TensorX 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 16 TensorX models starting at $0.20 per 1M input tokens with context windows up to 1.0M tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
Flagship model
kimi-k3.1-proIntelligence Index
46.5
All TensorX models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
| 1.0M | 262K | $3.00 | $15.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $0.30 | $1.20 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 66K | $0.50 | $1.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 393K | $0.50 | $1.50 | 👁🧠🔧⚡ | N/A | |
| 1M | 262K | $2.50 | $6.00 | 👁🧠🔧⚡ | N/A | |
| 1M | 262K | $2.50 | $6.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $0.20 | $0.50 | 🧠 | N/A | |
| 262K | 262K | $0.20 | $0.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $1.75 | $4.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $1.75 | $3.50 | 🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $0.25 | $0.30 | 🧠🔧⚡ | N/A | |
| 1.0M | 262K | $3.00 | $15.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $1.50 | $4.50 | 🧠🔧⚡ | N/A | |
| 262K | 262K | $1.25 | $4.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $0.40 | $2.00 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $1.75 | $3.50 | 🧠🔧⚡ | N/A |
About TensorX on Requesty
How many TensorX models are available through Requesty?
Requesty routes to 16 TensorX models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest TensorX model?
The cheapest TensorX model starts at $0.20 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on TensorX pricing?
No. Requesty passes through exactly what TensorX charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train TensorX models?
TensorX's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are TensorX models hosted?
TensorX 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 rows in the models explorer.