import httpx
from urllib.parse import quote

model_id = quote("paddleocr/pp-ocrv6", safe="")
response = httpx.get(
    f"https://gateway.vlm.run/v1/models/{model_id}",
    headers={"Authorization": "Bearer <VLMRUN_API_KEY>"},
)
print(response.json())

const modelId = encodeURIComponent("paddleocr/pp-ocrv6");
const response = await fetch(`https://gateway.vlm.run/v1/models/${modelId}`, {
  headers: { Authorization: "Bearer <VLMRUN_API_KEY>" },
});
console.log(await response.json());

vlmrun gw models pp-ocrv6

curl "https://gateway.vlm.run/v1/models/paddleocr%2Fpp-ocrv6" \
  -H "Authorization: Bearer $VLMRUN_API_KEY"

{
  "id": "qwen/qwen3.5-0.8b",
  "hf_model_id": "AxionML/Qwen3.5-0.8B-NVFP4",
  "name": "Qwen3.5 0.8B",
  "description": "Multimodal chat model with up to 64 images or one video per request.",
  "task": "chat",
  "context_length": 262144,
  "architecture": {
    "input_modalities": ["text", "image", "video"],
    "output_modalities": ["text"],
    "modality": "text+image+video->text"
  },
  "capabilities": {
    "max_images": 64,
    "max_videos": 1,
    "supports_text_only": true,
    "supports_document_url": false,
    "supports_json_object": true,
    "supports_json_schema": true,
    "supported_input_types": ["text", "image_url", "video_url"]
  },
  "aliases": ["Qwen/Qwen3.5-0.8B"],
  "methods": ["chat"],
  "supported_parameters": ["temperature", "top_p", "top_k", "min_p", "seed", "max_tokens", "max_completion_tokens", "stop", "presence_penalty", "frequency_penalty", "repetition_penalty", "logprobs", "top_logprobs", "response_format", "stream", "stream_options"],
  "pricing": {
    "prompt": 0.08,
    "completion": 0.15,
    "input_cache_read": 0.02,
    "input_cache_write": 0.0,
    "image": 0.0,
    "video": 0.0
  }
}

{
  "detail": {
    "error": {
      "message": "Model 'does-not/exist' not found.",
      "type": "model_not_found",
      "code": null,
      "param": null
    }
  }
}