Início Rápido

curl https://api.flexinference.com/v1/responses \
  -H "Authorization: Bearer $FLEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-nano",
    "input": "Write a haiku about cheap GPUs.",
    "start_within": "00h-00m-30s"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.flexinference.com/v1",
    api_key="flex_live_...",  # your FlexInference key
)

resp = client.responses.create(
    model="gpt-5-nano",
    input="Write a haiku about cheap GPUs.",
    extra_body={"start_within": "00h-00m-30s"},
)
print(resp.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.flexinference.com/v1",
  apiKey: "flex_live_...", // your FlexInference key
});

const resp = await client.responses.create({
  model: "gpt-5-nano",
  input: "Write a haiku about cheap GPUs.",
  // start_within is a FlexInference extension; cast to pass it through.
  start_within: "00h-00m-30s",
} as any);

console.log(resp.output_text);

curl https://api.flexinference.com/v1/interactions \
  -H "Authorization: Bearer $FLEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "Write a haiku about cheap GPUs.",
    "start_within": "00h-00m-30s"
  }'

curl https://api.flexinference.com/v1/messages \
  -H "Authorization: Bearer $FLEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Write a haiku about cheap GPUs." }],
    "start_within": "default"
  }'