# TensorX

TensorX sells inference on Liquid Inference. A buyer names one of its models as tensorx/\<model\>, or names the model and pays the lowest offer that meets the buyer's rules.

## Facts

- Handle: tensorx
- Website: https://tensorx.ai/
- On the exchange since: 2026-10-08
- Models: 7
- Offers: 7
- Regions: eu
- Precisions (declared): fp8, mxfp4, mxfp8, nvfp4
- Lowest price on: 2 of 7 models

## Reliability, last 3 days

- Probes answered: 97.29%
- Hours with an answer: 100.0%
- Median response time: 896ms

## Checked by the exchange

1 of 7 offers match the fingerprint of the model. 0 have a finished evaluation.

The exchange sends fixed prompts to each offer and compares the answers with a baseline for the model. It also runs benchmarks against the offers and keeps the results.

## Data handling

- Zero retention, declared by the provider
- No training, declared by the provider

## Models

- [GLM 5.3](https://liquidinference.ai/models/glm-5.3.md): declared precision fp8, eu, $1.750 input and $4.500 output per million tokens, $0.438 cache read per million tokens, 1M tokens of context
- [GLM 5.3 Flash](https://liquidinference.ai/models/glm-5.3-flash.md): declared precision fp8, eu, $0.200 input and $0.500 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
- [Kimi K3](https://liquidinference.ai/models/kimi-k3.md): declared precision mxfp4, eu, $3.000 input and $15.000 output per million tokens, $0.750 cache read per million tokens, 1M tokens of context
- [MiniMax M3.1 Flash](https://liquidinference.ai/models/MiniMax-M3.1-Flash.md): declared precision mxfp8, eu, $0.300 input and $1.200 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
- [Qwen 3.8 2.4t a95b](https://liquidinference.ai/models/qwen3.8-2.4t-a95b.md): declared precision nvfp4, eu, $2.500 input and $6.000 output per million tokens, $0.625 cache read per million tokens, 262.1K tokens of context
- [Qwen 3.8 27B](https://liquidinference.ai/models/qwen3.8-27b.md): declared precision fp8, eu, $0.400 input and $2.400 output per million tokens, $0.100 cache read per million tokens, 262.1K tokens of context
- [Qwen 3.8 Flash Next](https://liquidinference.ai/models/qwen3.8-flash-next.md): declared precision fp8, eu, $0.200 input and $0.500 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context

## Related pages

- [This page in a browser](https://liquidinference.ai/providers/97779c4e-1ca4-4fe3-a1e7-477adbb61e80)
- [All providers](https://liquidinference.ai/providers.md)
- [All models](https://liquidinference.ai/models)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)