TensorX
TensorX
Access models hosted through TensorX using Orq.ai for reasoning, coding, multimodal, and privacy-sensitive AI workloads through one API.
26 models · 26 direct routes · 1 region
Direct regions:
EU
Direct API routes
26 models · 26 direct routes · 1 region
EU
Zero data retention
26 of 26 routes
Capabilities
Code
Speech
Embeddings
Vision
Reasoning
Chat
Access TensorX through Orq.ai’s AI Router
TensorX is an EU-focused inference provider for open and open-weight AI models. Its platform provides OpenAI-compatible access to models for reasoning, coding, multimodal applications, embeddings, speech, and other AI workloads, with an emphasis on privacy-conscious infrastructure.
TensorX models available on Orq.ai
Compare the TensorX-hosted models currently available through Orq.ai, including their supported capabilities, context windows, pricing, and regional availability.
Why use TensorX through Orq.ai?
Chat & reasoning
Route TensorX-hosted models through Orq.ai while applying routing, tracing, evaluations, budgets, and governance controls around each request.
Code
Route coding workloads through Orq.ai, compare TensorX with other providers, and monitor cost, latency, and quality from a shared control layer.
Multimodal & specialized workloads
Combine supported TensorX embeddings, speech, and vision workloads, where available, with other providers using shared observability, evaluations, and governance.
Pricing
Pricing varies by model, capability, usage volume, and billing configuration. Input and output rates can differ, and other capabilities may use different billing units. Check Orq.ai and your TensorX setup for current rates, quotas, and billing details.
Works with
Orq.ai works with OpenAI-compatible clients and common AI development frameworks. Supported TensorX models can be incorporated into Orq.ai workflows depending on the model, endpoint, and integration configuration.
FAQs
Do I need a separate TensorX account to use TensorX through Orq.ai?
Can I route only some workflows to TensorX and others to different providers?
Does using TensorX through Orq.ai add latency?
Alternatives to TensorX

Meta
Explore Meta-created models through Orq.ai. Direct pricing and route statistics use Meta-hosted routes; other hosting providers are listed separately.
Image generation
Speech
Vision
Reasoning
Chat
Explore Google-created models, including Gemini and Gemma, through Orq.ai. Direct pricing and route statistics on this page use Google AI; other hosts are listed separately.
Code
Image generation
Speech
Embeddings
Vision
Reasoning
Chat
Inception
Access Inception’s Mercury diffusion language models through Orq.ai for fast reasoning, coding, agentic, and other latency-sensitive AI workloads.
Models:
Code
Vision
Reasoning
Chat
Anthropic
Access Anthropic’s Claude models through Orq.ai for reasoning, coding, vision, and agentic workflows through one API.
Vision
Reasoning
Chat