from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

models = client.models.list()
for model in models.data:
    caps = model.capabilities
    print(f"{model.id}: {caps.supported_input_types}")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.vlm.run/v1/openai",
  apiKey: process.env.VLMRUN_API_KEY,
});

const models = await client.models.list();
for (const model of models.data) {
  console.log(model.id);
}

vlmrun gw models

curl https://gateway.vlm.run/v1/openai/models \
  -H "Authorization: Bearer $VLMRUN_API_KEY"

{
  "object": "list",
  "data": [
    {
      "id": "qwen/qwen3.5-0.8b",
      "object": "model",
      "created": 1791157912,
      "owned_by": "vlm-run",
      "aliases": [],
      "methods": [],
      "default_method": "",
      "extra_body_help": "Multimodal chat (text + up to 64 images or 1 base64 video). No document_url: replies pass through verbatim.",
      "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"
        ]
      },
      "provider": "",
      "task": "chat",
      "task_capabilities": [
        "chat",
        "caption",
        "detection"
      ],
      "output_tps": 44.0,
      "context_length": 262144,
      "max_output_tokens": null,
      "name": "Qwen3.5 0.8B",
      "description": "Multimodal chat model with up to 64 images or one video per request.",
      "hf_model_id": "AxionML/Qwen3.5-0.8B-NVFP4",
      "pricing": {
        "prompt": 0.08,
        "completion": 0.15,
        "input_cache_read": 0.02,
        "input_cache_write": 0.0,
        "image": 0.0,
        "video": 0.0
      },
      "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"
      ],
      "is_ready": true
    },
    {
      "id": "zai-org/glm-ocr",
      "object": "model",
      "created": 1791157912,
      "owned_by": "vlm-run",
      "aliases": [
        "glm-ocr",
        "zai-org/GLM-OCR"
      ],
      "methods": [
        "markdown"
      ],
      "default_method": "markdown",
      "extra_body_help": "{\"method\":\"markdown\"} | document_url PDF (markdown per page)",
      "capabilities": {
        "max_images": 1,
        "max_videos": 0,
        "supports_text_only": false,
        "supports_document_url": true,
        "supports_json_object": true,
        "supports_json_schema": false,
        "supported_input_types": [
          "text",
          "image_url",
          "document_url",
          "file_url"
        ]
      },
      "provider": "",
      "task": "chat",
      "task_capabilities": [
        "markdown"
      ],
      "output_tps": 601.0,
      "context_length": 8192,
      "max_output_tokens": 8192,
      "name": "GLM-OCR",
      "description": "Compact multilingual document OCR and markdown extraction.",
      "hf_model_id": "zai-org/GLM-OCR",
      "pricing": {
        "prompt": 0.1,
        "completion": 0.2,
        "input_cache_read": 0.02,
        "input_cache_write": 0.0,
        "image": 30.0,
        "video": 0.0
      },
      "supported_parameters": [],
      "is_ready": true
    }
  ]
}