Google: Gemini 3.5 Flash
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
Specification
- Model ID
- google/gemini-3.5-flash
- Weight license
- Not verified; consult the exact publisher model card
- Modality
- Text+image+file+audio+video >text
- Context
- 1.0M tokens
- Input
- $1.50/1M
- Output
- $9.00/1M
- Image
- $1.50/1M
- Audio
- $3.00/1M
- Web search
- $14000.00/1M
- Updated
- Nov 14, 2026
Scores
Capabilities
- Supports tool calling
- Supports vision inputs
- Supports long-context workflows
- Supports deeper reasoning tasks
Input and output
Accepts Text, Image, Video, File, Audio inputs. Returns Text outputs.
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Related models
Build with Google: Gemini 3.5 Flash
Describe what you want to make and pick this model in the composer. A database and hosting are included.