---
title: "Draft OpenHands integration"
description: "Unverified draft settings for using OpenHands with minirouter."
canonical_url: "https://minirouter.sh/integrations/openhands"
markdown_url: "https://minirouter.sh/integrations/openhands.md"
last_updated: "2026-08-04"
---

# OpenHands + minirouter

Verification status: UNVERIFIED DRAFT
Confirm the current client fields and run the verification request before relying on this configuration.

Draft LLM configuration for OpenHands, which routes through LiteLLM and needs the openai/ prefix on every model id.

Base URL: https://api.minirouter.sh/v1
Get a key: https://minirouter.sh/key

## Settings

Settings → LLM → Advanced, or config.toml

1. Custom Model: openai/meta/llama-3.3-70b
   The openai/ prefix selects the OpenAI-compatible driver; everything after it is our model id, unchanged.
2. Base URL: https://api.minirouter.sh/v1
3. API Key: mr-live-… (your key)

## Draft configuration

config.toml — unverified draft

```
[llm]
model = "openai/meta/llama-3.3-70b"
base_url = "https://api.minirouter.sh/v1"
api_key = "mr-live-YOUR-KEY-HERE"
```

## Recommended models

Only use a model after confirming it appears in the live model catalog at https://minirouter.sh/api/v1/models.

- mistral/devstral-small-2: Coding-oriented candidate for edits and tool calls.
- deepseek/deepseek-v3: Reasoning-oriented candidate for multi-step work.
- meta/llama-4-maverick: Long-context candidate for larger repositories.
- zai/glm-5: Tool-calling candidate for the agent loop.

## Troubleshooting

### LLM provider not found, or the model id is rejected

The openai/ prefix is doing real work — without it the underlying LiteLLM layer tries to guess a provider from the id and fails. Write openai/ followed by our id exactly: openai/meta/llama-3.3-70b.

### 404, HTML, or a parse error on every request

Almost always the base URL. Use https://api.minirouter.sh/v1 — the bare host without /v1 also works, but never append /chat/completions to the base URL field; the client adds that path itself.

Error reference: https://minirouter.sh/docs/errors#invalid_request

### Credits gone overnight with nothing to show

An agent in a retry loop spends at machine speed. Set dailyLimitNano on the key the agent uses — one key per agent, so a runaway is contained to that key rather than the whole balance.

Error reference: https://minirouter.sh/docs/errors#insufficient_credits

### 401 on every request

Wrong or rotated key. Keys start with mr-live-; after a rotation the old key keeps working for 24 hours, then dies.

Error reference: https://minirouter.sh/docs/errors#invalid_api_key