impulse

FLUX Kontext Max

Image
API id flux-kontext-max
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
4K
tokens
Max output
4K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Where to run it

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

HostIn / out per 1M
flux-kontext-max
-
Fireworks AIInference
flux-kontext-max
$0.08 / $0.08
ReplicateInference
flux-kontext-max
-

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
Text
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 Black Forest Labs's API.

Python
from litellm import completion

response = completion(
    model="black_forest_labs/flux-kontext-max",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does FLUX Kontext Max cost?

Its lowest listed price is at Fireworks AI: $0.08 per million input tokens and $0.08 per million output tokens.

Which APIs offer FLUX Kontext Max?

FLUX Kontext Max runs on 3 APIs: Black Forest Labs, Fireworks AI and Replicate.

What is FLUX Kontext Max's context window?

4K tokens, with up to 4K tokens in one reply.

Is FLUX Kontext Max being retired?

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

What is FLUX Kontext Max's API model id?

Use flux-kontext-max with Black Forest Labs.

Sources

Raw catalog entry for flux-kontext-max on Black Forest Labs
{
  "litellm_provider": "black_forest_labs",
  "mode": "image_edit",
  "output_cost_per_image": 0.08,
  "source": "https://bfl.ai/pricing",
  "supported_endpoints": [
    "/v1/images/edits",
    "/v1/images/generations"
  ]
}