openrouter
chat
vision
open-source
Test your OpenRouter API key.
Validate an OpenRouter key and see your credit balance plus the catalogue of models routed through one API.
Stateless proxy — keys never logged, stored, or persisted. What happens to your key →
Detected
OpenRouter
What this key does
OpenRouter is a routing layer over OpenAI, Anthropic, Google, Meta, Mistral, and dozens of others. One key, one shape, one bill. Useful for fallback and price comparison.
How to get a OpenRouter API key
- Sign in at openrouter.ai.
- Top up credits or attach a card.
- Create a key starting with sk-or-v1-.
- Paste it here. We'll also pull your remaining balance.
Common errors and fixes
- 401 Unauthorized: Key is invalid, revoked, or pasted with extra whitespace. Generate a new key from the provider console and try again.
- 403 Forbidden: Key is valid but lacks permission for this resource. Check project / org / workspace scope, or that billing is set up for this key.
- 429 Too Many Requests: You hit the per-minute or per-day rate limit. Wait a moment and retry, or upgrade your tier.
- 404 Not Found: The endpoint or model id changed. Check the provider docs for the current path and model identifier.
- 5xx: The provider is having issues. Check their status page before assuming the bug is yours.
Security best practices
- Store keys in an env var or secret manager — never commit them to a repo, even a private one.
- Restrict scope: prefer per-project or per-deployment keys over a single root key shared across services.
- Rotate on a schedule (90 days is a sane default) and immediately on suspected leak.
- Audit usage in the provider console after rotation to confirm the old key has zero traffic.
- Set per-key spend limits where the provider supports them, so a leaked key has a bounded blast radius.
Pricing at a glance
OpenRouter passes through provider pricing with a thin markup. The savings come from automatic fallback and the ability to A/B between providers without touching code.
FAQ
- Why not just call providers directly?
- Two reasons: one bill across all providers, and fallback / price routing without writing the orchestration yourself.
- Is OpenRouter OpenAI-compatible?
- Yes — base URL https://openrouter.ai/api/v1.
- How is privacy handled?
- OpenRouter does not log prompt content by default. Some upstream providers may have their own logging — check OpenRouter's per-provider settings.
- Does it support streaming?
- Yes, on every model that the underlying provider streams.
- Can I see my credit balance?
- Yes — the validation pulls /v1/credits and we show your remaining balance and total spend.
- What model identifiers do I use?
- vendor/model — e.g. openai/gpt-4o, anthropic/claude-3.5-sonnet, google/gemini-2.5-pro.
Test other providers
Related reading
- OpenAI vs Anthropic pricing in 2026A side-by-side breakdown of OpenAI and Anthropic per-token pricing, batch discounts, and prompt-caching savings.
- Free LLM API keys for testing in 2026Which providers offer free credits, how long they last, and how to stretch them for prototyping without a credit card.