Step-by-step guide to getting your OpenRouter API key. Plus: why many developers are switching to LLMWise for simpler setup, automatic failover, and no 5% markup.
Free preview, Starter for the Auto lane, Teams for manual GPT, Claude, and Gemini Pro access. Add-on credits kick in after included plan tokens are used.
Start on cheap auto-routed models first, then move up only when your workload truly needs premium manual control.
Go to openrouter.ai and click Sign Up. You can register with Google, GitHub, or email. OpenRouter will ask you to verify your email before you can generate API keys. The signup process takes about 2 minutes.
Once logged in, navigate to Keys in the left sidebar (or go to openrouter.ai/keys directly). Click Create Key, give it a name, and copy the key immediately - OpenRouter only shows it once. The key starts with sk-or- and looks like sk-or-v1-abc123... Store it in your .env file, never commit it to version control.
OpenRouter requires prepaid credits before you can make API calls to paid models. Go to the Credits page and add funds via credit card. OpenRouter charges the provider's token price plus a 5% markup on every request. Free models (open-source variants) work without credits but have strict rate limits - typically 10 requests per minute.
OpenRouter uses an OpenAI-compatible API format. Set your base URL to https://openrouter.ai/api/v1, pass your API key as a Bearer token, and send a standard chat completion request. Specify the model using OpenRouter's model ID format (e.g., anthropic/claude-sonnet-4.5). The response follows the OpenAI chat completion schema.
If you want the same multi-model access without the 5% markup, LLMWise offers a comparable setup with additional features. Sign up, get an API key, and you immediately have access to GPT-5.2, Claude Sonnet 4.5, Gemini 3 Flash, and more - with 20 free credits, no credit card required. LLMWise adds automatic circuit-breaker failover, Compare mode for side-by-side testing, and BYOK support with zero markup. The API format is similar: role/content messages with SSE streaming.
Operational checklist coverage for teams implementing this workflow in production.
Free preview, Starter for the Auto lane, Teams for manual GPT, Claude, and Gemini Pro access. Add-on credits kick in after included plan tokens are used.
Start on cheap auto-routed models first, then move up only when your workload truly needs premium manual control.
Pricing changes, new model launches, and optimization tips. No spam.