Responses API

Use POST /v1/responses for typed input and output items, function-call continuations, and the newest OpenAI-compatible response shape.

On this page 1 of 6

Request#

For a single text turn, input can be a string:

Send a Responses request

from getpass import getpass

from openai import OpenAI

client = OpenAI(
    base_url="https://api.keirolabs.ai/v1",
    api_key=getpass("Keiro API key: "),
)

response = client.responses.create(
    model="eb1-preview",
    input="Give three practical uses for structured outputs.",
)

print(response.output_text)

Send a Responses request

import fs from "node:fs";
import OpenAI from "openai";

const keyPath = process.env.KEIRO_KEY_FILE;
if (!keyPath) {
  throw new Error("KEIRO_KEY_FILE must point to a protected secret file");
}

const client = new OpenAI({
  baseURL: "https://api.keirolabs.ai/v1",
  apiKey: fs.readFileSync(keyPath, "utf8").trim(),
});

const response = await client.responses.create({
  model: "eb1-preview",
  input: "Give three practical uses for structured outputs.",
});

console.log(response.output_text);

Send a Responses request

printf 'Keiro API key: '
IFS= read -rs KEIRO_BEARER
printf '\n'

curl -sS https://api.keirolabs.ai/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eb1-preview",
    "input": "Give three practical uses for structured outputs."
  }' \
  -H @- <<<"Authorization: Bearer $KEIRO_BEARER"

JSON payload JSON

{
  "model": "eb1-preview",
  "input": "Explain token buckets in one sentence."
}

For multimodal or multi-turn work, send an array of typed message, text, image, function-call, and function-output items. Put stable application instructions in instructions.

Response#

OpenAI-compatible SDKs expose response.output_text as a convenience. In raw JSON, inspect output in order and read assistant output_text content parts. The same array can contain function-call and other structured output items.

For tool continuation, resend the complete conversation items, including the model's function_call and your matching function_call_output. Stateful previous_response_id continuation is not a portable public eb1 contract.

Supported controls#

The current Responses surface supports documented input and instructions plus controls including metadata, text response format, function tools and tool choice, parallel tool calls, streaming, maximum output tokens, sampling and stop controls, reasoning, user attribution, include controls, service tier, prompt-cache key, truncation, and idempotency.

Strict validation rejects unknown fields. JSON mode and JSON Schema structured output are not currently supported.

Streaming#

Set stream to true to receive typed server-sent events. Assemble text from response.output_text.delta, process structured items by their output index, and finish only after response.completed or response.incomplete.

Stream a Responses request

from getpass import getpass

from openai import OpenAI

client = OpenAI(
    base_url="https://api.keirolabs.ai/v1",
    api_key=getpass("Keiro API key: "),
)

stream = client.responses.create(
    model="eb1-preview",
    input="Write a short haiku about reliable APIs.",
    stream=True,
)

for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)

Stream a Responses request

import fs from "node:fs";
import OpenAI from "openai";

const keyPath = process.env.KEIRO_KEY_FILE;
if (!keyPath) {
  throw new Error("KEIRO_KEY_FILE must point to a protected secret file");
}

const client = new OpenAI({
  baseURL: "https://api.keirolabs.ai/v1",
  apiKey: fs.readFileSync(keyPath, "utf8").trim(),
});

const stream = await client.responses.create({
  model: "eb1-preview",
  input: "Write a short haiku about reliable APIs.",
  stream: true,
});

for await (const event of stream) {
  if (event.type === "response.output_text.delta") {
    process.stdout.write(event.delta);
  }
}

Stream a Responses request

printf 'Keiro API key: '
IFS= read -rs KEIRO_BEARER
printf '\n'

curl -sS -N https://api.keirolabs.ai/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eb1-preview",
    "input": "Write a short haiku about reliable APIs.",
    "stream": true
  }' \
  -H @- <<<"Authorization: Bearer $KEIRO_BEARER"

The request's reasoning effort also selects the stream's documented time entitlement — how long a run may take before it is stopped with a truthful response.incomplete. See Streaming for the per-effort table, and Streaming for the event taxonomy and in-band errors.

Tools and images#

Responses function tools use flat name and parameters fields and return function_call output items; see Tool calling.
Images use input_image parts; see Images and vision.

Responses API

Request#

Response#

Supported controls#

Streaming#

Tools and images#

Related pages#