Model information
Released
2025-12-17
Context window
1M
Max output
66K
Weights
Closed
Modalities
Input
AudioDocumentImageTextVideo
Output
Text
Identity
- Version
- gemini-3-flash-preview
- Knowledge cutoff
- 2025-01
- Aliases
- Gemini 3 Flash Preview
Capabilities
AttachmentsReasoningStructuredTemperatureTool call
Official price
input $0.5/M · output $3/M
cache read $0.05/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| AnyAPI | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | - | Yes | ||
| gemini-3-flash-preview | google_generate_content | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | |||
| NanoGPT | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| LLM Gateway | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| GitHub Copilot | gemini-3-flash-preview | openai_chat | 1M | 66K | - | - | - | Yes | ||
| 302.AI | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsTool callTemperature | - | input $0.5/M · output $3/M | Yes | ||
| FrogBot | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| ZenMux | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callTemperature | - | input $0.5/M · output $3/M cache read $0.05/M · cache write $1/M | Yes | ||
| Abacus | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| Venice AI | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.7/M · output $3.75/M cache read $0.07/M | Yes | ||
| QiHang | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.07/M · output $0.43/M | Yes | ||
| AIHubMix | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| OrcaRouter | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| Vertex | gemini-3-flash-preview | custom | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| Requesty | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callTemperature | - | input $0.5/M · output $3/M cache read $0.05/M · cache write $1/M | Yes | ||
| Kilo Gateway | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M · cache write $0.083/M | Yes | ||
| Merge Gateway | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes | ||
| OpenRouter | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | Reasoning levels: high, medium, low, minimal, Default reasoning: medium | input $0.5/M · output $3/M cache read $0.05/M · cache write $0.083/M | Yes | ||
| Jiekou.AI | gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsTool callStructuredTemperature | - | input $0.5/M · output $3/M | Yes | ||
| Perplexity Agent | google/gemini-3-flash-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callTemperature | - | input $0.5/M · output $3/M cache read $0.05/M | Yes |