Create Content

curl --request POST \
  --url https://app.uselamina.ai/v1/content/create \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "brief": "Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography",
  "platform": "instagram",
  "modality": "image",
  "brandProfileId": null,
  "campaignId": null
}
'

import requests

url = "https://app.uselamina.ai/v1/content/create"

payload = {
    "brief": "Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography",
    "platform": "instagram",
    "modality": "image",
    "brandProfileId": None,
    "campaignId": None
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    brief: 'Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography',
    platform: 'instagram',
    modality: 'image',
    brandProfileId: null,
    campaignId: null
  })
};

fetch('https://app.uselamina.ai/v1/content/create', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://app.uselamina.ai/v1/content/create",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'brief' => 'Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography',
    'platform' => 'instagram',
    'modality' => 'image',
    'brandProfileId' => null,
    'campaignId' => null
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://app.uselamina.ai/v1/content/create"

	payload := strings.NewReader("{\n  \"brief\": \"Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography\",\n  \"platform\": \"instagram\",\n  \"modality\": \"image\",\n  \"brandProfileId\": null,\n  \"campaignId\": null\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://app.uselamina.ai/v1/content/create")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"brief\": \"Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography\",\n  \"platform\": \"instagram\",\n  \"modality\": \"image\",\n  \"brandProfileId\": null,\n  \"campaignId\": null\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://app.uselamina.ai/v1/content/create")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"brief\": \"Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography\",\n  \"platform\": \"instagram\",\n  \"modality\": \"image\",\n  \"brandProfileId\": null,\n  \"campaignId\": null\n}"

response = http.request(request)
puts response.read_body

{
  "data": {
    "runId": "fc32ae7d-6840-4be3-8fb1-539a60e33fc3",
    "workflowId": "80d4d454-8844-489f-b903-2ad65a414482",
    "workflowName": "AI Product Photography",
    "status": "queued"
  }
}

{
  "error": "brief is required (string)"
}

{
  "error": "Invalid API key"
}

"Too many requests from this IP, please try again in a minute"

Create

Create Content

One-call creation endpoint. Provide a natural-language brief and Lamina handles everything: resolves brand context, selects the best workflow/app, injects guidance into prompts, and executes.

How it works:

Resolves brand DNA and active guidance for the workspace
If no appId is provided, selects the best-matching app for the brief, platform, and modality
Translates the brief into app-specific inputs using brand context
Starts the execution and returns immediately (async)

After starting: Use GET /v1/runs/{runId} to poll for results, GET /v1/runs/{runId}/stream for SSE streaming, or pass a webhook query parameter on the execution.

Optional overrides:

appId — Force a specific app instead of automatic selection
inputs — Override specific input parameters on the selected app
templateId — Apply a content template for structured guidance (from GET /v1/templates)
brandProfileId / campaignId — Scope brand context to a specific profile or campaign

POST

content

create

Create Content

curl --request POST \
  --url https://app.uselamina.ai/v1/content/create \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "brief": "Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography",
  "platform": "instagram",
  "modality": "image",
  "brandProfileId": null,
  "campaignId": null
}
'

import requests

url = "https://app.uselamina.ai/v1/content/create"

payload = {
    "brief": "Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography",
    "platform": "instagram",
    "modality": "image",
    "brandProfileId": None,
    "campaignId": None
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    brief: 'Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography',
    platform: 'instagram',
    modality: 'image',
    brandProfileId: null,
    campaignId: null
  })
};

fetch('https://app.uselamina.ai/v1/content/create', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://app.uselamina.ai/v1/content/create",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'brief' => 'Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography',
    'platform' => 'instagram',
    'modality' => 'image',
    'brandProfileId' => null,
    'campaignId' => null
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://app.uselamina.ai/v1/content/create"

	payload := strings.NewReader("{\n  \"brief\": \"Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography\",\n  \"platform\": \"instagram\",\n  \"modality\": \"image\",\n  \"brandProfileId\": null,\n  \"campaignId\": null\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://app.uselamina.ai/v1/content/create")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"brief\": \"Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography\",\n  \"platform\": \"instagram\",\n  \"modality\": \"image\",\n  \"brandProfileId\": null,\n  \"campaignId\": null\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://app.uselamina.ai/v1/content/create")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"brief\": \"Create an eye-catching Instagram post showcasing our new summer sneaker collection with lifestyle photography\",\n  \"platform\": \"instagram\",\n  \"modality\": \"image\",\n  \"brandProfileId\": null,\n  \"campaignId\": null\n}"

response = http.request(request)
puts response.read_body

{
  "data": {
    "runId": "fc32ae7d-6840-4be3-8fb1-539a60e33fc3",
    "workflowId": "80d4d454-8844-489f-b903-2ad65a414482",
    "workflowName": "AI Product Photography",
    "status": "queued"
  }
}

