Subconscious

How to use eve with Subconscious

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

Make Subconscious the model provider in my eve project.

Subconscious is an inference API for agents. It serves open models through OpenAI- and Anthropic-compatible endpoints, billed per token.
- OpenAI-compatible base URL: https://api.subconscious.dev/v1
- Anthropic-compatible base URL: https://api.subconscious.dev
- Model: subconscious/glm-5.3-marathon
- API key: read it from the SUBCONSCIOUS_API_KEY environment variable. Never commit the key or paste it into project files. If it is not set, ask me to create one at https://platform.subconscious.dev.

Follow these steps. Run commands and edit files yourself. If I already have agent code, change its model setup to match the example instead of adding a new file.

1. Install eve
Install the framework and its OpenAI-compatible client.
```bash
npx eve@latest init my-agent
cd my-agent
pnpm add @ai-sdk/openai-compatible
```

2. Create a Subconscious API key
Sign in at https://platform.subconscious.dev, create an API key, and export it so the tool can read it.
```bash
export SUBCONSCIOUS_API_KEY="your_key"
```

3. Point it at Subconscious
A model string routes through Vercel AI Gateway, so pass a provider model instance instead. eve requires modelContextWindowTokens for models outside the Gateway catalog; 5,000,000 matches what the Subconscious CLI uses.
```ts
import { defineAgent } from "eve";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const subconscious = createOpenAICompatible({
  name: "subconscious",
  apiKey: process.env.SUBCONSCIOUS_API_KEY,
  baseURL: "https://api.subconscious.dev/v1",
  includeUsage: true,
});

export default defineAgent({
  model: subconscious("subconscious/glm-5.3-marathon"),
  modelContextWindowTokens: 5_000_000,
});
```

4. Run it
Start the dev server and open a session.
```bash
pnpm dev
curl -X POST http://127.0.0.1:3000/eve/v1/session \
  -H 'content-type: application/json' -d '{"message":"Hello"}'
```

Full guide: https://www.subconscious.dev/agents/frameworks/eve.md

When you are done, confirm the tool is using subconscious/glm-5.3-marathon, then summarize what you changed.

To use eve with Subconscious, create an OpenAI-compatible provider with @ai-sdk/openai-compatible and base URL https://api.subconscious.dev/v1, then pass subconscious("subconscious/glm-5.3-marathon") as the model in defineAgent, along with modelContextWindowTokens. Your eve agent then runs on Subconscious instead of AI Gateway.

Get an API keyRead the API docs

Last verified against the eve docs on

Before you start

  • Node.js and pnpm
  • A Subconscious account and API key

eve docs · Source on GitHub

Set up eve

  1. Step 1: Install eve

    Install the framework and its OpenAI-compatible client.

    Terminal
    npx eve@latest init my-agent
cd my-agent
pnpm add @ai-sdk/openai-compatible

  2. Step 2: Create a Subconscious API key

    Sign in at https://platform.subconscious.dev, create an API key, and export it so the tool can read it.

    Terminal
    export SUBCONSCIOUS_API_KEY="your_key"

  3. Step 3: Point it at Subconscious

    A model string routes through Vercel AI Gateway, so pass a provider model instance instead. eve requires modelContextWindowTokens for models outside the Gateway catalog; 5,000,000 matches what the Subconscious CLI uses.

    agent/agent.ts
    import { defineAgent } from "eve";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const subconscious = createOpenAICompatible({
  name: "subconscious",
  apiKey: process.env.SUBCONSCIOUS_API_KEY,
  baseURL: "https://api.subconscious.dev/v1",
  includeUsage: true,
});

export default defineAgent({
  model: subconscious("subconscious/glm-5.3-marathon"),
  modelContextWindowTokens: 5_000_000,
});

  4. Step 4: Run it

    Start the dev server and open a session.

    Terminal
    pnpm dev
curl -X POST http://127.0.0.1:3000/eve/v1/session \
  -H 'content-type: application/json' -d '{"message":"Hello"}'

Why run eve on Subconscious

No new SDK
Subconscious speaks OpenAI Chat Completions and Anthropic Messages, so the client you already use works with a base URL change.
Pay per token
No plan and no commitment: sign up, get an API key and pay for the tokens your agents use.
Long sessions stay fast
2x faster task completion on long tasks than standard open-model inference, especially past 200k tokens of context.
Context that keeps going
The OrangeLine runtime compresses the parts of context that stopped mattering, on the GPU, while the run continues. That gives a 5M+ token context window with no stop-and-compact pause.

Connection details

For any client that takes a custom OpenAI- or Anthropic-compatible endpoint.

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 reference in the Subconscious API docs.

Questions

Can I use eve's built-in openai() helper with Subconscious?
No. That helper reads OPENAI_API_KEY and rejects model IDs that contain a slash. Use an AI SDK provider such as @ai-sdk/openai-compatible.
Which Subconscious model should I use with eve?
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 eve on Subconscious OpenAI- or Anthropic-compatible?
This guide connects eve 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 eve 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.

More frameworks

See all