Cortecs integrates Nebius inference into its LLM gateway. Its website lists Nebius among 16 active providers. Cortecs describes the integrated Nebius inference stack as running on NVIDIA GPUs in Finland.
The gateway filters providers against customer requirements, then ranks remaining options by price and performance. Cortecs names Nebius B.V. as an upstream subprocessor for generative AI inference in its data processing agreement. Routing depends on customer configuration. Providers excluded by a customer do not process that customer's data.
Cortecs Nebius provider pageListed 20 Oct 2026 · Cortecs · Web pageCortecs describes Nebius inference as integrated into its gateway and running on NVIDIA GPUs in Finland.
Cortecs data processing agreement
Listed 20 Oct 2026 · Cortecs · Web page
Cortecs names Nebius B.V. as an upstream AI inference subprocessor. The agreement makes provider routing dependent on customer configuration and excludes processing by providers the customer has disabled.
Cortecs data processing agreementListed 20 Oct 2026 · Cortecs · Web pageCortecs names Nebius B.V. as an upstream AI inference subprocessor. The agreement makes provider routing dependent on customer configuration and excludes processing by providers the customer has disabled.
Cortecs Nebius fast provider route
Listed 20 Oct 2026 · Cortecs · Web page
The additional Cortecs Nebius provider page repeats the description of integrated Nebius inference on NVIDIA GPUs in Finland.
Cortecs Nebius fast provider routeListed 20 Oct 2026 · Cortecs · Web pageThe additional Cortecs Nebius provider page repeats the description of integrated Nebius inference on NVIDIA GPUs in Finland.
Cortecs official gateway homepage
Listed 20 Oct 2026 · Cortecs · Web page
Cortecs lists Nebius among the active providers available through its policy-based LLM gateway.
Cortecs official gateway homepageListed 20 Oct 2026 · Cortecs · Web pageCortecs lists Nebius among the active providers available through its policy-based LLM gateway.
Cortecs is an AI gateway operated by Vienna-based Cortecs GmbH for developers and businesses building AI applications. Its unified API connects applications to models across multiple providers, with policy-based routing that filters providers against customer requirements and ranks eligible options by price and performance. The platform supports text, vision, embeddings, audio transcription and speech generation. Teams can track requests and costs, manage budgets and integrate existing tools through OpenAI- or Anthropic-compatible endpoints. Usage is billed at provider rates with a service fee.
Documented financing · private company
AmountUndisclosedGrant — aws Digitalisierung, AI-Adoption: Green
Cortecs operates an LLM gateway with policy-based routing across multiple model providers. · Infrastructure
How they use Nebius Token Factory
Cortecs integrates Nebius inference into its LLM gateway. Its website lists Nebius among 16 active providers. Cortecs describes the integrated Nebius inference stack as running on NVIDIA GPUs in Finland.
The gateway filters providers against customer requirements, then ranks remaining options by price and performance. Cortecs names Nebius B.V. as an upstream subprocessor for generative AI inference in its data processing agreement. Routing depends on customer configuration. Providers excluded by a customer do not process that customer's data.
Cortecs Nebius provider pageListed 20 Oct 2026 · Cortecs · Web pageCortecs describes Nebius inference as integrated into its gateway and running on NVIDIA GPUs in Finland.
Cortecs data processing agreement
Listed 20 Oct 2026 · Cortecs · Web page
Cortecs names Nebius B.V. as an upstream AI inference subprocessor. The agreement makes provider routing dependent on customer configuration and excludes processing by providers the customer has disabled.
Cortecs data processing agreementListed 20 Oct 2026 · Cortecs · Web pageCortecs names Nebius B.V. as an upstream AI inference subprocessor. The agreement makes provider routing dependent on customer configuration and excludes processing by providers the customer has disabled.
Cortecs Nebius fast provider route
Listed 20 Oct 2026 · Cortecs · Web page
The additional Cortecs Nebius provider page repeats the description of integrated Nebius inference on NVIDIA GPUs in Finland.
Cortecs Nebius fast provider routeListed 20 Oct 2026 · Cortecs · Web pageThe additional Cortecs Nebius provider page repeats the description of integrated Nebius inference on NVIDIA GPUs in Finland.
Cortecs official gateway homepage
Listed 20 Oct 2026 · Cortecs · Web page
Cortecs lists Nebius among the active providers available through its policy-based LLM gateway.
Cortecs official gateway homepageListed 20 Oct 2026 · Cortecs · Web pageCortecs lists Nebius among the active providers available through its policy-based LLM gateway.
Cortecs is an AI gateway operated by Vienna-based Cortecs GmbH for developers and businesses building AI applications. Its unified API connects applications to models across multiple providers, with policy-based routing that filters providers against customer requirements and ranks eligible options by price and performance. The platform supports text, vision, embeddings, audio transcription and speech generation. Teams can track requests and costs, manage budgets and integrate existing tools through OpenAI- or Anthropic-compatible endpoints. Usage is billed at provider rates with a service fee.
Documented financing · private company
AmountUndisclosedGrant — aws Digitalisierung, AI-Adoption: Green
