Gemini 3 Flash Preview

Capabilities

Capability	Supported
Vision (image input)	Yes
Document input	No
Audio input	No
Tool calling	Yes
Thinking	Yes

Thinking

This model supports a controllable thinking mode, exposed as reasoning_effort. Allowed values: low, medium, high.

Unlike the chat composer, the developer API forwards the request body verbatim and never adds this parameter. If it is not sent, the model answers without extended thinking.

JSON

{
    "model": "gemini-3-flash-preview",
    "messages": [
        {
            "role": "user",
            "content": "Explain the Monty Hall problem."
        }
    ],
    "reasoning_effort": "high"
}

Reasoning tokens are billed as ordinary completion tokens, with no separate rate.

Parameters

Every field below except brand is relayed to the upstream gateway untouched. Parameters beyond this list may work but are not guaranteed. brand is the one field AI HUB consumes.

Parameter	Type	Notes
`model`	string	Required. A published model slug (see Models).
`messages`	array	Required. Role/content turns: system, user, assistant.
`stream`	boolean	Optional. Stream tokens as server-sent events. Defaults to false.
`temperature`	number	Optional. Relayed to the model untouched.
`max_tokens`	integer	Optional. Caps the response length.
`top_p`	number	Optional. Relayed to the model untouched.
`stop`	string \| array	Optional. One stop string or an array of them. Relayed to the model untouched.
`response_format`	object	Optional. Relayed to the model untouched. Support varies by model.
`tools`	array	Optional. Function/tool definitions. Relayed to the model untouched. Support varies by model.
`tool_choice`	string \| object	Optional. Relayed to the model untouched.
`seed`	integer	Optional. Relayed to the model untouched. Support varies by model.
`reasoning_effort`	string	Optional. low, medium, or high. Only has an effect on a thinking-capable model, as listed on that model's own page.
`brand`	string	Optional. A Brand DNA id from the account. Unlike every other field here, this one is NOT relayed. AI HUB consumes it, prepends the brand's voice as a system message, and removes it before the request reaches the model.

Example

cURL

curl https://console.aimodelhub.ai/v1/chat/completions \
  -H "Authorization: Bearer $AIHUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-3-flash-preview","messages":[{"role":"user","content":"Hello!"}]}'