FLUX.1 Kontext [pro]

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

Third-party

FLUX.1 Kontext [pro] creates and edits images from text prompts with strong character and style consistency.

Model Info
Terms and License	link ↗
More information	link ↗
Pricing	Per image$0.04

Usage

const response = await env.AI.run(
  'black-forest-labs/flux-1-kontext-pro',
  { prompt: 'A small furry elephant pet looks out from a cat house' },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "black-forest-labs/flux-1-kontext-pro",
  "input": {
    "prompt": "A small furry elephant pet looks out from a cat house"
  }
}'

{
  "state": "Completed",
  "result": {
    "image": "https://examples.aig.cloudflare.com/black-forest-labs/flux-1-kontext-pro/text-to-image.png"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Examples

Wide Cinematic Image — Generate a cinematic landscape using a wide aspect ratio.

const response = await env.AI.run(
  'black-forest-labs/flux-1-kontext-pro',
  {
    prompt:
      'A remote gas station swallowed by crimson fog, green glow from overhead lights staining the asphalt, cinematic wide shot',
    input_image:
      'https://cdn.sanity.io/images/gsvmb6gz/production/3ae6ee032b85373b84934574f3ac3bb2fb792d64-2048x1365.jpg',
    aspect_ratio: '16:9',
    output_format: 'jpeg',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "black-forest-labs/flux-1-kontext-pro",
  "input": {
    "prompt": "A remote gas station swallowed by crimson fog, green glow from overhead lights staining the asphalt, cinematic wide shot",
    "input_image": "https://cdn.sanity.io/images/gsvmb6gz/production/3ae6ee032b85373b84934574f3ac3bb2fb792d64-2048x1365.jpg",
    "aspect_ratio": "16:9",
    "output_format": "jpeg"
  }
}'

{
  "state": "Completed",
  "result": {
    "image": "https://examples.aig.cloudflare.com/black-forest-labs/flux-1-kontext-pro/wide-cinematic-image.jpeg"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Parameters

prompt

stringrequiredText prompt for image generation or editing.

input_image

stringOptional base64 encoded image or URL to edit.

aspect_ratio

stringOutput aspect ratio, from 3:7 to 7:3. Defaults to 1:1.

seed

integer | nullOptional seed for reproducible generation.

prompt_upsampling

booleanWhether to upsample the prompt. Defaults to false.

safety_tolerance

integerminimum: 0maximum: 6Moderation tolerance. 0 is strictest and 6 is most permissive.

output_format

stringenum: jpeg, pngOutput image format. Defaults to jpeg.

image

stringformat: uriURL to the generated image

API Schemas (Raw)

Input

Output