G
Gemini 2.5 Flash
Gemini 2.5 Flash, a language model from Google.
modelOverride: { model: "gemini-2.5-flash" }
GGoogle·Released June 2025
Pricing
- Input
- $0.30 / 1M
- Cached input
- $0.030 / 1M
- Output
- $2.50 / 1M
- Input
- $0.54 / 1M
- Output
- $4.50 / 1M
Specifications
- Context window
- 1,000,000 tokens
- Max output
- 64,000 tokens
- Released
- June 2025
- Capabilities
- VisionFastLow costLarge contextMultimodal
Parameters
Model options, passed in
modelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
thinkingBudget | Select | auto | offmanualauto |
thinkingBudgetLimitMust be less than Max Response Size | Number | — | 1–24576 |
tools | Tools | — | — |
priorityMode | Select | false | falsetrue |
Use this model
await mindstudio.generateText({ message: "...", modelOverride: { model: "gemini-2.5-flash", config: { priorityMode: "false", }, }, });