Free credits / metered
openrouter/OpenRouter
100+ models via one API key. 27 free-tier models.
openrouter.aiQuick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click OpenRouter
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
openrouter/anthropic/claude-opus-4How OpenRouter billing works with kRouter
OpenRouter gives you free starting credits, then bills per token. kRouter tracks the remaining quota and fails over to another provider before you hit a wall. kRouter authenticates it via apikey. 14 models are routable as openrouter/<model>. Its catalog is fetched live, so new models appear without a kRouter update.
Through kRouter, OpenRouter serves chat and code completion, embeddings, exposed on /v1/embeddings, text-to-speech, exposed on /v1/audio/speech, image understanding (OCR / vision-to-text). Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from OpenRouter is a one-line model change in your client rather than a rewrite.
Free tier: 27+ free models, no credit card needed, 200 req/day. After $10 credit: 1,000 req/day.
OpenRouter models & pricing
Prices are USD per 1M tokens, cheapest first. kRouter bills nothing on top; this is the provider's own rate.
| Model | Route as | Input /1M | Output /1M |
|---|---|---|---|
| Qwen3 Embedding 8B | openrouter/qwen/qwen3-embedding-8b | $0.50 | $2.00 |
| OpenAI Text Embedding 3 Large | openrouter/openai/text-embedding-3-large | — | — |
| OpenAI Text Embedding 3 Small | openrouter/openai/text-embedding-3-small | — | — |
| OpenAI Text Embedding Ada 002 | openrouter/openai/text-embedding-ada-002 | — | — |
| Perplexity Embed V1 4B | openrouter/perplexity/pplx-embed-v1-4b | — | — |
| Perplexity Embed V1 0.6B | openrouter/perplexity/pplx-embed-v1-0.6b | — | — |
| NVIDIA Nemotron Embed VL 1B V2 (Free) | openrouter/nvidia/llama-nemotron-embed-vl-1b-v2:free | — | — |
| GPT-4o Mini TTS | openrouter/openai/gpt-4o-mini-tts | — | — |
| TTS-1 HD | openrouter/openai/tts-1-hd | — | — |
| TTS-1 | openrouter/openai/tts-1 | — | — |
| DALL-E 3 (via OpenRouter) | openrouter/openai/dall-e-3 | — | — |
| GPT Image 1 (via OpenRouter) | openrouter/openai/gpt-image-1 | — | — |
| Imagen 3 (via OpenRouter) | openrouter/google/imagen-3.0-generate-002 | — | — |
| FLUX.1 Schnell (via OpenRouter) | openrouter/black-forest-labs/FLUX.1-schnell | — | — |
OpenRouter links
OpenRouter FAQ
Is OpenRouter free through kRouter?
OpenRouter is pay-per-token: you bring your own API key and are billed by OpenRouter at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use OpenRouter with Claude Code or Cursor?
Connect OpenRouter in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as openrouter/<model>.
Which OpenRouter models can kRouter route to?
14 models, including OpenAI Text Embedding 3 Large, OpenAI Text Embedding 3 Small, OpenAI Text Embedding Ada 002. Every one is addressed as openrouter/<model> from any client.
What happens when OpenRouter is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.