How they use Nebius Token Factory
LLM Gateway provides an OpenAI-compatible API for accessing models across multiple providers. Its Nebius provider page identifies Nebius AI Studio and documents access through LLM Gateway without a separate Nebius account or SDK.
For pay-as-you-go keys, the documented nebius/minimax-m3.1-flash model identifier pins requests to Nebius. DevPass coding plans do not support provider pinning. LLM Gateway lists Nebius in its provider register, which its subprocessor policy identifies as the authoritative list of AI providers it routes to. These providers receive request content when a user selects a model they serve or enables automatic routing.
The provider register lists no API-data training or prompt logging, zero-day retention and supported request cancellation for Nebius. A merged repository change scheduled the 15 remaining active Nebius mappings for deactivation on August 31, 2026, while preserving earlier deactivation dates.
Sources
4 sourcesLLM Gateway provider-account disclosure
Listed 2 Nov 2026 · LLM Gateway · Web page
LLM Gateway lists Nebius Group N.V. as the contracting entity for Nebius AI. Its register lists no API-data training or prompt logging, zero-day retention and supported request cancellation for Nebius.
Open original sourceLLM Gateway AI provider subprocessors
Listed 2 Nov 2026 · LLM Gateway · Web page
LLM Gateway identifies its provider register, which lists Nebius, as the authoritative AI-provider subprocessor list and explains that selected providers receive request content to generate responses.
Open original sourcechore(models): retire Nebius mappings by steebchen · Pull Request #3811 · theopenco/llmgateway · GitHub
Listed 3 Nov 2026 · github.com · Web page
In a merged LLM Gateway pull request, steebchen describes scheduling the 15 remaining active Nebius mappings for deactivation on August 31, 2026, while preserving existing historical deactivation dates.
Open original sourceCompany context
llmgateway.ioLLM Gateway, operated by Polar Lights LLC, makes an open-source API gateway for developers and product teams building applications with multiple AI model providers. Its OpenAI-compatible interface routes requests to providers including OpenAI, Anthropic and Google, while a dashboard tracks usage, costs and performance. The gateway supports response caching, automatic failover and centralized API key management. Teams can use the hosted service, bring their own provider keys or self-host the platform. Commercial enterprise features add team access controls, guardrails and audit logs.
LLM Gateway — AboutRecent updates
33 updatesLLM Gateway launches six additional video models in Lounge
Lounge's Video Studio added FLUX 3 Max, KLING v3.0 Pro, Gemini Omni 1.1 Flash, VEED Fabric 1.0, MiniMax H3 Max and Grok Imagine Video 1.5 Lite.
LLM GatewayLLM Gateway adds Qwen3.8 Omni Flash
LLM Gateway added Qwen3.8 Omni Flash through Alibaba Model Studio, supporting text, image and audio inputs.
LLM Gateway GitHubLLM Gateway adds TypeSafe's Jev 1.14
LLM Gateway added Jev 1.14 for decision-model requests, with a 64K context window and input pricing of $0.042 per million tokens.
LLM Gateway GitHub