OpenAI

GPT-5.1 Codex Max

OpenAI 2025 旗舰代码专用模型，具备最强代码理解和生成能力，支持超大上下文和复杂代码任务

类型文本模型 Model ID gpt-5.1-codex-max

上下文长度512K tokens

模型类型旗舰代码专用模型

特色能力复杂系统架构、代码审查、深度重构、性能优化

定价与规格

💰 定价

输入$1.25 / M tokens

输出$10 / M tokens

⚙️ 规格

上下文长度512K tokens

模型类型旗舰代码专用模型

特色能力复杂系统架构、代码审查、深度重构、性能优化

缓存支持支持 Prompt Caching 加速

推理能力增强的代码推理和问题解决能力

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-max",
    messages=[
        {"role": "user", "content": "请帮我设计一个高性能的分布式缓存系统架构"}
    ]
)

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-max",
    "messages": [
      {"role": "user", "content": "请帮我设计一个高性能的分布式缓存系统架构"}
    ]
  }'

开发者辅助

# 配置 ~/.codex/config.toml
cat > ~/.codex/config.toml << 'EOF'
model_provider = "xai"
model = "gpt-5.1-codex-max"
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 = false
env_key = "OPENAI_API_KEY"

[features]
web_search_request = true

[notice]
hide_gpt5_1_migration_prompt = true
hide_rate_limit_model_nudge = false
EOF

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

# 启动 Codex
codex -m gpt-5.1-codex-max

← 返回模型列表