blackforestlabs/flux-3-klein/text-to-imageFLUX 3 Klein Text to Image turns prompts into product shots, scenes and illustrations at 1K, 2K or 4K, with seven presets, exact custom sizes and up to four images per call. It keeps per-image cost low so you can iterate widely before rendering finals.
Get API KeyEstimated cost: 1.8 credits · $0.0090
Credits are reserved when the task is submitted and refunded in full if it fails.
A cinematic wide photograph of a small fishing harbour at dawn, pastel houses along the quay, still water reflections, thin mist, a single rowing boat in the foreground, soft pink and teal light. No brand names, logos, watermark, split screen or comparison panels.
A layered paper-craft illustration of a lighthouse on a cliff under a starry sky, cut-paper waves in five shades of blue, warm beam of light, vertical book-cover composition with empty space at the top. No brand names, logos, watermark, split screen or comparison panels.
REST API
This flow submits one valid FLUX 3 Klein Text to Image request, captures its task_id, and reads result file URLs after the asynchronous task ends.
Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.
https://api.vidgo.ai/api/generate/submitSend the current model ID and an input object to the unified submit endpoint. input may only contain the fields listed for this endpoint; any other field returns 400.
curl --request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "blackforestlabs/flux-3-klein/text-to-image",
"input": {
"prompt": "A top-down product photograph of a folded sage-green linen shirt on a warm oak table, a small ceramic dish with brass buttons, soft window light from the left, natural fabric texture, calm editorial catalogue style. No brand names, logos, watermark, split screen or comparison panels.",
"size": "4:3",
"resolution": "1K",
"n": 1,
"output_format": "png",
"enable_safety_checker": true
}
}'Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.
GET https://api.vidgo.ai/api/generate/status/{task_id}Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.
not_startedrunningfinishedfailed{
"code": 200,
"data": {
"task_id": "task-example",
"status": "not_started",
"created_time": "2026-11-03T08:00:00"
}
}{
"code": 200,
"data": {
"task_id": "task-example",
"status": "finished",
"created_time": "2026-11-03T08:00:00",
"progress": 100,
"files": [
{
"file_url": "https://example.com/result.png",
"file_type": "image"
}
]
}
}Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.
set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"
REQUEST_BODY=$(cat <<'JSON'
{
"model": "blackforestlabs/flux-3-klein/text-to-image",
"input": {
"prompt": "A top-down product photograph of a folded sage-green linen shirt on a warm oak table, a small ceramic dish with brass buttons, soft window light from the left, natural fabric texture, calm editorial catalogue style. No brand names, logos, watermark, split screen or comparison panels.",
"size": "4:3",
"resolution": "1K",
"n": 1,
"output_format": "png",
"enable_safety_checker": true
}
}
JSON
)
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data "$REQUEST_BODY")
TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
exit 1
fi
while true; do
STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
--url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
--header "Authorization: Bearer $VIDGO_API_KEY")
STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
case "$STATUS" in
finished)
printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
break
;;
failed)
printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
exit 1
;;
not_started|running)
sleep 2
;;
*)
printf 'Unexpected task status: %s
' "$STATUS" >&2
exit 1
;;
esac
doneThis table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
| input.prompt | string | Yes | – | Non-blank text describing the image. |
| input.size | string | No | 1:1 | Preset 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 or 2:3 (long edge set by resolution), or WIDTHxHEIGHT with each side 256–4096 in multiples of 16. |
| input.resolution | string | No | 1K | 1K, 2K or 4K; presets use a long edge of 1024, 2048 or 4096. A custom size must send the tier of its longer side: ≤1024 → 1K, ≤2048 → 2K, otherwise 4K. |
| input.n | integer | No | 1 | Number of images, integer 1–4. |
| input.output_format | string | No | png | png, jpeg or webp. |
| input.enable_safety_checker | boolean | No | true | Boolean. Turns the upstream safety checker on or off. |
The submit response identifies the task. The status response supplies result files or failure details at a terminal state.
| Field | Type | Description |
|---|---|---|
| code | integer | Business response code; 0 or 200 indicates success. |
| message | string | Optional human-readable response message. |
| data.task_id | string | Unique task ID used for status queries after submission. |
| data.status | string | not_started, running, finished, or failed. |
| data.created_time | string | Task creation timestamp. |
| data.progress | integer | Progress from 0–100 in status responses. |
| data.files[] | array | Generated files in returned order when finished. |
| data.files[].file_url | string | Direct URL of the generated file (.png). |
| data.files[].file_type | string | Result files are identified as image. |
| data.error_message | string | null | Readable failure reason for failed tasks. |
Only the first two states may be polled again. finished and failed are terminal.
not_startedAccepted and queued; wait before checking again.
runningGeneration is in progress; continue polling.
finishedSuccessful terminal state; validate files and read file URLs.
failedFailure terminal state; read error_message and stop. Reserved credits are refunded in full.
| Specification | Value | Details |
|---|---|---|
| Model | blackforestlabs/flux-3-klein/text-to-image | FLUX 3 Klein Text to Image |
| Input | prompt | Text only |
| Output | PNG / JPEG / WebP × n (1–4) | Image URLs in files[] |
| resolution | 1K / 2K / 4K | 1.8 / 2.8 / 7.2 credits per image |
| size | 7 presets or WIDTHxHEIGHT | 256–4096 px per side, multiples of 16 |
FLUX 3 Klein Text to Image is a Black Forest Labs model for generating images from written prompts. It renders product shots, scenes and illustrations at 1K, 2K or 4K, in seven preset ratios or exact custom sizes, with up to four images per request in PNG, JPEG or WebP. As the compact 5.6B-parameter member of the FLUX 3 family, it keeps per-image cost low while sharing a model with the matching edit endpoint. You can call it programmatically or try it from the playground above.
Per output image: 1K 1.8 credits ($0.009), 2K 2.8 credits ($0.014) and 4K 7.2 credits ($0.036). The total is the rate multiplied by n.
By the longer side: up to 1024 px needs 1K, up to 2048 px needs 2K, and up to 4096 px needs 4K. Send resolution explicitly; for example 1536x1024 requires 2K.
Presets 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 and 2:3, or any WIDTHxHEIGHT with sides from 256 to 4096 px in multiples of 16.
Set n from 1 to 4. Each image is billed at the selected resolution rate.
No. This endpoint accepts a prompt only. To work from existing pictures, use FLUX 3 Klein Edit with 1–10 images in image_urls.
png (default), jpeg or webp, selected with output_format.
The API needs no GPU provisioning, includes 4K output and bills only per image. Self-hosting the open weights is governed by the licence on Black Forest Labs' model card, which you should review for your use.
