
TensorX Ltd. models are hosted in 🇪🇺 EU (Ireland). Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the TensorX Ltd. rows in the models explorer.