---
title: Claude Code
description: Run Claude Code on Half Off Dev at half the official Claude price: two environment variables or settings.json, model choice, and prompt caching.
---

Claude Code reads its endpoint and credentials from environment variables, and it talks the Anthropic Messages API, which Half Off Dev serves without translation. Point those variables at Half Off Dev and the same terminal coding assistant keeps working, billed at 50% of Anthropic's list price. Create an [API key](/app/keys) before you start.

## Configure it {#configure}

For a quick try, export three variables and launch `claude` in the same shell:

```bash title="Shell"
export ANTHROPIC_BASE_URL=https://halfoff.dev
export ANTHROPIC_AUTH_TOKEN=$HALFOFF_API_KEY
export ANTHROPIC_MODEL=claude-sonnet-5.5
claude
```

To make it permanent, put the values in `~/.claude/settings.json`, using your full key:

```json title="~/.claude/settings.json"
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://halfoff.dev",
    "ANTHROPIC_AUTH_TOKEN": "ho-...",
    "ANTHROPIC_MODEL": "claude-sonnet-5.5",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "claude-haiku-4.5"
  }
}
```

Leave `/v1` off the base URL: Claude Code adds it.

### Or import it from the dashboard {#import}

On [API keys](/app/keys), choose **Use in tools** → **Claude Code**. You get the setup above with your key in place, and **Import with CC Switch** creates a Half Off Dev provider in the [CC Switch](https://github.com/farion1231/cc-switch) desktop app with the models preset (CC Switch has to be installed). A key you just created is already filled in; for an older one, paste the full key, since Half Off Dev only keeps its hash.

## Models {#models}

Claude Code uses two slots. `ANTHROPIC_MODEL` is the model you work with; `ANTHROPIC_DEFAULT_HAIKU_MODEL` handles small background jobs, so a fast, cheap model fits there. Any Claude id from `GET /v1/models` is valid, `claude-opus-5.5` for instance. All ids are on the [model list](/models).

## Prompt caching {#prompt-caching}

Claude Code relies heavily on prompt caching, and it keeps working here. Half Off Dev pins each session to the channel that holds its cache, so the large, repeated context of a coding session is billed at the cached-input rate turn after turn. Details in [Prompt caching](/docs/models/caching).

## Fixing errors {#troubleshooting}

| What you see | What to do |
| --- | --- |
| `401` `Missing API key` | No key is reaching Half Off Dev. Export `ANTHROPIC_AUTH_TOKEN` in the shell that runs `claude`, or set it in `~/.claude/settings.json`. |
| `401` `Invalid or revoked API key` | The key was mistyped, cut short or revoked. Paste it again or make a new one. |
| `404` `Model '...' is not available` | That id doesn't exist. Copy a Claude id from `GET /v1/models` or the [model list](/models). |
| `404` with `/v1/v1/` in the path | `ANTHROPIC_BASE_URL` ends in `/v1`. Change it to `https://halfoff.dev`. |
| `402` | The balance is empty or the key has hit its spend cap. See [Billing](/docs/account/billing). |

Any other status is explained in [Errors](/docs/api/errors).