Under the list
Every line is metered 50% below what the provider lists. No tiers, no minimums, no monthly floor.
Your fast & cheap AI gateway with GLM 5.2
and 17 other open models
One endpoint in front of every open model worth running, in OpenAI or Anthropic format. Keep the client you already use, swap the base URL and the key, and pay per token — always below what the provider charges you directly.
base url
https://universalvoronez.tech/openai/v1 DeepSeek V3.1 DeepSeek V4 Flash (0731) DeepSeek V4 Pro (0813) Gemma 4 31B Granite 4.2 8B Llama 3.1 8B Llama 3.3 70B MiniMax M3 Kimi K2.6 Kimi K2.7 Code Nemotron 3 Ultra 550B Nemotron 3.5 Lightning 30B GPT-OSS 120B GPT-OSS 20B Qwen3.6 35B A3B Qwen3.8 27B GLM 5.2 GLM 5.3 Flash
Either wire
OpenAI or Anthropic format — one pool, one key. Swap the base URL and your client is done.
Whole rack
GLM, DeepSeek, Kimi, Qwen, Llama and the rest behind a single key, with reasoning-effort variants.
One command
writes the config of every client it finds$
curl -fsSL https://universalvoronez.tech/install.sh | sh Writes the Nergate provider and sync plugin into opencode, then the model list refreshes from the
gateway on every start. Undo with --uninstall.
Provider + sync plugin A small Nergate provider and the model-sync plugin land in opencode’s own config.
automaticLive model list The plugin pulls /models on every start — new models and prices show up without a reinstall.
automaticEffort as a variant Reasoning levels ride under each model — press Tab or pick “GLM 5.2 (max)”.
automaticOrg filter & offline cache Choose which organizations to show; a cached list keeps working without a connection.
automaticModel rack
pick a line — rates and limits follow it your app
- in / 1M
- $0.1900
- $0.3800
- out / 1M
- $0.6050
- $1.2100
- context
- 1049k
- text only
- effort
- nonelowmediumhighxhighmax
patched to GLM 5.2