Use gateways with Subconscious

Let your AI do the setup. Paste this into Claude Code, Codex, ChatGPT or any assistant.

Set up the AI gateway I use to run on Subconscious as its model provider.

Subconscious is an inference provider for long-running agents. Gateways serve its models as one provider among many, under the gateway’s own API key and model IDs.
- API key: use the gateway’s own key from the environment. Never commit the key or paste it into project files. If it is not set, ask me to create one.

Work out which of these tools I am using: check my project and installed tools, or ask me. Then fetch its setup guide and follow it. Each guide is Markdown and lists every command and config file.

Gateways:
- Vercel AI Gateway: https://www.subconscious.dev/integrations/gateways/vercel-ai-gateway.md
- Liquid Inference: https://www.subconscious.dev/integrations/gateways/liquid-inference.md
- RouterPlus: https://www.subconscious.dev/integrations/gateways/routerplus.md
- Cloudflare AI Gateway: https://www.subconscious.dev/integrations/gateways/cloudflare-ai-gateway.md
- OpenRouter: https://www.subconscious.dev/integrations/gateways/openrouter.md
- Requesty: https://www.subconscious.dev/integrations/gateways/requesty.md
- Snowflake Cortex AI: https://www.subconscious.dev/integrations/gateways/snowflake-cortex-ai.md

If you cannot fetch URLs, ask me for the guide.

When you are done, confirm the gateway served the request from Subconscious, then summarize what you changed.

Already send model traffic through a gateway? Route it to Subconscious there, with the key, billing and fallbacks you already have.

Get an API key Read the API docs

Vercel AI Gateway

One Vercel key for hundreds of models, with Subconscious serving GLM-5.3 and DeepSeek V4.1.

Setup guide