Flux.1 Dev Serverless API

Flux Dev is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions

~20.36s
POST /v2/flux-dev · 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-dev",
 9    prompt="detailed cinematic dof render of an old dusty detailed CRT monitor on a wooden desk in a dim room with items around, messy dirty room. On the screen are the letters “FLUX dev” glowing softly. High detail hard surface render",
10    samples=1,
11    guidance=3.5,
12    steps=25,
13    prompt_strength=0.8,
14    aspect_ratio="1:1",
15    seed=46588,
16    output_format="webp",
17    output_quality=80,
18)
19print(result["status"])                      # COMPLETED
20print(result.get("output"))                  # model output (e.g. media URL)
21print(result["metrics"]["inference_time"])   # server compute seconds
22
23# --- Or submit + poll manually (track request_id, control the cadence) ---
24from segmind import SegmindClient, InferenceFailed, InferenceTimeout
25
26client = SegmindClient()                      # reads SEGMIND_API_KEY
27payload = {
28    "prompt": "detailed cinematic dof render of an old dusty detailed CRT monitor on a wooden desk in a dim room with items around, messy dirty room. On the screen are the letters “FLUX dev” glowing softly. High detail hard surface render",
29    "samples": 1,
30    "guidance": 3.5,
31    "steps": 25,
32    "prompt_strength": 0.8,
33    "aspect_ratio": "1:1",
34    "seed": 46588,
35    "output_format": "webp",
36    "output_quality": 80,
37}
38job = client.submit_async("flux-dev", **payload)
39print(job.request_id)                         # available immediately
40try:
41    result = job.wait(timeout=600, interval=1.0)
42except InferenceTimeout as e:
43    print("still running:", e.request_id)
44except InferenceFailed as e:
45    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/flux-dev

Parameters

promptrequired
string

Text prompt for image generation

Default: "detailed cinematic dof render of an old dusty detailed CRT monitor on a wooden desk in a dim room with items around, messy dirty room. On the screen are the letters “FLUX dev” glowing softly. High detail hard surface render"
aspect_ratiooptional
string

Type of scheduler.

Default: ""
Allowed values :
"1:1""16:9""21:9""2:3""3:2""4:5""5:4""9:16""9:21"
guidanceoptional
integer

guidance

Default: 3Range: 0 - 10
output_formatoptional
string

An enumeration.

Default: "webp"
Allowed values :
"webp""jpg""png"
output_qualityoptional
integer

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80Range: 0 - 100
prompt_strengthoptional
number

Prompt Strength

Default: 0.8Range: 0 - 1
samplesoptional
integer

Number of samples to generate.

Default: 1Range: 1 - 4
seedoptional
integer

Seed for random number generation

Default: 46588
stepsoptional
integer

number of steps

Default: 25Range: 1 - 50

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-dev

    Submitreturns request_id, status_url, response_url

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

    Polluntil COMPLETED or FAILED

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

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (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