Responses.

Endpoint

POST /v1/responses

Authenticate with Authorization: Bearer lx1_.... This is the surface a Codex provider block with wire_api = "responses" talks to — see the Codex CLI guide.

Request parameters

Parameter	Type	Notes
`model`	string · required	Any catalog id.
`input`	string \| array · required	A plain string, or a list of input items (messages, tool results).
`instructions`	string	System-level guidance for the run.
`max_output_tokens`	integer	Output ceiling. On reasoning models, hidden reasoning counts against it.
`temperature`	number	Sampling temperature.
`tools`	array	Function tools. See Tool calling.
`stream`	boolean	SSE event stream when true.
`reasoning`	object	Opt into visible reasoning; `reasoning.effort` sets the level. See Reasoning.
`store`	boolean	Persist this response so it can be chained on or re-read. See Stateful conversations.
`previous_response_id`	string	Continue from a stored response, sending only the new input items.
`prompt_cache_key`	string	A conversation-stable identity hint that keeps a session on a warm cache. `safety_identifier` and legacy `user` are accepted as fallbacks. See Prompt caching.

On reasoning models a very small max_output_tokens can be consumed entirely by hidden reasoning, leaving an empty output_text. If you see empty outputs, raise the budget — 4,000+ is a safe floor for reasoning models.

Example

curl https://api.layerx1.com/v1/responses \
  -H "authorization: Bearer $LAYERX1_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "lx1-gpt-oss-120b",
    "input": "Say hi."
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.layerx1.com/v1",
    api_key="lx1_your_key",
)

r = client.responses.create(
    model="lx1-gpt-oss-120b",
    input="Say hi.",
)
print(r.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.layerx1.com/v1",
  apiKey: process.env.LAYERX1_API_KEY,
});

const r = await client.responses.create({
  model: "lx1-gpt-oss-120b",
  input: "Say hi.",
});
console.log(r.output_text);

Response (shape)

{
  "id": "resp_...",
  "object": "response",
  "model": "lx1-gpt-oss-120b",
  "output": [{
    "type": "message",
    "role": "assistant",
    "content": [{ "type": "output_text", "text": "Hi." }]
  }],
  "usage": { "input_tokens": 14, "output_tokens": 3 }
}

Streaming

With stream: true the response is an SSE event stream — typed events such as response.output_text.delta as text generates, closed by response.completed. The OpenAI SDKs’ responses.stream(...) helpers consume it unchanged. See Streaming.

Stateful conversations

Responses is the one chat dialect that can hold the conversation for you. Set store: true and the response is persisted under your key; a later turn then chains on it by id and sends only the new input, instead of re-uploading the whole transcript. This is the OpenAI SDK’s default conversation pattern, and it works here unchanged.

Turn 1 — store it

curl https://api.layerx1.com/v1/responses \
  -H "authorization: Bearer $LAYERX1_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"lx1-gpt-oss-120b","input":"Remember the number 42.","store":true}'

Turn 2 — chain on it

curl https://api.layerx1.com/v1/responses \
  -H "authorization: Bearer $LAYERX1_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "lx1-gpt-oss-120b",
    "previous_response_id": "resp_...",
    "input": "What number did I ask you to remember?"
  }'

Both fields are echoed back on every envelope, so a client can always see what it is chained to.

Reading a stored response back

GET /v1/responses/{id}

Returns the exact envelope you already received — the same bytes, replayed. Authenticated like every other data route, and scoped to your key: an id belonging to someone else is a 404, never their response.

curl https://api.layerx1.com/v1/responses/resp_123 \
  -H "authorization: Bearer $LAYERX1_API_KEY"

Chaining on an unknown or expired id is a 404 with an invalid_request_error body, naming only the id you sent. That is deliberate: a loud failure beats a conversation that silently lost its history and answers as if the earlier turns never happened.

Only responses you asked to store are stored. Without store: true nothing is persisted for chaining and GET /v1/responses/{id} has nothing to return — send the full transcript each turn instead, exactly like Chat Completions.

Errors

Standard status codes, OpenAI-shaped bodies. Retry on 429/5xx with backoff and honor retry-after. Full reference: Errors.

Get started

API reference

Agent-native API

Guides

Reference

Endpoint

Request parameters

Example

Streaming

Stateful conversations

Reading a stored response back

Errors

​Endpoint

​Request parameters

​Example

​Streaming

​Stateful conversations

​Reading a stored response back

​Errors

Endpoint

Request parameters

Example

Streaming

Stateful conversations

Reading a stored response back

Errors