多模态

# 支持图像输入的模型
GET /v1/models?supported_parameters=vision
# 输出图像的模型
GET /v1/models?output_modalities=image
# 输出音频的模型
GET /v1/models?output_modalities=audio

{
  "model": "openai/gpt-5.4",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What's in this image?"},
      {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
    ]
  }]
}