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.
Gemini OpenAI 兼容格式
你可以通过 OpenAI Chat Completions 兼容格式调用 Gemini。
POST /v1/chat/completions
2026-03-22 已在 Crazyrouter 生产环境复核过的兼容层行为。
当前主示例模型：
当前主结论
本轮生产复核确认：
gemini-3-pro 可以通过 /v1/chat/completions 正常对话- 流式返回兼容
chat.completion.chunk SSE 结构
- 如果你需要 Gemini 的结构化输出、Google Search、thinking 等能力，当前仍应优先看 Gemini 原生格式
基本对话
curl https://crazyrouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gemini-3-pro",
"messages": [
{
"role": "system",
"content": "You are a concise assistant."
},
{
"role": "user",
"content": "Explain quantum entanglement in one sentence."
}
],
"max_tokens": 128
}'
{
"object": "chat.completion",
"model": "gemini-3-pro",
"choices": [
{
"message": {
"role": "assistant",
"content": "..."
}
}
]
}
Python 示例
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://crazyrouter.com/v1"
)
response = client.chat.completions.create(
model="gemini-3-pro",
messages=[
{"role": "system", "content": "You are a concise assistant."},
{"role": "user", "content": "Explain quantum entanglement in one sentence."}
],
max_tokens=128
)
print(response.choices[0].message.content)
流式输出
本轮生产也复核了流式兼容返回：
stream = client.chat.completions.create(
model="gemini-3-pro",
messages=[
{"role": "user", "content": "Write one short sentence about AI."}
],
max_tokens=64,
stream=True
)
for chunk in stream:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="")
data: {"object":"chat.completion.chunk","model":"gemini-3-pro",...}
data: {"choices":[{"delta":{"content":"..."}}],...}
data: [DONE]
何时用兼容格式，何时用原生格式
- 已有 OpenAI SDK 代码，且只需要标准对话：优先用兼容格式
- 需要 Gemini 的结构化输出、Google Search、thinking、原生字段：优先用 Gemini 原生格式
