Model information
Released
2026-04-23
Context window
1.1M
Max output
128K
Weights
Closed
Modalities
Input
ImageText
Output
Text
Identity
- Version
- gpt-5.5
- Knowledge cutoff
- 2025-12-01
- Aliases
- GPT-5.5
Capabilities
AttachmentsReasoningStructuredTool call
Official price
input $5/M · output $30/M
cache read $0.5/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| CrossModel | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M · cache write $5/M | Yes | ||
| Poe | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $4.546/M · output $27.273/M cache read $0.455/M | Yes | ||
| Vivgrid | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| NanoGPT | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| FastRouter | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M | Yes | ||
| NEAR AI Cloud | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| DaoXE | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| LLM Gateway | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Kenari | gpt-5-5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $0/M · output $0/M | Yes | ||
| OpenCode Zen | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| GitHub Copilot | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| UnoRouter | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $0.188/M · output $1.125/M | Yes | ||
| UnoRouter | gpt-5.5:free | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $0/M · output $0/M | Yes | ||
| FrogBot | gpt-5-5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool call | - | input $2.5/M · output $15/M cache read $0.25/M | Yes | ||
| SAP AI Core | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Pioneer | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M · cache write $5/M | Yes | ||
| AI-ROUTER | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| ZenMux | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Abacus | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Azure Cognitive Services | gpt-5.5 | custom | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Model Oracle AI | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | - | Yes | ||
| Azure | gpt-5.5 | openai_responses | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| AIHubMix | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Ofox | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| OrcaRouter | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| GMI Cloud | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| FreeModel | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M · cache write $5/M | Yes | ||
| Kilo Gateway | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Merge Gateway | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Vercel AI Gateway | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructuredTemperature | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| OpenRouter | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | Moderated, Reasoning levels: xhigh, high, medium, low, none, Default reasoning: medium | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Cloudflare AI Gateway | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Perplexity Agent | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool call | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| OpenAI | gpt-5.5 | openai_responses | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $5/M · output $30/M cache read $0.5/M | Yes | ||
| Xpersona | gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructured | - | input $1.5/M · output $12/M cache read $0.15/M | Yes | ||
| HPC-AI | openai/gpt-5.5 | openai_chat | 1.1M | 128K | AttachmentsReasoningTool callStructuredTemperature | - | input $5/M · output $30/M cache read $0.5/M | Yes |