impulse

FLUX Kontext Dev

Image
API id dev
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve FLUX Kontext Dev. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
dev
-
ReplicateInference
flux-kontext-dev
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Images

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Black Forest Labs models

No similar Black Forest Labs model keeps its key capabilities.

Other frontier labs

Open-weight picks

No similar open-weight match.

Call it

Using fal's API.

Python
from litellm import completion

response = completion(
    model="fal_ai/dev",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer FLUX Kontext Dev?

FLUX Kontext Dev runs on 2 APIs: fal and Replicate.

Is FLUX Kontext Dev being retired?

No retirement date is scheduled for it on any API we track.

What is FLUX Kontext Dev's API model id?

Use dev with fal. Other hosts use their own ids: flux-kontext-dev on Replicate.

Sources

Raw catalog entry for dev on fal
{
  "litellm_provider": "fal_ai",
  "metadata": {
    "notes": "fal bills fal-ai/flux-kontext/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"
  },
  "mode": "image_generation",
  "output_cost_per_image": 0.025,
  "output_cost_per_pixel": 2.384185791015625e-8,
  "source": "https://fal.ai/models/fal-ai/flux-kontext/dev",
  "supported_endpoints": [
    "/v1/images/edits",
    "/v1/images/generations"
  ],
  "supports_vision": true
}