FLUX 3 Text to Image Serverless API

Bounding-box layout control, native 4K text-to-image.

PlaygroundAPI
Pricing
~73.34s
POST /v2/flux-3-text-to-image · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "flux-3-text-to-image",
 9    prompt="Top-down flat-lay on a reclaimed-wood workbench, four components arranged in a clean grid with even daylight: a disassembled brass pocket-watch movement <watch>, a tight coil of bright copper wire <wire>, a teal printed circuit board <board>, and a fan of red-handled jeweler's screwdrivers <drivers>, with a small white index card <label> in the centre. [{\"id\": \"watch\", \"bbox\": [60, 60, 470, 470], \"desc\": \"disassembled brass pocket-watch movement with exposed gears\"}, {\"id\": \"wire\", \"bbox\": [60, 530, 470, 940], \"desc\": \"tightly wound coil of bright copper wire\"}, {\"id\": \"board\", \"bbox\": [530, 60, 940, 470], \"desc\": \"teal printed circuit board with silver solder points\"}, {\"id\": \"drivers\", \"bbox\": [530, 530, 940, 940], \"desc\": \"fan of six red-handled jeweler's screwdrivers\"}, {\"id\": \"label\", \"bbox\": [420, 300, 580, 700], \"desc\": \"a small white index card with the handwritten words BENCH KIT No. 3\"}]",
10    resolution="2k",
11    aspect_ratio="1:1",
12    safety_tolerance=2,
13    grounding=False,
14)
15print(result["status"])                      # COMPLETED
16print(result.get("output"))                  # model output (e.g. media URL)
17print(result["metrics"]["inference_time"])   # server compute seconds
18
19# --- Or submit + poll manually (track request_id, control the cadence) ---
20from segmind import SegmindClient, InferenceFailed, InferenceTimeout
21
22client = SegmindClient()                      # reads SEGMIND_API_KEY
23payload = {
24    "prompt": "Top-down flat-lay on a reclaimed-wood workbench, four components arranged in a clean grid with even daylight: a disassembled brass pocket-watch movement <watch>, a tight coil of bright copper wire <wire>, a teal printed circuit board <board>, and a fan of red-handled jeweler's screwdrivers <drivers>, with a small white index card <label> in the centre. [{\"id\": \"watch\", \"bbox\": [60, 60, 470, 470], \"desc\": \"disassembled brass pocket-watch movement with exposed gears\"}, {\"id\": \"wire\", \"bbox\": [60, 530, 470, 940], \"desc\": \"tightly wound coil of bright copper wire\"}, {\"id\": \"board\", \"bbox\": [530, 60, 940, 470], \"desc\": \"teal printed circuit board with silver solder points\"}, {\"id\": \"drivers\", \"bbox\": [530, 530, 940, 940], \"desc\": \"fan of six red-handled jeweler's screwdrivers\"}, {\"id\": \"label\", \"bbox\": [420, 300, 580, 700], \"desc\": \"a small white index card with the handwritten words BENCH KIT No. 3\"}]",
25    "resolution": "2k",
26    "aspect_ratio": "1:1",
27    "safety_tolerance": 2,
28    "grounding": False,
29}
30job = client.submit_async("flux-3-text-to-image", **payload)
31print(job.request_id)                         # available immediately
32try:
33    result = job.wait(timeout=600, interval=1.0)
34except InferenceTimeout as e:
35    print("still running:", e.request_id)
36except InferenceFailed as e:
37    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/flux-3-text-to-image

Parameters

promptrequired
string

Describe subject, composition, lighting and style. Supports bounding-box layouts: tag elements with <id> and append a JSON array of {id, bbox:[y_min,x_min,y_max,x_max] on a 0-1000 grid, desc}.

Default: "Top-down flat-lay on a reclaimed-wood workbench, four components arranged in a clean grid with even daylight: a disassembled brass pocket-watch movement <watch>, a tight coil of bright copper wire <wire>, a teal printed circuit board <board>, and a fan of red-handled jeweler's screwdrivers <drivers>, with a small white index card <label> in the centre. [{\"id\": \"watch\", \"bbox\": [60, 60, 470, 470], \"desc\": \"disassembled brass pocket-watch movement with exposed gears\"}, {\"id\": \"wire\", \"bbox\": [60, 530, 470, 940], \"desc\": \"tightly wound coil of bright copper wire\"}, {\"id\": \"board\", \"bbox\": [530, 60, 940, 470], \"desc\": \"teal printed circuit board with silver solder points\"}, {\"id\": \"drivers\", \"bbox\": [530, 530, 940, 940], \"desc\": \"fan of six red-handled jeweler's screwdrivers\"}, {\"id\": \"label\", \"bbox\": [420, 300, 580, 700], \"desc\": \"a small white index card with the handwritten words BENCH KIT No. 3\"}]"
aspect_ratiooptional
string

auto lets the prompt decide, else 1:1. Pick a fixed ratio for a known canvas.

Default: "auto"
Allowed values (16 total):
"auto""21:9""2:1""16:9""3:2""7:5""4:3""5:4""1:1""4:5"+6 more
groundingoptional
boolean

Let the model ground the prompt in web and image search (real places, products, people in the news). Off for pure imagination.

Default: true
resolutionoptional
string

Output size tier (equal pixel area; exact dimensions follow the aspect ratio). Price scales with the tier.

Default: "1k"
Allowed values :
768sq (768 x 768)→"768sq"
1k (about 1 MP)→"1k"
1.5k (about 2.3 MP)→"1.5k"
2k (about 4 MP)→"2k"
4k (about 16 MP)→"4k"
safety_toleranceoptional
integer

Input and output moderation level: 0 is strictest, 4 most permissive.

Default: 2Range: 0 - 4

Response Type

Returns: Text/JSON

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/flux-3-text-to-image

    Submit — returns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Poll — until COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out