max_completion_tokens

4096

modalities

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

moderated

true

rate

{
  "prompt": "0.00000025",
  "completion": "0.00000125",
  "web_search": "0.01",
  "input_cache_read": "0.00000003",
  "input_cache_write": "0.0000003",
  "input_cache_write_1h": "0.0000005"
}

supported_parameters

[
  "max_tokens",
  "stop",
  "temperature",
  "tool_choice",
  "tools",
  "top_k",
  "top_p"
]