Model information
Released
2025-08-07
Context window
400K
Max output
128K
Weights
Closed
Modalities
Input
ImageText
Output
Text
Identity
- Version
- gpt-5-mini
- Knowledge cutoff
- 2024-05-31
- Aliases
- GPT-5 Mini
Capabilities
AttachmentsReasoningStructuredTool call
Official price
input $0.25/M · output $2/M
cache read $0.025/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| AnyAPI | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | - | Yes | ||
| Poe | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool call | - | input $0.22/M · output $1.8/M cache read $0.022/M | Yes | ||
| Vivgrid | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool call | - | input $0.25/M · output $2/M cache read $0.03/M | Yes | ||
| NanoGPT | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoning | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| FastRouter | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callTemperature | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| NEAR AI Cloud | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| LLM Gateway | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| GitHub Copilot | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| 302.AI | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M | Yes | ||
| Helicone | gpt-5-mini | openai_chat | 400K | 128K | Tool call | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Neon | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| SAP AI Core | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Pioneer | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M · cache write $0.25/M | Yes | ||
| Abacus | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Azure Cognitive Services | gpt-5-mini | custom | 400K | 128K | AttachmentsReasoningTool call | - | input $0.25/M · output $2/M cache read $0.03/M | Yes | ||
| Azure | gpt-5-mini | openai_responses | 400K | 128K | AttachmentsReasoningTool call | - | input $0.25/M · output $2/M cache read $0.03/M | Yes | ||
| QiHang | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callTemperature | - | input $0.04/M · output $0.29/M | Yes | ||
| OrcaRouter | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Requesty | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool call | - | input $0.25/M · output $2/M cache read $0.03/M | Yes | ||
| Kilo Gateway | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Merge Gateway | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Vercel AI Gateway | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| OpenRouter | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | Moderated, Reasoning levels: high, medium, low, minimal, Default reasoning: medium, Reasoning required | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| Jiekou.AI | gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.225/M · output $1.8/M | Yes | ||
| Perplexity Agent | openai/gpt-5-mini | openai_chat | 400K | 128K | AttachmentsReasoningTool call | - | input $0.25/M · output $2/M cache read $0.025/M | Yes | ||
| OpenAI | gpt-5-mini | openai_responses | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.25/M · output $2/M cache read $0.025/M | Yes |