Back to Models

FLUX.1 Kontext Pro

black-forest-labsblack-forest-labs/flux-kontext-pro

Black Forest Labs' image-edit model. 12B parameters, flow-matching diffusion transformer. Edits an input image based on a text instruction while preserving composition.

FLUX.1 Kontext [pro] is Black Forest Labs' production-grade in-context image editing model released May 29, 2025 as the flagship of the Kontext suite. It unifies high-quality text-to-image generation, local editing, character-consistent multi-turn editing, and style reference in a single hosted flow-matching model. The model is closed-source and served exclusively via BFL's hosted API (and partners including SiliconFlow).

For TheRouter operators, [pro] is the recommended default for iterative editing workloads: brand asset iteration, product visualization, narrative illustration, and any scenario where speed + character consistency matter more than absolute typography perfection. It is priced at $0.04 per image (half the [max] tier) and shares the same async API contract and regional endpoints.

Best for
  • β€’ Iterative multi-turn editing sessions where character/identity consistency across scenes is critical.
  • β€’ Brand asset pipelines, product visualization, and narrative illustration requiring fast turnaround.
  • β€’ Local editing and targeted modifications without affecting the rest of the image.
Reach for something else if
  • β€’ Highest-fidelity typography or maximum prompt adherence β€” use [max] instead.
  • β€’ Cost-sensitive high-volume generation β€” use [dev] when open weights are acceptable.
Context Length
--
Max Output
--
Image Priceper request
$0.0432/ image
Input Priceper request
$0.0432/ 1M tokens

Modalities

textimage→image

Capabilities

VisionImage GenerationImage Edit

Media Generation Capabilities

image_edit
sizes
  • 1024x1024
  • 1024x1536
  • 1536x1024
  • 1280x720
  • 720x1280
aspect_ratios
  • 1:1
  • 16:9
  • 9:16
  • 4:3
  • 3:4
max_reference_images
1
defaults
size
1024x1024

Pricing Breakdown

TypeRate
Image$0.0432 / image
Input$0.0432 / 1M tokens
Per image$0.0432 / image

Per-image flat fee. Black Forest Labs' published price: FLUX.1 Kontext [pro] $0.04/image (bfl.ai/pricing, FLUX.1 tab, read 2026-07-29).

Supported Parameters

promptsizeimageseedaspect_ratioprompt_upsamplingsafety_tolerance

Specifications

Release date2025-05-29bfl.ai β†—verified
AvailabilityHosted API only (BFL global + regional endpoints; SiliconFlow via TheRouter)docs.bfl.ai β†—verified
Inference speedUp to 8Γ— faster than leading models (GPT-Image class); 3–5 s at 1 MP reported for Kontext familybfl.ai β†—verified
License / accessCommercial via BFL API and authorized partners only; no open weightsbfl.ai β†—verified
Training cutoff / dataNot publicly disclosedunknown

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

Recommended: use the async API

Image generation typically takes 30–180s, beyond the edge sync timeout. The examples below use the ?async=true submit + poll pattern. Read the full async image generation & edit guide β†’

cURL
# 1) Submit job (returns 202 immediately with a polling URL).
# Image generation takes 30-180s β€” always use the async path in production.
JOB=$(curl -s -X POST "https://api.therouter.ai/v1/images/generations?async=true"   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "black-forest-labs/flux-kontext-pro",
    "prompt": "A cinematic product render with soft studio lighting"
  }' | python3 -c "import sys,json;print(json.load(sys.stdin)['id'])")
echo "submitted: $JOB"

# 2) Poll until terminal (succeeded / failed / cancelled / expired).
while :; do
  R=$(curl -s "https://api.therouter.ai/v1/jobs/$JOB"     -H "Authorization: Bearer $THE_ROUTER_API_KEY")
  S=$(echo "$R" | python3 -c "import sys,json;print(json.load(sys.stdin)['status'])")
  echo "status: $S"
  case "$S" in
    succeeded) echo "$R" | python3 -c "import sys,json;print(json.load(sys.stdin)['unsigned_urls'][0])"; break ;;
    failed|cancelled|expired) echo "$R"; exit 1 ;;
  esac
  sleep 5
done

Image Editing Examples

Upload an image and describe the edit you want with a text prompt; the model returns the edited image as base64.

cURL
# Same async submit + poll pattern as /v1/images/generations.
JOB=$(curl -s -X POST "https://api.therouter.ai/v1/images/edits?async=true"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -F "model=black-forest-labs/flux-kontext-pro"   -F "prompt=Turn this scene into a watercolor painting"   -F "size=1024x1024"   -F "image=@input.png" | python3 -c "import sys,json;print(json.load(sys.stdin)['id'])")
echo "submitted: $JOB"

while :; do
  R=$(curl -s "https://api.therouter.ai/v1/jobs/$JOB"     -H "Authorization: Bearer $THE_ROUTER_API_KEY")
  S=$(echo "$R" | python3 -c "import sys,json;print(json.load(sys.stdin)['status'])")
  echo "status: $S"
  case "$S" in
    succeeded) echo "$R" | python3 -c "import sys,json;print(json.load(sys.stdin)['unsigned_urls'][0])"; break ;;
    failed|cancelled|expired) echo "$R"; exit 1 ;;
  esac
  sleep 5
done

More from black-forest-labs

Similar models

Cross-provider sibling models

News & changes

2025-05-29

Black Forest Labs launches FLUX.1 Kontext [pro] and [max]

BFL announced the Kontext suite at the end of May 2025, introducing two closed hosted models ([pro] as the production workhorse and the premium [max]) alongside a private beta of the open-weight [dev] variant. [pro] ranked highest in text editing and character preservation on KontextBench and was positioned as the fast iterative editing pioneer.

re-authored by TheRouterbfl.ai β†—

Frequently asked

When should I choose [pro] vs [max]?

[pro] is the recommended default for most production editing workloads: it offers the best balance of speed, character consistency, and cost ($0.04/image). Choose [max] only when typography quality or absolute prompt adherence is the top priority and budget allows the higher per-image price ($0.08).

re-authored by TheRouterbfl.ai β†—
Can I self-host FLUX.1 Kontext [pro]?

No. [pro] is a closed, hosted-only model. The only open-weight Kontext variant is [dev] (12B), which is available on Hugging Face and compatible with existing FLUX.1 [dev] inference stacks.

re-authored by TheRouterbfl.ai β†—
Fact ledger β€” every claim on this page traces here
sourceURLretrieved
Release datebfl.ai β†—2026-05-25verified
Availabilitydocs.bfl.ai β†—2026-05-25verified
Inference speedbfl.ai β†—2026-05-25verified
License / accessbfl.ai β†—2026-05-25verified
Training cutoff / dataβ€”β€”unknown
Black Forest Labs launches FLUX.1 Kontext [pro] and [max]bfl.ai β†—2026-05-25verified
When should I choose [pro] vs [max]?bfl.ai β†—2026-05-25to verify
Can I self-host FLUX.1 Kontext [pro]?bfl.ai β†—2026-05-25to verify
Help & contact