Try MiniMax FastH3 from Fastvideo →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
LLM & ChatActive

google / gemini-3.5-flash

gemini-3.5-flash

bygoogle

Google’s Gemini 3.5 Flash is a fast multimodal reasoning model built for agents, coding, and long-context analysis. It takes text plus media and returns text.

Partner LLM
Model ID
gemini-3.5-flash
Provider
google
Runs
25218
Updated
1779364683
gemini-3.5-flash
25218
Runs
11
Comments
Average rating : 4.5 (19 users)
Providergoogle
Modelgemini-3.5-flash
Runs25218
Partner LLM
wiro playground—google/gemini-3.5-flash
Reset to defaults
Delete All
0 / 50
Maximum 50 files allowed

Optional. Supports images, videos, and audio.

Required.

Random

Required for chat history. Numeric or string ID.

Random

Required for chat history. Numeric or string ID.

Sample outputs

No samples yet

Run this model to create outputs and build up samples.

Updated 1779364683

Overview

Gemini 3.5 Flash is a natively multimodal reasoning model from Google DeepMind. It reads text and can also interpret images, audio, and video, then produces a text response. It supports “thinking levels” that change how deeply it reasons before it answers. This makes it a strong pick for agent-style workflows where the model must plan, iterate, and keep context across many steps.

What you can build

  • Coding copilots that draft, refactor, and explain code with multi-step plans
  • Agent workflows that break large tasks into steps and track progress across turns
  • Screenshot and chart explainers for UI debugging, dashboards, and scientific figures
  • Audio summarizers for meetings, interviews, and long recordings
  • Video understanding tools that describe scenes, events, and changes over time
  • High-volume text pipelines for classification, extraction, rewriting, and translation

Inputs

  • A required instruction written as plain text, such as a question or task description
  • Optional images you want the model to interpret, with support for multiple images per request
  • Optional videos for analysis, with support for multiple videos per request and long durations
  • Optional audio for analysis, including long recordings
  • Optional system-style instructions that set the role, tone, and rules for the whole session
  • Optional reasoning depth selection (from minimal to high) to trade speed for deeper reasoning
  • Optional randomness controls for generation to make outputs more deterministic or more varied
  • An optional cap on response length, up to 65,536 tokens
  • Optional user and session identifiers to keep multi-turn chat history consistent

Outputs

Gemini 3.5 Flash returns text. The text can be short answers, long reports, step-by-step plans, or code blocks. It can produce very long responses, up to 65,536 tokens, when you allow it.

Limitations

  • The model’s output is text only. It does not generate images, audio, or video.
  • The maximum input context is up to 1,048,576 tokens, and the maximum output is 65,536 tokens.
  • Very long or messy inputs can still cause missed details. Clear structure helps a lot.
  • Blurry screenshots, tiny on-image text, noisy audio, and low-detail video reduce accuracy.
  • The model can plan actions, but it cannot take real actions without tools your app provides.

Safety & compliance

Gemini 3.5 Flash was developed under Google’s Frontier Safety Framework. It includes strengthened safeguards for cyber and CBRN-related harmful requests. Expect refusals for disallowed content, plus filtering for unsafe instructions. You are responsible for complying with applicable laws, product policies, and the rights you have to any content you upload.

API quick start

Run gemini-3.5-flash with a single API call.

POST https://api.wiro.ai/v1/Run/google/gemini-3.5-flash
{
  "prompt": "Tell me about Türkiye",
  "inputAll": "https://your-cdn.com/input.png",
  "user_id": "...",
  "session_id": "..."
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion