Model information
Released
2025-10-06
Context window
400K
Max output
272K
Weights
Closed
Modalities
Input
ImageText
Output
Text
Identity
- Version
- gpt-5-pro
- Knowledge cutoff
- 2024-09-30
- Aliases
- GPT-5 Pro
Capabilities
AttachmentsReasoningStructuredTool call
Official price
input $15/M · output $120/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Poe | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool call | - | input $14/M · output $110/M | Yes | ||
| NanoGPT | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoning | - | input $15/M · output $120/M cache read $1.5/M | Yes | ||
| LLM Gateway | gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| 302.AI | gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| Helicone | gpt-5-pro | openai_chat | 400K | 272K | - | - | input $15/M · output $120/M | Yes | ||
| Azure Cognitive Services | gpt-5-pro | custom | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| Azure | gpt-5-pro | openai_responses | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| OrcaRouter | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| Requesty | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| Kilo Gateway | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes | ||
| Vercel AI Gateway | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructuredTemperature | - | input $15/M · output $120/M | Yes | ||
| OpenRouter | openai/gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructured | Moderated, Reasoning levels: high, Default reasoning: high, Reasoning required | input $15/M · output $120/M | Yes | ||
| Jiekou.AI | gpt-5-pro | openai_chat | 400K | 272K | AttachmentsReasoningTool callStructuredTemperature | - | input $13.5/M · output $108/M | Yes | ||
| OpenAI | gpt-5-pro | openai_responses | 400K | 272K | AttachmentsReasoningTool callStructured | - | input $15/M · output $120/M | Yes |