安装与配置
流式输出
复用上面配置好且关闭自动重试的client,订阅输出文本增量。流式支持取决于路由能力。
Chat Completions
若模型支持chat-completions,使用 client.chat.completions.create;请求与流式事件格式见 Chat Completions。
供应商 SDK 只是客户端;实际能力与限制由 Codeflare 模型及渠道配置决定。Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
使用官方 OpenAI SDK 接入 Responses 与 Chat Completions。
npm install openai
export CODEFLARE_API_KEY="YOUR_CODEFLARE_KEY"
from openai import OpenAI
import os
client = OpenAI(
api_key=os.environ["CODEFLARE_API_KEY"],
base_url="https://YOUR-REGION.example/v1",
max_retries=0,
)
response = client.responses.create(
model="MODEL_ID", input="Hello",
max_output_tokens=256, store=False,
)
print(response.output_text)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.CODEFLARE_API_KEY,
baseURL: "https://YOUR-REGION.example/v1",
maxRetries: 0,
});
const response = await client.responses.create({
model: "MODEL_ID", input: "Hello",
max_output_tokens: 256, store: false,
});
console.log(response.output_text);
curl "https://YOUR-REGION.example/v1/responses" \
-H "Authorization: Bearer $CODEFLARE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model":"MODEL_ID","input":"Hello","max_output_tokens":256,"store":false}'
client,订阅输出文本增量。流式支持取决于路由能力。
with client.responses.create(
model="MODEL_ID", input="Hello",
max_output_tokens=256, store=False, stream=True,
) as stream:
for event in stream:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
const stream = await client.responses.create({
model: "MODEL_ID", input: "Hello",
max_output_tokens: 256, store: false, stream: true,
});
for await (const event of stream) {
if (event.type === "response.output_text.delta") {
process.stdout.write(event.delta);
}
}
chat-completions,使用 client.chat.completions.create;请求与流式事件格式见 Chat Completions。
max_retries=0(Python)或 maxRetries: 0(JavaScript)。连接中断时先检查请求日志和已保存的响应,不要盲目重发。