Access Tensorix through Orq.ai’s AI Router

Tensorix is an EU‑sovereign inference provider offering 50+ open‑source and open‑weight models behind a fully OpenAI‑compatible API, with zero data retention and pay‑as‑you‑go pricing per 1M tokens. Its endpoints cover general chat, advanced reasoning, coding, multimodal vision, and cost‑efficient high‑volume use cases.

Tensorix models available on Orq.ai

Why use Tensorix through Orq.ai?

This gives teams a practical way to use Tensorix where it performs best while centralising routing, observability, evals, and cost controls across the wider model stack.

Pricing

Plans and API access

Tensorix offers:

• Token‑based API pricing per 1M tokens with no monthly minimums; you buy credits and pay only for actual usage.docs

• A model browser and cost calculator where each model’s input and output prices are listed, typically much lower than flagship proprietary models

Pricing is usage‑based:

• Each model has separate input and output token rates, displayed per 1M tokens.

• All inference is zero data retention, aimed at privacy‑sensitive workloads.infrabase+1

Representative prices (per 1M tokens):eurouter+1

• deepseek/deepseek-v4-pro: $1.75 input / $3.50 output.

• deepseek/deepseek-v4-flash: $0.15 input / $0.30 output.

• z-ai/glm-5.2: $1.50 input / $4.50 output.

• z-ai/glm-5: $1.00 input / $3.20 output.

• z-ai/glm-4.7: $0.60 input / $2.20 output.

• moonshotai/kimi-k2.6: $1.00 input / $4.00 output.

• moonshotai/kimi-k2.5: $0.50 input / $2.80 output.

• qwen/qwen3.5-122b-a10b: $0.50 input / $3.50 output.

• qwen/qwen3.5-9b: $0.15 input / $0.20 output.

• nvidia/nemotron-3-super-120b-a12b: $0.30 input / $0.90 output.

• openai/gpt-oss-120b (served via Tensorix): around $0.04 input / $0.20 output.tensorx+1

Tensorix emphasises that typical use cases can see 60–97% lower costs compared to GPT‑4‑class proprietary models, especially on GLM‑4.7 / GLM‑5 and MiniMax M‑series.

Check the Tensorix models page and the Orq.ai pricing/integration pages for current per‑model rates, quotas, and plan details when using Tensorix via Orq.ai.docs.

Compatible frameworks and tools

Orq.ai exposes Tensorix through:

• a Tensorix provider configuration in AI Gateway > BYOK, where you paste your Tensorix API key, and

• an OpenAI‑compatible integration, because Tensorix already speaks the OpenAI API format.

That means:

• Existing backend workflows using OpenAI SDKs or OpenAI‑compatible clients can point to Orq.ai’s base URL and route some traffic to Tensorix models without changing request shapes.

• Agents, code assistants, and tools that integrate with Orq.ai can be configured so that specific steps (for example, cost‑sensitive reasoning or EU‑hosted workloads) are served by Tensorix, while other steps use different providers, all sharing the same observability and governance layer.

Check the Orq.ai integration docs for the latest supported frameworks and tools for Tensorix.

FAQs