TensorX

TensorX is a platform that states it runs its models inside the European Union. The LLMTR catalog carries 12 chat models and 1 embedding model; all are addressed with the tensorx/ prefix, exactly as the catalog spells them.

Model	Context	Input / Cache read / Output ($/1M)	Image input	Reasons by default
`tensorx/kimi-k3-tensorx`	1,048,576	3 / 0.75 / 15	yes	yes
`tensorx/kimi-k2.7-code-tensorx`	262,144	1.25 / 0.31 / 4.5	yes	yes
`tensorx/glm-5.3-tensorx`	1,048,576	1.75 / 0.44 / 4.5	no	yes
`tensorx/glm-5.3-flash-tensorx`	1,048,576	0.2 / 0.05 / 0.5	yes	yes
`tensorx/glm-5.2-tensorx`	1,048,576	1.5 / 0.38 / 4.5	no	yes
`tensorx/minimax-m3-tensorx`	1,048,576	0.4 / 0.1 / 2	yes	yes
`tensorx/deepseek-v4-pro-0813-tensorx`	1,048,576	2 / 0.5 / 4	no	no
`tensorx/deepseek-v4.1-flash-tensorx`	1,048,576	0.5 / 0.13 / 1.5	yes	no
`tensorx/deepseek-v4-flash-0731-tensorx`	1,048,576	0.25 / 0.06 / 0.3	no	no
`tensorx/qwen3.8-2.4t-a95b-tensorx`	262,144	2.5 / 0.63 / 6	no	yes
`tensorx/qwen3.8-27b-tensorx`	262,144	0.4 / 0.1 / 2.4	yes	yes
`tensorx/qwen3.8-flash-next-tensorx`	262,144	0.2 / 0.05 / 0.5	yes	yes

The other EU-hosted models are listed in the model catalog.

TensorX models cannot be called until your account has granted the data-transfer consent for TensorX; without it every request returns 403 provider_consent_required.

Consent is given, and withdrawn, from the "Data-transfer consents" card in Settings. It is account-level and applies to every API key on that account. Consent is per provider: a consent given for GreenPT does not cover the TensorX models.

The content of your request is transferred to TensorX to produce the response and processed by TensorX on your behalf; account details such as your name and e-mail are not transferred. See TensorX's data processing agreement (DPA) for the details.

Chat

curl "$LLMTR_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tensorx/kimi-k3-tensorx",
    "messages": [
      { "role": "user", "content": "Summarize this stack trace in three bullets." }
    ],
    "max_tokens": 1024
  }'

Every chat model supports tool/function calling and streaming.

Reasoning

On models that reason by default, those tokens bill as output. If a response comes back with finish_reason: "length", raise max_tokens and retry.

reasoning_effort is not supported on this provider; a request that sends it is refused with 400 invalid_request.

Image input

Images can only be sent to the models marked "yes" under "Image input". A request with an image to any other model is refused with 400 unsupported_input and is not billed.

Embeddings

curl "$LLMTR_BASE_URL/v1/embeddings" \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tensorx/qwen3-embedding-8b-tensorx",
    "input": ["merhaba dunya", "hello world"]
  }'

Model	Context	Dimensions	Price ($/1M tokens)
`tensorx/qwen3-embedding-8b-tensorx`	40,960	4096	0.02

See Embeddings for the shared request and response shape.