# FAQ

> Solutions to common LMU AI API errors and setup issues — 401 / 403 / 429 / 500, token billing, model switching, and Claude Code / Codex CLI troubleshooting.

URL: https://docs.lmuai.ai/docs/guide/faq



## Issue 1: Stream disconnected / timeout [#issue-1]

**Error message:**

```
stream disconnected before completion: error sending request for url
(https://api.lmuai.ai/responses)
```

**Cause:** a classic stream disconnect, usually from:

* an unstable local network (frequent Wi-Fi / cellular switching, weak signal, packet loss)
* **a VPN / proxy / system proxy is on**: the proxy rotates the exit IP and breaks the connection

**Solution:**

1. **Turn off any VPN / proxy / system proxy and retry** — the LMU AI overseas gateway connects directly, no extra proxy needed
2. Check that your local network is stable; switch to a more reliable network if needed

<Callout type="info" title="Direct overseas access — no extra proxy needed">
  The LMU AI **international gateway** `api.lmuai.ai` can be called directly from networks outside mainland China with **no extra proxy required**. A direct connection gives the fastest, most stable results; conversely, a proxy that rotates the exit IP tends to cause stream disconnects.
</Callout>

***

## Issue 2: 429 retry error [#issue-2]

**Error message:**

```
exceeded retry limit, last status: 429 Too Many Requests
```

**Cause:** your daily quota is used up.

**Solution:**

1. Open **My Subscription** and confirm whether the daily quota is exhausted
2. If you need more, buy a plan of a **different tier**, then switch to the new plan's group under **API Keys** in the console

<Callout type="warn" title="Renewal vs. adding quota">
  * **Do not buy the same plan** — the same plan renews, it does not add quota
  * To add quota, buy a different plan (e.g. switch from a day pass to a month pass)
</Callout>

***

## Issue 3: 401 Incorrect API key [#issue-3]

**Error message:**

```
unexpected status 401 Unauthorized: Incorrect API key provided
```

**Cause:** the request still went to OpenAI's official endpoint instead of our relay.

**Solution:**

1. Confirm both `config.toml` and `auth.json` were created or replaced correctly
2. Restart the IDE (VS Code / Cursor, etc.) to reload the config files
3. If you previously signed in with an official or another provider's account, sign out first, then reconfigure

<Callout type="info" title="What to do when you hit an error">
  Take a screenshot of the error and translate it — that usually pinpoints the cause quickly.
</Callout>

***

## Issue 4: Scripts are disabled (Windows) [#issue-4]

**Error message:**

```
codex: cannot be loaded because running scripts is disabled on this system.
```

**Solution:** run the following in the terminal, then open a new terminal:

```powershell
Set-ExecutionPolicy RemoteSigned -Scope CurrentUser
```

***

## Issue 5: Node.js not found (Windows) [#issue-5]

**Error message:** `CODEX` is not recognized as a cmdlet, or similar

**Cause:** Node.js is not installed or its PATH is broken.

**Solution:** reinstall Node.js 20+, then open a new terminal.

***

## Issue 6: 503 No available accounts (env vars override the key) [#issue-6]

**Error message:**

```
Error code: 503 - {'error': {'message': 'No available accounts: no available accounts', 'type': 'api_error'}}
```

**Cause:** your `~/.zshrc` (or `~/.bashrc`) sets `ANTHROPIC_AUTH_TOKEN` / `ANTHROPIC_BASE_URL` / `ANTHROPIC_MODEL`. Once the shell starts, these variables take effect globally and override the API key configured in your IDE (Cursor, VS Code, etc.), so the request uses the wrong key.

**Solution (pick one):**

**Option A: remove the variables from `.zshrc`**

Open `~/.zshrc` and delete these lines:

```bash
export ANTHROPIC_AUTH_TOKEN="..."
export ANTHROPIC_BASE_URL="..."
export ANTHROPIC_MODEL="..."
```

Then run `source ~/.zshrc` to apply, and restart the IDE.

**Option B: move the variables to a separate file, loaded only for the Claude Code CLI**

1. Create `~/.claude_env` with the three lines:

```bash
export ANTHROPIC_AUTH_TOKEN="sk-your-lmu-ai-api-key"
export ANTHROPIC_BASE_URL="https://api.lmuai.ai"
export ANTHROPIC_MODEL="the-model-you-use"
```

2. Delete those three lines from `~/.zshrc`.

3. Load them manually when starting Claude Code:

```bash
source ~/.claude_env && claude
```

This way the IDE uses the key from its config file and the Claude Code CLI uses the environment variables, without interfering with each other.

***

## Issue 7: 400 Invalid signature in thinking block (switching models across groups) [#issue-7]

**Error message:**

```
upstream error: 400 messages.<index>.content.<index>:
Invalid `signature` in `thinking` block
```

**Cause:** when Claude's Extended Thinking generates a `thinking` block, it attaches an **encrypted signature** that is tightly bound to the **specific upstream account** that produced it. If you **switch models across groups** within one conversation (e.g. from `claude-sonnet-5` in a "Claude-Pro direct" group to `claude-fable-5` in a "Claude-MAX high-multiplier" group), the client sends the previous history (including the signed thinking block) to the new group's upstream account. Different groups use **different upstreams** and cannot verify a signature issued by another, so it returns 400.

