Documentation Index
Fetch the complete documentation index at: https://docs.crazyrouter.com/llms.txt
Use this file to discover all available pages before exploring further.
Reasoning
本文档只收录 已在 Crazyrouter 生产环境实际请求验证成功 的 Reasoning / Thinking 用法。
验证时间:
已验证模型:
gpt-5.4
claude-opus-4-7
gemini-3-pro
已验证能力矩阵
| 模型 | 协议 | 端点 | 成功标志 |
|---|
gpt-5.4 | OpenAI Responses | POST /v1/responses | output 中出现 reasoning item |
claude-opus-4-7 | Anthropic Messages | POST /v1/messages | 返回 thinking block |
gemini-3-pro | Gemini Native | POST /v1beta/models/{model}:generateContent | usageMetadata 中出现 thoughtsTokenCount |
GPT-5.4
curl https://crazyrouter.com/v1/responses \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-5.4",
"input": "Which is larger, 9.11 or 9.9? Explain briefly.",
"reasoning": {
"effort": "high",
"summary": "detailed"
}
}'
生产验证返回的关键 output.type:
其中 reasoning item 的关键字段包括:
{
"type": "reasoning",
"summary": [
{
"type": "summary_text",
"text": "..."
}
]
}
说明在 Crazyrouter 当前生产环境里,gpt-5.4 的推理能力应以 Responses API 的 reasoning item 为准,而不是依赖 Chat Completions 的 reasoning_content。
Claude Opus 4.7 Thinking
curl https://crazyrouter.com/v1/messages \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-d '{
"model": "claude-opus-4-7",
"max_tokens": 320,
"thinking": {
"type": "enabled",
"budget_tokens": 128
},
"messages": [
{
"role": "user",
"content": "Which is larger, 9.11 or 9.9? Explain briefly."
}
]
}'
生产验证返回的关键字段:
{
"content": [
{
"type": "thinking",
"thinking": "..."
},
{
"type": "text",
"text": "..."
}
]
}
注意:
claude-opus-4-6 基础模型在同日测试中只返回普通 text
claude-opus-4-7 才验证到明确的 thinking block
因此文档应优先使用 claude-opus-4-7 作为 Claude 4.7 推理示例。
Gemini 3 Pro
curl "https://crazyrouter.com/v1beta/models/gemini-3-pro:generateContent?key=YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Which is larger, 9.11 or 9.9? Explain briefly."
}
]
}
],
"generationConfig": {
"thinkingConfig": {
"thinkingBudget": 256
},
"maxOutputTokens": 512
}
}'
生产验证返回的关键字段:
usageMetadata.thoughtsTokenCount
这说明在当前生产环境中,gemini-3-pro 的 thinking 模式已实际生效。
当前不写入主结论的组合
gpt-5.4 的 Chat Completions 路由在本轮复核中未稳定返回 reasoning_content,因此本页不再把它作为 GPT 主示例
claude-opus-4-6 基础模型未在本轮验证中返回 thinking block
claude-sonnet-4-6 未发现同等明确的 thinking 能力模型
相关文档