{
  "error": "brief is required (string)"
}

{
  "error": "Invalid API key"
}

"Too many requests from this IP, please try again in a minute"

One-call creation. Describe what you want, and the API handles app selection, input mapping, brand context injection, and execution. Instead of manually choosing an app and mapping inputs, pass a brief describing the content you need. The engine resolves brand context, selects the best-fit app, injects creative guidance, and starts the execution. The operation is asynchronous — use the returned run ID with the wait, stream, or get-run endpoints to retrieve results. Best for agent-driven workflows where you want a single call to go from intent to finished asset.

Headless mode (unattended agents)

By default, create may return status: "needs_input" with askUser prompts when the chosen path needs information a human would supply — a dead end for an unattended worker or agent. Pass headless: true (or terminalMode: "auto") to make the call reliable for agentic callers. In headless mode the engine:

forces the self-drafting recipe path and dispatches best-effort — it never returns needs_input;
returns status: "unmatched" (machine-actionable) if a run genuinely can’t be formed, instead of an interactive ask;
surfaces any unmet asks on the ran response as structured unmetAsks[] — each { name, key, question, type, required, autoFillable } — so an agent can satisfy one (e.g. generate an image_url via POST /v1/generate/image) and re-run.

A pinned appId is ignored in headless mode. See the Agent Creation Loop guide for the full create → satisfy → run pattern.

Authorizations

x-api-key

string

header

required

Workspace API key. Prefix: lma_. Example: lma_abc123...

Body

application/json

brief

string

required

Natural-language description of what content to create. This is the primary input.

platform

string | null

Target platform (e.g. instagram, tiktok, facebook). Helps select the right app and optimize guidance.

modality

string | null

Desired content modality (e.g. image, video). Helps select the right app.

brandProfileId

string<uuid> | null

Scope brand context to a specific brand profile.

campaignId

string<uuid> | null

Scope guidance to a specific campaign.

appId

string<uuid> | null

Force a specific app instead of automatic selection. Use GET /v1/apps to find app IDs.

headless

boolean | null

default:false

Headless/agentic mode for unattended callers (workers, autonomous agents). Forces the self-drafting recipe path and dispatches best-effort — it NEVER returns needs_input. If a run genuinely cannot be formed it returns status: "unmatched" (machine-actionable) instead of an interactive ask. Any unmet asks ride along on the ran response as structured unmetAsks[] ({ name, key, question, type, required, autoFillable }), so an agent can satisfy one (e.g. generate an image_url) and re-run. A pinned appId is ignored in this mode.

inputs

object | null

Override specific input parameters on the selected app. Keys are parameter names.

templateId

string | null

Apply a content template for structured guidance. Use GET /v1/templates to find template IDs.

autoQuality

object | null

Auto-quality guarantee. Score output after completion and retry if below threshold.

Show child attributes

aspectRatio

string | null

Output aspect ratio. Auto-mapped to the matching workflow parameter. Common values: 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, auto.

Example:

"9:16"

metadata

object | null

Freeform context about the target placement, injected into prompt engineering as structured document context. Useful for passing context from the calling application without manually writing it into the brief.

Example:

{
  "documentTitle": "Summer Collection 2026",
  "fieldName": "heroImage",
  "fieldPurpose": "Main banner image for collection landing page",
  "dimensions": { "width": 1920, "height": 1080 }
}

webhookUrl

string<uri> | null

HTTPS URL to POST the completion event to when the run finishes — so an unattended caller is notified instead of polling. Also accepted nested as metadata.webhookUrl (the SDK's LaminaCreateParams surfaces both); the top-level field takes precedence when both are present.

Example:

"https://example.com/webhooks/lamina"

Response

Content creation started. Poll the run for results.

data

object

Run details including runId, workflowId, and status.

Overview

Install

Concepts

API Reference

Guides

Create Content

Headless mode (unattended agents)

Authorizations

Body

Response

​Headless mode (unattended agents)

Authorizations

Body

Response

Headless mode (unattended agents)