GPT-5.5
GPT-5.5（代号 Spud）是 OpenAI 于 2026 年 4 月发布的旗舰推理模型，专为 Agent 编程、计算机操控与知识工作设计，支持 100 万 token 上下文。本页收录完整基准评测、API 定价与模型解读。
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $5.00/ 1M | $30.00/ 1M |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $2.50/ 1M | $15.00/ 1M |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $12.50/ 1M | $75.00/ 1M |
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | - | - | $0.500/ 1M |
| Text | 5m | $6.25/ 1M | $0.500/ 1M |
| Text | 1h | $6.25/ 1M | $0.500/ 1M |
GPT-5.5 currently shows benchmark results led by ARC-AGI-2 (1 / 59, score 85), Terminal Bench 2.0 (1 / 46, score 82.70), FrontierMath (2 / 60, score 51.70). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
GPT-5.5（代号 Spud）是 OpenAI 于 2026 年 4 月发布的旗舰推理模型，专为 Agent 编程、计算机操控与知识工作设计，支持 100 万 token 上下文。本页收录完整基准评测、API 定价与模型解读。
Follow DataLearner on WeChat for AI model updates and research notes.
Want a custom combination? Open the compare tool
