openai/gpt-5.6-sol
GPT-5.6 旗舰模型,面向高难推理、编码与长链路 Agent 工作流。支持文本与图片输入、105 万 token 上下文、最高 max 推理强度、Pro 模式、跨轮持久推理与显式 prompt cache。
来源: openai_x0.05 · 核验于 2026-07-10
缓存读 $0.025/M · 缓存写 $0.3125/M
| 档位 | 输入 | 缓存读 | 缓存写 | 输出 |
|---|---|---|---|---|
| Standard ≤272K | $0.25 | $0.025 | $0.3125 | $1.5 |
| Standard >272K | $0.5 | $0.05 | $0.625 | $2.25 |
API 调用时用任一 ID 都可以。
openai/gpt-5.6-sol请求里的 model 可以直接使用这些名字。
把 ONEHOP_KEY 占位符替换为你的 API Key。 创建 →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="openai/gpt-5.6-sol",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)GPT-5.6 均衡款,兼顾生产级能力与成本。
$0.125/M↓ · $0.75/M↑
GPT-5.6 高效款,适合高并发与延迟敏感任务。
$0.05/M↓ · $0.3/M↑
OpenAI GPT-5.5 — 旗舰,100 万上下文,推理与 Agent 编码顶级。
$0.5/M↓ · $3/M↑
OpenAI GPT-5.4 — 通用强,100 万上下文,比 5.5 便宜。
$0.25/M↓ · $1.5/M↑
GPT-5.4 mini — 快,GPT-5 文本最便宜款。
$0.075/M↓ · $0.45/M↑