Using Your Own API Key
Beaver allows you to use your own API key for unlimited access. This bypasses Beaver's built-in credits system and bills usage directly to your provider account.
Why is login required with my own API key? All requests are processed through Beaver's server. Your computer connects to our server, which then calls the AI provider. This enables many features and is central to how Beaver works. Your API key is stored locally, transmitted securely, and never saved on our servers.
Supported Providers
Beaver supports API keys from three major AI providers:
| Provider | Models | Get API Key |
|---|---|---|
| OpenAI | GPT 5.4, GPT 5.2, GPT 5.1, GPT 5.4 mini | platform.openai.com |
| Anthropic | Claude Sonnet 4.6, Haiku 4.5, Opus 4.6 | console.anthropic.com |
| Gemini 3 Flash Preview, Gemini 3.1 Pro Preview | aistudio.google.com |
Adding Your API Key
Open Beaver Preferences
In Beaver, go to Beaver → User account and settings → Settings.
Navigate to API Keys
Open the "API Keys" section
Enter Your Key
Copy your API key into the field for your chosen provider (OpenAI, Anthropic, or Google).
Save and Use
Click Confirm* to ensure that your API is working
Select Model
Close settings and select a model under Your API Key from the model selector
Common Issues
The issues below are caused by limitations of your API key or provider account. They are not Beaver bugs. You can always switch to Beaver credits to avoid them entirely.
Google/Gemini: Rate limits, model overloaded, or slow responses
Google/Gemini API keys frequently hit rate limits, report the model as overloaded, or time out. These are well-documented Google API constraints that affect all applications, not just Beaver.
-
Free API keys are extremely limited and not appropriate for Beaver. Upgrade to a paid key.
-
Paid Tier 1 keys can still hit limits when Google servers are overloaded or under heavy use. Retry after a moment, or upgrade to Tier 2 or higher.
Solution: Upgrade to a paid Gemini key (Tier 2+), or switch providers.
Anthropic: Rate limits or insufficient credits
This error means your Anthropic API key has either run out of credits or exceeded its rate limit.
-
Check your balance in the Claude Console and add credits if needed.
-
Rate limits on Tier 1 keys cap input tokens at 30,000 per minute (ITPM). Because Beaver is an AI agent that makes repeated requests, this limit can be exhausted quickly. Upgrade to Tier 2 or higher, switch to Haiku 4.5 (which has higher rate limits), or use a different provider.
Solution: Add credits, upgrade to Tier 2+, or switch providers.
OpenAI: Verification required
OpenAI requires identity verification before allowing streaming (real-time responses):
"OpenAI requires verification to use this model with streaming."
Solution: Visit OpenAI Settings and click "Verify Organization." Verification can take up to 15 minutes to propagate.
Custom Models and Endpoints
Using custom models and endpoints is an advanced feature and should only be used by experienced users. Many models or endpoints are incompatible with Beaver and will not work correctly. Some of these issues show up as error messages in Beaver, and others may lead to degraded performance or incorrect responses. While we always try to return useful error messages, it is impossible to test every model and endpoint. As a result, error messages may be misleading, incomplete and even wrong.
Solution: Custom models and endpoints require experimentation and a willingness to troubleshoot.