max_completion_tokens

128000

modalities

{
  "input_modalities": [
    "text",
    "image",
    "file"
  ],
  "output_modalities": [
    "text"
  ]
}

moderated

true

rate

{
  "prompt": "0.000005",
  "completion": "0.00003",
  "web_search": "0.01",
  "input_cache_read": "0.0000005"
}

supported_parameters

[
  "max_tokens",
  "response_format",
  "seed",
  "structured_outputs",
  "tool_choice",
  "tools"
]