Gemini 3.6 Flash
Gemini 3.6 Flash remains a supported GA efficiency-first model, while Gemini 3.8 Flash is the newer workhorse for harder coding, multimodal analysis, knowledge work, and multi-step agent workflows.
Platform: Replicate
Language ModelMultimodalCoding AssistantAgent WorkflowsLong ContextGoogle
Gemini API / Google AI Studio / Gemini Enterprise / Google Antigravity
Gemini API standard paid tier: $1.50 per million input tokens and $7.50 per million output tokens
Commercial🚀Function Overview
Gemini 3.6 Flash improves coding, multimodal, and agentic performance over Gemini 3.5 Flash while lowering standard output-token pricing and reducing token use in Google-reported evaluations.
Key Features
- Official GA Gemini API model ID gemini-3.6-flash
- 1-million-token context window and 64K maximum output
- Text, image, audio, and video input with text output
- Medium default thinking level with configurable thinking effort
- Built-in tools including Computer Use
- Standard Gemini API pricing of $1.50 per million input tokens and $7.50 per million output tokens
- March 2026 knowledge cutoff in the official model card
- Recommended migration target for Gemini 3.5 Flash, Gemini 3 Flash Preview, and Gemini 3.1 Pro
Use Cases
- •Multi-step coding and repository agents
- •Document, chart, image, audio, and video analysis
- •Knowledge-work automation and report generation
- •Computer-use agents on supported Gemini surfaces
- •Production migration from earlier Gemini Flash models
⚙️Input Parameters
model
stringUse gemini-3.6-flash for the generally available Gemini API model.
input
objectInteractions API input containing text or supported multimodal content such as images, audio, and video.
system_instruction
stringOptional system-level behavior and output-format instruction.
thinking_level
stringReasoning-effort control; medium is the documented default for Gemini 3.6 Flash.
💡Usage Examples
Example 1
Input Parameters
{
"model": "gemini-3.6-flash",
"input": "Inspect this migration plan, identify the riskiest assumption, and return the smallest verifiable implementation sequence.",
"thinking_level": "medium"
}Output Results
Gemini 3.6 Flash returns a text response through the Gemini Interactions API. Validate tool calls, token use, latency, and task success against the current API contract before production migration.
Quick Actions
Technical Specifications
- Hardware Type
- Gemini API / Google AI Studio / Gemini Enterprise / Google Antigravity
- Commercial Use
- Supported
- Pricing
- Gemini API standard paid tier: $1.50 per million input tokens and $7.50 per million output tokens
- Platform
- Replicate