Setup Guide
API Keys & BYOK on OpenClaw Launch
The API Keys page lets you bring your own provider key (BYOK) and route your bot’s chat, image, video and music through your own account instead of our shared routing. This guide explains every provider you can add, what each key unlocks, and exactly how to wire it up — for both OpenClaw and Hermes Agent instances.
What Is BYOK?
BYOK — bring your own key — means you paste an API key from a provider you already pay (or one with a free tier) into your OpenClaw Launch account. Your running bots then call that provider directly using your key, instead of going through the credits bundled with your plan.
Why do it? Three reasons. First, cost and speed: a direct DeepSeek, MiniMax or Groq key is usually faster and cheaper than the same model proxied through a router. Second, access: some models (OpenAI image generation, Grok video, Gemini voice transcription) only run when you supply that provider’s key. Third, control: usage shows up on your provider dashboard and counts against your quota, not ours.
Every key you add is validated against the provider before it saves, stored encrypted at rest, and applied to your existing running instances with no redeploy. Nothing is exposed in plain text after you save it — the page only ever shows a masked preview.
Where to Find the API Keys Page
- Sign in at openclawlaunch.com.
- Open the API Keys page from the dashboard navigation.
- Find the card for the provider you want, paste your key, and click Save. A green Active badge confirms it is live.
Chat Model Providers
These keys change which model answers your bot. After saving any chat provider, use the “Set as primary model” control on the card to push that model to all of your running instances at once.
| Provider | What it unlocks | Cost | Guide |
|---|---|---|---|
| OpenRouter | 400+ models behind one key — the universal default | Pay-as-you-go | OpenRouter |
| Anthropic | Claude models direct (Opus, Sonnet, Haiku) | Pay-as-you-go | Anthropic |
| OpenAI | GPT chat + GPT Image generation (direct key) | Pay-as-you-go | OpenAI |
| Google AI | Gemini models + voice-message transcription | Free tier | Gemini |
| xAI | Grok chat, Grok Imagine video, Grok web search | Pay-as-you-go | Grok |
| DeepSeek | DeepSeek V4 direct — cheaper than via a router | Pay-as-you-go | DeepSeek |
| Moonshot | Kimi models direct | Pay-as-you-go | Kimi |
| Groq | Ultra-fast Llama / Kimi / Qwen / GPT-OSS (<500ms first token) | Free tier | Groq |
| Qwen / DashScope | Alibaba Qwen models direct | Pay-as-you-go | Qwen |
| Z.AI | Zhipu GLM models direct | Pay-as-you-go | GLM |
| Perplexity | Sonar — web-connected answers with citations | Pay-as-you-go | Perplexity |
| Agnes | Free OpenAI-compatible multimodal gateway (256K context) | Free | Agnes |
| OpenCode Go | Aggregated Zen catalog (Kimi, Qwen, GLM, DeepSeek, MiMo) | Subscription | OpenCode Go |
Image, Video & Music Providers
These keys power the generation tools your bot can call. After saving a media provider, pick the model you want in your instance’s image, video or music settings.
| Provider | What it unlocks | Guide |
|---|---|---|
| fal | Image (FLUX, Nano Banana Pro, Seedream, GPT Image 2) + Kling video | fal |
| MiniMax | M2.7 chat + Image-01, Hailuo 2.3 video, Music 2.5 | MiniMax |
| Runway | Runway Gen-4.5 cinematic video | Runway |
| BytePlus | Seedance 1.5 Pro video | BytePlus |
| Replicate | Thousands of open video & music models | Replicate |
| ComfyUI | Cloud ComfyUI music & video workflows | ComfyUI |
Set as Primary Model
Saving a chat key does not, by itself, switch your bot to that provider. Click “Set as primary model” on the provider card and pick a model from the dropdown — the change hot-applies to every running instance on your account in a second or two, no restart. Media keys work differently: there is no “primary” for them; you choose the image, video or music model per instance.
What About Embeddings?
Your bot uses small session-memory embeddings (Qwen3) to recall past conversation. These keep running through OpenRouter at roughly $0.10 per million tokens — typically pennies a month — regardless of which chat provider you BYOK. The OpenRouter card has a toggle to use your own OpenRouter key for embeddings if you prefer.
Custom Endpoint
If your provider is not listed but exposes an OpenAI-compatible API (Together AI, Mistral, a self-hosted vLLM server, and so on), use the Custom API Provider card to enter the endpoint URL and key directly.
OpenClaw vs Hermes Agent
The same API Keys page serves both frameworks. Keys you add apply to whichever instances you run — classic OpenClaw bots and Hermes Agent instances alike. Each provider guide below has an OpenClaw version and a Hermes version with framework-specific notes. See the BYOK overviews: OpenClaw BYOK and Hermes Agent BYOK.
Troubleshooting
The key won’t save / shows an error
The page validates every key against the provider before saving. A save error almost always means the key is wrong, revoked, or out of credit. Re-copy it from the provider’s dashboard, check for trailing spaces, and confirm the key prefix matches (for example sk-ant- for Anthropic, pplx- for Perplexity, gsk_ for Groq).
I saved a key but my bot still uses the old model
Saving stores the key; it does not switch the model on its own. Use “Set as primary model” on the chat provider’s card to point your instances at the new model.
Image or video generation still fails after adding a media key
Media keys unlock models but you still have to select one. Open your instance settings and pick a model whose provider matches the key you added (for example a fal model after adding a fal key).
Frequently Asked Questions
Is my API key safe on OpenClaw Launch?
Yes. Keys are validated, then encrypted at rest, and only ever shown back to you as a masked preview. They are passed to your own containers to call the provider on your behalf and are never displayed in plain text again.
Do I have to redeploy my bot after adding a key?
No. Saving a key and setting a primary model hot-applies to your running instances in a second or two. There is no rebuild or downtime.
Do I need BYOK to use OpenClaw Launch?
No. Every paid plan and the free trial include credits that work out of the box. BYOK is optional — add it when you want a specific model, lower cost, or usage on your own provider account.
Can I add more than one provider key?
Yes. You can save keys for many providers at once — for example a chat provider, an image provider, and a video provider — and each is used for its part of the pipeline.
What's Next?
- AI plans compared — subscription coding plans vs pay-as-you-go API token pricing, side by side
- OpenClaw BYOK guide — the BYOK basics for OpenClaw
- Compare AI models — pick the right model before you bring a key
- See pricing — plans start at $3/month, BYOK optional