Skip to content

37 listings across 26 models

Page 1 of 2. The lists below split this page's listings into those sold by Tensorx, run by Tensorx, or sent to Tensorx by a marketplace.

Sold by Tensorx

24 listings on this page sold by Tensorx.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Kimi K3
$3.00cache read $0.75$15.001M
Qwen3.8 Maxqwen/qwen3.8-2.4t-a95b
$2.50cache read $0.63$6.00262K
GLM 5.3
$1.75cache read $0.44$4.501M
$0.50cache read $0.13$1.501M
$2.00cache read $0.50$4.001M
$0.20cache read $0.05$0.50262KNot enough data yetNot measuredNot measured
GLM 5.2
$1.50cache read $0.375$4.501M
$0.20cache read $0.05$0.501M
Kimi K2.6
$1.00cache read $0.25$4.00cache write $1.25262K
DeepSeek V4 Flash 0731
$0.25cache read $0.06$0.301M
GLM 5.1
$1.40cache read $0.35$4.40cache write $1.75203K
$1.75cache read $0.4375$3.50cache write $2.1851M
GLM 5
$1.00cache read $0.25$3.20cache write $1.25203K
Qwen 3.8 27B
$0.40cache read $0.10$2.40262KNot measured
Kimi K2.5
$0.50cache read $0.125$2.80cache write $0.625262K
$1.25cache read $0.3125$4.50262K
GLM 5 Turbo
$1.20cache read $0.30$4.00cache write $1.50203KNot measuredNot measured
GLM 5V Turbo
$1.20cache read $0.30$4.00cache write $1.50203KNot measuredNot measured
MiniMax M3
$0.40cache read $0.10$2.001M
$0.50cache read $0.125$3.50cache write $0.625262KNot measuredNot measured
DeepSeek V3.2
$0.30cache read $0.075$0.50cache write $0.375164KNot measured
MiniMax M2.5
$0.30cache read $0.075$1.20cache write $0.375197KNot measured
DeepSeek R1deepseek/deepseek-r1-0528 · 0528
$0.66cache read $0.165$2.60cache write $0.825164K
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507
$0.072cache read $0.018$0.464cache write $0.09131KNot measured

Run by Tensorx

12 listings on this page where Tensorx runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
 Eden AI$0.50cache read $0.125$1.501M
Kimi K3
 Requesty$3.00cache read $0.75$15.001M
 Eden AI$0.50cache read $0.125$1.501M
 Eden AI$2.00cache read $0.50$4.001M
GLM 5.2
 Requesty$1.50cache read $0.38$4.501M
DeepSeek V4 Flash 0731
 Eden AI$0.25cache read $0.0625$0.301M
DeepSeek V4 Flash 0731
 Requesty$0.25cache read $0.06$0.301M
DeepSeek V4 Protensorx/deepseek-v4-pro-0424 · 0424
 Requesty$1.75cache read $0.44$3.501M
Kimi K2.5
 Eden AI$0.50cache read $0.125$2.80262K
 Requesty$1.25cache read $0.31$4.50262K
MiniMax M3
 Requesty$0.40cache read $0.10$2.001M
DeepSeek R1tensorx/deepseek/deepseek-r1-0528 · 0528
 Eden AI$0.66cache read $0.165$2.60164K

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

Around the web

  • Overview | TensorX Docs
    The TensorX API provides OpenAI-compatible endpoints with streaming and non-streaming responses. The TensorX API uses …The TensorX API provides OpenAI-compatible endpoints with streaming and non-streaming responses. The TensorX API uses API keys for ...

    docs.tensorx.ai

    Docs
  • TensorX
    Software Programmed Everything with Intelligence Our mission at TensorX is to programmatically automate infrastructure and …Software Programmed Everything with Intelligence Our mission at TensorX is to programmatically automate infrastructure and monitor the performance.Read more

    linkedin.com

  • Blog - TensorX
    Insights from TensorX on private AI, EU data sovereignty, GDPR and the EU AI Act, …Insights from TensorX on private AI, EU data sovereignty, GDPR and the EU AI Act, open-source models, and getting the latest models into production fast.

    tensorx.ai

  • TensorX Valuation & Funding History
    TensorX is an AI infrastructure company that provides a private, sovereign AI inference platform on …TensorX is an AI infrastructure company that provides a private, sovereign AI inference platform on dedicated Nvidia GPUs for regulated industries.

    caplight.com

  • TensorX vs. The World: Why Infrastructure Matters
    Not all inference providers are created equal. We compare the privacy architectures of major US …Not all inference providers are created equal. We compare the privacy architectures of major US providers vs. TensorX.

    google.com

  • Dedicated AI Inference on EU GPUs - TensorX
    For AI Developers. Switch to TensorX in a single line of code. Full OpenAI-compatible API, …For AI Developers. Switch to TensorX in a single line of code. Full OpenAI-compatible API, 42+ models, and EU data residency out of the box. Dedicated Inference.Read more

    google.com

  • TensorX's Post
    Tensorix is now TensorX, and the new site is live: TensorX-owned GPU's, based in the …Tensorix is now TensorX, and the new site is live: TensorX-owned GPU's, based in the EU, with zero data retention.

    google.com

  • TensorX: Extensible API for Neural Network Model Design ...
    TensorX is a Python library for prototyping, design, and deployment of complex neural network models …TensorX is a Python library for prototyping, design, and deployment of complex neural network models in TensorFlow.Read more

    google.com

  • TensorX - Crunchbase Company Profile & Funding
    TensorX serves as the sovereign backbone for the next generation of European artificial intelligence. TensorX …TensorX serves as the sovereign backbone for the next generation of European artificial intelligence. TensorX provides privacy-native inference for the world's ...Read more

    google.com

How this data works