Three new models are now live on Nebius Token Factory, expanding the choice for coding, agent, and multimodal workflows.
Two new DeepSeek releases offer different strengths:
• DeepSeek-V4-Pro-0813 is the official V4 Pro release, built for coding agents that use tools, reason through complex problems, and work across multiple steps.
• DeepSeek-V4.1-Flash adds native image understanding and an architecture designed for faster inference, higher throughput, and efficient agent workflows.
And GLM-5.3, which brings Zai’s latest post-training improvements for complex software engineering, from planning changes across a repository to carrying long-running agent tasks through to completion.
And we’re serving it fast: Nebius currently ranks among the top two GLM-5.3 providers on Artificial Analysis for both output speed and time to first answer token.
Use all three through an OpenAI-compatible API, with Token Factory handling the serving infrastructure.
DeepSeek-V4.1-Flash is now live on Nebius Token Factory
The model comes with native image understanding plus an architecture built for faster inference and higher throughput on long, input-heavy workflows.
It combines native vision and a 1M token context with a 552B MoE that activates just 8B parameters for input and 16B for output.
Try it out:
tokenfactory.nebius.com/?mod…