Model information
Released
2026-05-19
Context window
1M
Max output
66K
Weights
Closed
Modalities
Input
AudioDocumentImageTextVideo
Output
Text
Identity
- Version
- gemini-3.5-flash
- Knowledge cutoff
- 2025-01
- Aliases
- Gemini 3.5 Flash
Capabilities
AttachmentsReasoningStructuredTemperatureTool call
Official price
input $1.5/M · output $9/M
cache read $0.15/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Poe | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructured | - | input $1.515/M · output $9.091/M cache read $0.152/M | Yes | ||
| gemini-3.5-flash | google_generate_content | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | |||
| NanoGPT | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| FastRouter | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M | Yes | ||
| NEAR AI Cloud | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| LLM Gateway | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M · cache write $0.083/M | Yes | ||
| OpenCode Zen | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| GitHub Copilot | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| Neon | gemini-3-5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| UnoRouter | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.186/M · output $1.114/M | Yes | ||
| SAP AI Core | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| Pioneer | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M · cache write $0.083/M | Yes | ||
| ZenMux | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| Abacus | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| Venice AI | gemini-3-5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.55/M · output $9.45/M cache read $0.155/M · cache write $0.086/M | Yes | ||
| AIHubMix | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $1.5/M | Yes | ||
| Vertex | gemini-3.5-flash | custom | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| Kilo Gateway | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M · cache write $0.083/M | Yes | ||
| Merge Gateway | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| Vercel AI Gateway | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.5/M · output $9/M cache read $0.15/M | Yes | ||
| OpenRouter | google/gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | Reasoning levels: high, medium, low, minimal, Default reasoning: medium, Reasoning required | input $1.5/M · output $9/M cache read $0.15/M · cache write $0.083/M | Yes | ||
| Xpersona | gemini-3.5-flash | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.55/M · output $12.2/M cache read $0.155/M | Yes |