FLUX.1 Kontext Max API

Run black-forest-labs/FLUX.1-kontext-max through FastInfra's OpenAI-compatible API. Pay per token, no subscription, routed to the cheapest available provider.

Read the docs
Pricing

FLUX.1 Kontext Max pricing

Billed per token used. Prices sync automatically from wholesale providers.

Direction Price per 1M tokens
Input
Output
Availability

Served by 2 providers

Requests route to SiliconFlow by default (cheapest). Pin a specific provider with the :provider suffix.

Provider Upstream model ID
together black-forest-labs/FLUX.1-kontext-max
siliconflow black-forest-labs/FLUX.1-Kontext-max
Quickstart

Call FLUX.1 Kontext Max in 30 seconds

Works with any OpenAI SDK — change the base URL and API key only.

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")

response = client.chat.completions.create(
    model="black-forest-labs/FLUX.1-kontext-max",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl

curl https://api.fastinfra.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "black-forest-labs/FLUX.1-kontext-max",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
FAQ

FLUX.1 Kontext Max — common questions

How much does the black-forest-labs/FLUX.1-kontext-max API cost?

On FastInfra, black-forest-labs/FLUX.1-kontext-max costs Pay-per-token pricing via provider routing. Billing is per token used, with no subscription.

Is black-forest-labs/FLUX.1-kontext-max compatible with the OpenAI SDK?

Yes. FastInfra exposes black-forest-labs/FLUX.1-kontext-max through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.

Which providers serve black-forest-labs/FLUX.1-kontext-max?

black-forest-labs/FLUX.1-kontext-max is available from 2 provider(s): together, siliconflow. Requests route to SiliconFlow by default (cheapest); append ":provider" to the model ID to pin one.