Model information
Released
2025-04-16
Context window
200K
Max output
100K
Weights
Closed
Modalities
Input
ImageText
Output
Text
Identity
- Version
- o4-mini
- Knowledge cutoff
- 2024-06-01
- Aliases
- o4-mini
Capabilities
AttachmentsReasoningStructuredTool call
Official price
input $1.1/M · output $4.4/M
cache read $0.275/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| AnyAPI | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | - | Yes | ||
| Poe | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool call | - | input $0.99/M · output $4/M cache read $0.25/M | Yes | ||
| NanoGPT | openai/o4-mini | openai_chat | 200K | 100K | ReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.55/M | Yes | ||
| NEAR AI Cloud | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| LLM Gateway | o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| Helicone | o4-mini | openai_chat | 200K | 100K | Tool call | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| Abacus | o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M | Yes | ||
| Azure Cognitive Services | o4-mini | custom | 200K | 100K | AttachmentsReasoningTool call | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| Model Oracle AI | o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | - | Yes | ||
| Azure | o4-mini | openai_responses | 200K | 100K | AttachmentsReasoningTool call | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| Requesty | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callTemperature | - | input $1.1/M · output $4.4/M cache read $0.28/M | Yes | ||
| Kilo Gateway | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| Merge Gateway | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| GitHub Models | openai/o4-mini | openai_chat | 200K | 100K | - | - | - | Yes | ||
| Vercel AI Gateway | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| OpenRouter | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | Moderated | input $1.1/M · output $4.4/M cache read $0.275/M | Yes | ||
| Cloudflare AI Gateway | openai/o4-mini | openai_chat | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.28/M | Yes | ||
| Jiekou.AI | o4-mini | openai_chat | 200K | 100K | AttachmentsTool callStructuredTemperature | - | input $1.1/M · output $4.4/M | Yes | ||
| OpenAI | o4-mini | openai_responses | 200K | 100K | AttachmentsReasoningTool callStructured | - | input $1.1/M · output $4.4/M cache read $0.275/M | Yes |