推理模式
GetVibe API 的推理级别:Chat Completions 中使用 reasoning_effort,Responses API 中使用 reasoning.effort,Claude 在 /v1/messages 中使用原生 thinking。值 none、minimal、low、medium、high、xhigh 和 max 取决于模型,必须根据其模型卡进行检查;GPT-5.6 Luna、Terra 和 Sol 发布了从 minimal 到 max 的全部六个级别。
推理可以提升困难任务的质量,但通常会增加延迟和输出令牌消耗。参数格式取决于端点,可用级别取决于具体模型。
参数格式
| 参数 | 类型 | 描述 |
|---|---|---|
reasoning_effort | string | /v1/chat/completions 的顶层字段。 |
reasoning.effort | string | 用于 /v1/responses 的嵌套字段,即标准的 Responses API 格式。 |
GetVibe 支持
none、minimal、low、medium、high、xhigh 和 max。GPT-5.6 Luna、Terra 和 Sol 发布了从 minimal 到 max 的全部六个级别;其他模型可能只发布其中较小的子集。正确的拼写是 medium,而不是 middle。等级如何应用
| 参数 | 类型 | 描述 |
|---|---|---|
GPT-5 / o3 / o4 | native | 该级别会以所选端点格式传递给模型。 |
GLM / Qwen | binary | none、minimal、low 禁用思考;medium 及以上启用思考。 |
Gemini | binary | 较低级别会将 thinkingBudget=0,中等及以上级别使用自动预算。 |
DeepSeek / Kimi | native | 推理已内置于模型中,不受此参数切换。 |
Claude | /v1/messages | Updated reasoning parameters: adaptive thinking and output_config.effort; legacy models support budget_tokens (zh). |
聊天补全(curl)
curl https://getvibeapi.com/v1/chat/completions \
-H "Authorization: Bearer $GETVIBE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"reasoning_effort": "high",
"messages": [{"role": "user", "content": "Solve step by step: 17 * 23"}]
}'聊天补全(OpenAI SDK)
from openai import OpenAI
client = OpenAI(base_url="https://getvibeapi.com/v1", api_key=os.environ["GETVIBE_API_KEY"])
r = client.chat.completions.create(model="gpt-6.1-sol", reasoning_effort="high",
messages=[{"role":"user","content":"Hello!"}])
print(r.choices[0].message.content)Responses API(curl)
curl https://getvibeapi.com/v1/responses \
-H "Authorization: Bearer $GETVIBE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"reasoning": {"effort": "high"},
"input": "Solve step by step: 17 * 23"
}'Claude:原生思考
New Claude models use thinking.type=adaptive and thinking.display=summarized for readable reasoning, with output_config.effort for its level. Older models use thinking.type=enabled with budget_tokens. Example (zh):
from anthropic import Anthropic
client = Anthropic(base_url="https://getvibeapi.com", api_key=os.environ["GETVIBE_API_KEY"])
r = client.messages.create(model="claude-sonnet-5.5", max_tokens=2048,
thinking={"type":"adaptive","display":"summarized"},
output_config={"effort":"medium"},
messages=[{"role":"user","content":"Hello!"}])
print(r.content)For Claude use
thinking with /v1/messages or Chat Completions with reasoning_effort; the gateway requests a visible reasoning summary. Tools: Tool connections. (zh)