Model information
Released
2025-12-11
Context window
400K
Max output
128K
Weights
Closed
Modalities
Input
ImageText
Output
Text
Identity
- Version
- gpt-5.2-codex
- Knowledge cutoff
- 2025-08-31
- Aliases
- GPT-5.2 Codex
Capabilities
AttachmentsReasoningStructuredTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Poe | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool call | - | input $1.6/M · output $13/M cache read $0.16/M | Yes | ||
| Vivgrid | gpt-5.2-codex | openai_chat | 400K | 128K | ReasoningTool call | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| NanoGPT | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| LLM Gateway | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| OpenCode Zen | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| GitHub Copilot | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Neon | gpt-5-2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| ZenMux | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool call | - | input $1.75/M · output $14/M cache read $0.17/M | Yes | ||
| Abacus | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Azure Cognitive Services | gpt-5.2-codex | custom | 400K | 128K | ReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Azure | gpt-5.2-codex | openai_responses | 400K | 128K | ReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| QiHang | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $0.14/M · output $1.14/M | Yes | ||
| AIHubMix | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| OrcaRouter | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Requesty | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Kilo Gateway | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Vercel AI Gateway | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| OpenRouter | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | Reasoning levels: xhigh, high, medium, low, Default reasoning: medium, Reasoning required | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Cloudflare AI Gateway | openai/gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructured | - | input $1.75/M · output $14/M cache read $0.175/M | Yes | ||
| Jiekou.AI | gpt-5.2-codex | openai_chat | 400K | 128K | AttachmentsReasoningTool callStructuredTemperature | - | input $1.75/M · output $14/M | Yes | ||
| OpenAI | gpt-5.2-codex | custom | 400K | 128K | - | - | - | Yes |