Gemini 3 Pro
PremiumGoogle · Text · Video → Text
Google’s top Gemini model — text, image, and video reasoning.
gemini-3-proWorkflow: geminiOverview
Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.
That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.
The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.
Make a request
Call the workflow with ai.apis.run() in TypeScript, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.
These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// Calls the 'gemini' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('gemini', {
contents: [
{
parts: []
}
]
}, {
mode: ApiRunMode.SYNC,
});
console.log(result); // workflow-specific output
console.log(usage?.credits); // credits chargedParameters
4 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
contentsContents array with parts | Content[] | yes | — | — |
└ partsArray of parts containing text and/or image data | GeminiPart[] | yes | — | — |
└ textText input | string | no | — | e.g. Hi, This is a picture of me. Can you add a llama next to me |
└ imageUrl | string | no | — | — |
└ audioUrlURL pointing to the generated audio file | string | no | — | — |
└ typedeprecatedOnly used for custom imageUrl data | string | no | — | — |
└ fileDataFile data | object | no | — | — |
└ inlineDataInline data | object | no | — | — |
└ functionCallA predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name with the arguments and their values. | object | no | — | — |
└ functionResponseThe result output of a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. | object | no | — | — |
└ thought | boolean | no | — | — |
└ thoughtSignatureOptional. An opaque signature for the thought so it can be reused in subsequent requests. A base64-encoded string | string | no | — | — |
└ partMetadataCustom metadata associated with the Part | object | no | — | — |
└ videoMetadataOptional. Video metadata | object | no | — | — |
└ role | string | no | — | — |
generationConfig | object | no | — | — |
└ temperatureTemperature value for controlling randomness | number | no | — | e.g. 1.2 |
└ topKTop-K sampling value | number | no | — | e.g. 40 |
└ topPTop-P (nucleus) sampling value | number | no | 1 | e.g. 0.95 |
└ maxOutputTokensMaximum number of output tokens | number | no | — | e.g. 8192 |
└ candidateCountNumber of response variations to return. | number | no | — | e.g. 2 |
└ responseMimeTypeResponse MIME type | string | no | — | e.g. text/plain |
└ imageConfigImage config | object | no | — | — |
└ aspectRatioImage aspect ratio. Support is model-dependent: the extreme ratios 1:4, 4:1, 1:8, 8:1 are only supported by Gemini 3 image models. gemini-2.5-flash-image supports only 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 and returns 400 unsupported_aspect_ratio for any other value. | string | no | — | 1:12:33:23:44:34:55:49:1616:921:91:44:11:88:1 |
└ imageSizeImage resolution. Support is model-dependent: gemini-2.5-flash-image and gemini-3.1-flash-lite-image support 1K only; gemini-3-pro-image supports 1K, 2K, 4K; gemini-3.1-flash-image supports 0.5K, 1K, 2K, 4K. | string | no | — | 0.5K1K2K4K |
└ responseModalitiesResponse modalities | string[] | no | — | e.g. ["Text","Image","Audio"] |
└ thinkingConfigConfiguration for the model's thinking/reasoning capabilities. Supported by gemini-2.5-pro, gemini-2.5-flash, gemini-3-pro, gemini-3.1-pro, gemini-3-pro-image. | object | no | — | — |
└ thinkingBudgetNumber of thinking tokens the model should use. Range: 0-24576. Set to 0 to disable thinking. Not supported by gemini-2.5-flash-image or gemini-3.1-flash-lite-image. | number | no | — | 0–24576 e.g. 1024 |
└ includeThoughtsWhether to include thought summaries in the response. When true, the response will contain thought parts. | boolean | no | false | e.g. true |
└ thinkingLevelControls the depth of the model's internal reasoning process. Only LOW and HIGH are supported. Not supported by gemini-2.5-flash-image or gemini-3-pro-image. | string | no | — | MINIMALLOWMEDIUMHIGH |
└ speechConfigSpeech configuration for TTS. Use voiceConfig for single-speaker or multiSpeakerVoiceConfig for multi-speaker. | object | no | — | — |
└ voiceConfigSingle-speaker voice config | object | no | — | — |
└ multiSpeakerVoiceConfigMulti-speaker voice config | object | no | — | — |
modelModel for image generation | string | no | gemini-2.0-flash-preview-image-generation | gemini-2.5-progemini-2.5-flashgemini-2.5-flash-image-previewgemini-2.5-flash-imagegemini-2.5-flash-lite-preview-06-17gemini-2.0-flashgemini-2.0-flash-preview-image-generationgemini-2.0-flash-litegemini-1.5-flashgemini-1.5-flash-8bgemini-1.5-progemini-embedding-expgemini-3-progemini-3-pro-previewgemini-3.1-pro-previewgemini-3.1-flash-litegemini-3.1-flash-lite-previewgemini-3-pro-imagegemini-3-pro-image-previewgemini-3.1-flash-image-previewgemini-3.1-flash-imagegemini-3.1-flash-lite-imagegemini-2.5-flash-ttsgemini-2.5-pro-ttsinstant-ramen |
toolsOptional tools with function declarations | object[] | no | — | — |
Response
Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the resultitself is the vendor's own shape.
{
"result": {
"candidates": [
{
"content": {
"parts": []
},
"finishReason": "…",
"index": 0
}
]
},
"usage": {
"credits": 360
}
}