# How to use Warp with Subconscious

> To use Warp with Subconscious, open Settings, search for "inference endpoint", and add a custom endpoint with URL `https://api.subconscious.dev/v1`, your Subconscious API key and model `subconscious/glm-5.3-marathon`. Select it in the model picker and Warp's agent runs on Subconscious, billed per token.

Canonical page: https://www.subconscious.dev/agents/terminal-and-ide/warp
Category: [Terminal and IDE agents](https://www.subconscious.dev/agents/terminal-and-ide)
Last verified: 2026-09-30
Warp: https://www.warp.dev

## Before you start

- The Warp terminal app
- A Subconscious account and API key

## Set up Warp

### 1. Create a Subconscious API key

Sign in at https://platform.subconscious.dev and create an API key. You will paste it into the settings screen below.

### 2. Open custom inference settings

In Warp, open Settings and search for "inference endpoint".

### 3. Add the Subconscious endpoint

Add a new endpoint with these values. You can give the model a short alias.

- Endpoint URL: `https://api.subconscious.dev/v1`
- API key: `Your Subconscious API key`
- Model identifier: `subconscious/glm-5.3-marathon`

### 4. Select the model

Save, then pick the model in the model picker or with /model followed by its alias.

## Connection details

- OpenAI-compatible base URL: https://api.subconscious.dev/v1
- Anthropic-compatible base URL: https://api.subconscious.dev
- API key: From subc login or the Subconscious dashboard
- Model: subconscious/glm-5.3-marathon
- Multimodal, high-throughput model: subconscious/deepseek-v4.1-flash-marathon

Full API reference: https://docs.subconscious.dev

## Frequently asked questions

### Which Warp plans support custom inference endpoints?

Warp's docs list custom endpoints on Free and paid individual plans and for organizations with 10 or fewer employees; larger teams need Business or Enterprise. Requests route through Warp's servers, and custom endpoints are not used by Cloud Agents or Auto models.

### Which Subconscious model should I use with Warp?

Start with subconscious/glm-5.3-marathon, an open frontier coding model built for long agent runs. subconscious/deepseek-v4.1-flash-marathon is a cheaper, high-throughput alternative that also takes image input. Use the full model ID, including the subconscious/ prefix.

### Is Warp on Subconscious OpenAI- or Anthropic-compatible?

This guide connects Warp through the OpenAI-compatible Subconscious API. Subconscious serves both formats: OpenAI Chat Completions at https://api.subconscious.dev/v1 and Anthropic Messages at https://api.subconscious.dev.

### How is Warp usage on Subconscious billed?

Per token by default, with no commitment. Heavy users can switch to a monthly token plan: a fixed price for a large daily token allowance shared across your team.