Model information
Released
2026-02-19
Context window
1M
Max output
66K
Weights
Closed
Modalities
Input
AudioDocumentImageTextVideo
Output
Text
Identity
- Version
- gemini-3.1-pro-preview
- Knowledge cutoff
- 2025-01
- Aliases
- Gemini 3.1 Pro Preview
Capabilities
AttachmentsReasoningStructuredTemperatureTool call
Official price
input $2/M · output $12/M
cache read $0.2/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Vivgrid | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| gemini-3.1-pro-preview | google_generate_content | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | |||
| NanoGPT | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M · cache write $0.375/M | Yes | ||
| FastRouter | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M | Yes | ||
| DaoXE | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| LLM Gateway | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| GitHub Copilot | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| FrogBot | gemini-3-1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| ZenMux | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callTemperature | - | input $2/M · output $12/M cache read $0.2/M · cache write $4.5/M | Yes | ||
| Abacus | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| Venice AI | gemini-3-1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2.5/M · output $15/M cache read $0.5/M · cache write $0.5/M | Yes | ||
| Auriko | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| AIHubMix | gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| Ofox | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M · cache write $4.5/M | Yes | ||
| OrcaRouter | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $4/M · output $18/M cache read $0.2/M | Yes | ||
| Vertex | gemini-3.1-pro-preview | custom | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| Kilo Gateway | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M · cache write $0.375/M | Yes | ||
| Merge Gateway | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| Vercel AI Gateway | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes | ||
| OpenRouter | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callStructuredTemperature | Reasoning levels: high, medium, low, Default reasoning: medium, Reasoning required | input $2/M · output $12/M cache read $0.2/M · cache write $0.375/M | Yes | ||
| Perplexity Agent | google/gemini-3.1-pro-preview | openai_chat | 1M | 66K | AttachmentsReasoningTool callTemperature | - | input $2/M · output $12/M cache read $0.2/M | Yes |