**Typical triggers:**

* The client supports switching models mid-conversation and carries the full prior history
* The groups before and after the switch come from **different upstream accounts** (e.g. "direct group" ↔ "relay / MAX high-multiplier group")

**Solution (any one):**

1. **Start a new conversation when switching groups** — carrying no old history is the simplest, most reliable fix.
2. **Keep one group per conversation** — if you need multi-model collaboration, switch within the same group (same upstream).
3. **Strip the thinking blocks from history** — if the client supports editing history, remove the `thinking` blocks before switching groups.

<Callout type="info" title="Why doesn't retrying help?">
  This is an **unrecoverable 4xx client error caused by an invalid signature**. Once the gateway detects it, it passes the 400 straight back to the client and does not auto-retry on another account — because any non-matching upstream would fail the same way.
</Callout>

***

## Issue 8: 400 Unknown parameter: 'tools\[0].n' (tools sent to an image endpoint) [#issue-8]

**Error message:**

```
400 - {'error': {'code': 'unknown_parameter', 'message': "Unknown parameter: 'tools[0].n'.", 'param': 'tools[0].n', 'type': 'invalid_request_error'}}
```

**Endpoints affected:** `/v1/images/generations`, `/v1/images/edits` (image generation / editing).

**Cause:** the client put a `tools` array into the image request body, with an `n` field inside `tools[0]`. OpenAI's image endpoints &#x2A;*do not accept `tools`** (tool calls belong to the Chat / Responses endpoints; image endpoints have no such concept), so the upstream rejects it with 400.

This usually comes from a buggy client / SDK wrapper that puts the "number of images `n`" in the wrong place — nested into `tools[0].n`, or copied from a Chat request template.

**Solution:**

1. **Remove the `tools` field from the request body** — image `generations` / `edits` do not support tool calls; drop the field entirely.
2. **To generate multiple images, put the count in the top-level `n`** — only `/v1/images/generations` supports `n` (multiple per call); `/v1/images/edits` does not, so drop `n` there.
3. **Check the client SDK version** — if a wrapper builds the parameters automatically, upgrade or replace it so it does not apply a Chat template to image endpoints.

<Callout type="info" title="Why don't switching accounts / retrying help?">
  This is a 4xx client error caused by an **invalid request body**, unrelated to the upstream account or group — the gateway passes the request through as-is, and any account returns the same 400. You must fix the request parameters the client sends.
</Callout>

***

## Issue 9: Do I need a VPN? [#issue-9]

**No.** The LMU AI **international gateway** `api.lmuai.ai` can be called directly from networks outside mainland China with no VPN or proxy.

Conversely, a VPN or proxy that rotates the exit IP tends to cause stream disconnects (see [Issue 1](#issue-1)). A direct connection gives the fastest, most stable results.

***

## Issue 10: 401 API\_KEY\_REQUIRED (Codex sends no key) [#issue-10]

**Error message:**

```
unexpected status 401 Unauthorized: {"code":"API_KEY_REQUIRED","message":"API key is required in Authorization header (Bearer scheme), x-api-key header, or x-goog-api-key header"}, url: https://api.lmuai.ai/responses, request id: ...
```

**Cause:** a Codex bug — when a custom model provider uses `wire_api = "responses"`, the request Codex sends carries **no API key at all** (none of `Authorization`, `x-api-key`, `x-goog-api-key` is sent), so the gateway finds no key and returns 401 `API_KEY_REQUIRED`.

Note this is different from the `Incorrect API key provided` in [Issue 3](#issue-3): that one sends a key that is wrong (usually because the request went to OpenAI's official endpoint instead of the LMU AI relay), whereas this one sends **no key at all**.

**Solution:** open `~/.codex/config.toml`, find your model provider section `[model_providers.<ID>]` (usually `[model_providers.codex]` if you followed this site's guide), and add `requires_openai_auth = true` inside it:

```toml
[model_providers.codex]
name = "codex"
base_url = "https://api.lmuai.ai"
wire_api = "responses"
requires_openai_auth = true
```

Save, reopen the terminal, and restart Codex.

<Callout type="info" title="Users who followed this site's guide are unaffected">
  Every Codex guide on this site ([Mac](/docs/tools/codex-cli-mac) / [Windows](/docs/tools/codex-cli-windows) / [Server](/docs/tools/codex-cli-server) / [Codex App](/docs/tools/codex-app)) already includes `requires_openai_auth = true` in its `config.toml` example. If you hit this error, your config was likely copied from an older guide or another source that omitted this line — add it as shown above.
</Callout>

***

## Still stuck? [#still-stuck]

If a special environment still blocks you during install or setup, contact support:

* Add support on WeChat
* Reach support on Xianyu (闲鱼)

> Remote-assist hours: &#x2A;*after 2 p.m.** (mornings are spent resolving complex environment setups remotely).
>
> If you need remote help, download **NetEase UU Remote** first and send it to support; technical guidance and remote assistance run in the afternoon after 2 p.m.