OpenAI

GPT-5.1 Codex Mini

OpenAI 2025 轻量级代码模型，在保持高质量代码能力的同时提供更快的响应速度和更低的成本

类型文本模型 Model ID gpt-5.1-codex-mini

上下文长度256K tokens

模型类型轻量级代码模型

特色能力快速代码生成、代码补全

定价与规格

💰 定价

输入$0.375 / M tokens

输出$3 / M tokens

⚙️ 规格

上下文长度256K tokens

模型类型轻量级代码模型

特色能力快速代码生成、代码补全

缓存支持支持 Prompt Caching 加速

响应速度优化延迟

训练截止日期2025年6月

API 兼容性OpenAI、Codex

API 调用示例

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.xairouter.com/v1"
)

response = client.chat.completions.create(
    model="gpt-5.1-codex-mini",
    messages=[
        {"role": "user", "content": "请帮我写一个 Python 快速排序函数"}
    ]
)

print(response.choices[0].message.content)

cURL (OpenAI API)

curl https://api.xairouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.1-codex-mini",
    "messages": [
      {"role": "user", "content": "请帮我写一个 Python 快速排序函数"}
    ]
  }'

开发者辅助

# 配置 ~/.codex/config.toml
cat > ~/.codex/config.toml << 'EOF'
model_provider = "xai"
model = "gpt-5.1-codex-mini"
model_reasoning_effort = "high"
model_reasoning_summary = "detailed"
approval_policy = "never"
sandbox_mode = "danger-full-access"
network_access = true
preferred_auth_method = "apikey"

[shell_environment_policy]
inherit = "all"
ignore_default_excludes = false

[model_providers.xai]
name = "xai"
base_url = "https://api.xairouter.com"
wire_api = "responses"
requires_openai_auth = true
env_key = "OPENAI_API_KEY"

[tools]
web_search = true
EOF

# 配置 ~/.codex/auth.json
cat > ~/.codex/auth.json << 'EOF'
{
  "OPENAI_API_KEY": "sk-Xvs..."
}
EOF

# 启动 Codex
codex

← 返回模型列表