HPP Router Playground
Models, pricing, API docs, and LLM testing — no admin login required
Need an API key? Get one from HPP Hub.
Test LLM Inference
provider/model
Stored in sessionStorage for this tab only.
PNG/JPEG/GIF/WebP · max 5
Multimodal via image_url in chat completions. Large images are resized client-side before upload.
Your Usage
Enter your API key above to view usage statistics.
Total Requests
-
Total Tokens
-
Quota Used
-
Quota Remaining
-
Provider Usage
Recent Requests
Last 15 requests (newest first).
| Time | Provider | Model | Tokens | Billed | Status |
|---|---|---|---|---|---|
| No requests yet | |||||
API Endpoints
OpenAI Compatible
…
Use provider/model or hpprouter/auto for smart routing.
Native Anthropic (Claude Code)
…
Example — chat (curl)
Example — vision / multimodal (curl)
Replace BASE64_IMAGE_DATA with a PNG/JPEG base64 payload (no data: prefix). Works with vision-capable models such as openai/gpt-4o.
Model Pricing
Rates shown per 1M tokens (USD).
| Model | Input ($/1M) | Output ($/1M) | Cache Write | Cache Read |
|---|---|---|---|---|
| Loading… | ||||