Skip to main content

Model requests

Terminal can support additional open-source serverless models by request. Examples include:
Model familyTypical use
GLM 5.2General reasoning, coding, and long-context tasks
DeepSeek V4 ProGeneral reasoning, coding, and agentic workloads
Kimi K2.6Coding, agentic workflows, and long-context tasks
DeepSeek V4 FlashFast, low-cost long-context inference
NVIDIA Nemotron 3 UltraAgentic and high-throughput production workloads
If there is an OSS model you want to run through Terminal, send us the model name or link.

Request a model

Email shubham@terminal.fyi with:
  • The model name or public model link.
  • Your expected input and output token volume.
  • Whether you need Standard, Flex, or both.
  • Any latency or throughput target you care about.
We will confirm availability, pricing, and expected behavior before you send production traffic.