FLUX Kontext Pro API

FLUX Kontext Pro is the fast, iterative tier of Black Forest Labs' FLUX.1 Kontext family — a flow-matching (rectified-flow transformer) model that unifies text-to-image generation and in-context image editing behind one endpoint. Give it a prompt to generate from scratch, or hand it a reference image plus an instruction to edit locally (a single object), globally (a whole scene), match a style, or correct the text rendered inside an image. Because the model reads your input image as context rather than starting from a blank canvas, it preserves faces, objects, and layout across multi-turn edits — the exact point where most editing models drift. It is not a language model: there is no token context window, no function calling, and no document reasoning. Images and text go in; an image comes out.

On  GPTProto this page runs the image-to-image task — a text prompt in, an image out, at $0.032 per image. Text-to-image is FLUX Kontext Pro's signature; on the platform it runs through the editing task rather than this endpoint.

Which tier: Pro or Max?

FLUX Kontext Pro is the value tier: at $0.032/image it's half the price of Max and the fastest of the family, built for text-to-image and everyday edits. Step up to FLUX Kontext Max ($0.064/image) only when in-image typography or exact prompt adherence is the deciding factor — both share the same editing interface and character consistency. See the full tier-by-tier breakdown (and how Max stacks up against gpt-image-2) on the FLUX Kontext Max page.

Switching from Black Forest Labs (drop-in)

Moving from BFL's direct API to the FLUX Kontext Pro API on GPTProto is a small
diff, not a rewrite:

1. base_url  →  https://gptproto.com/v1/images/generation 

2. auth →  Authorization: Bearer YOUR_GPTPROTO_KEY  (replaces BFL's x-key)

3. model→  keep "flux-kontext-pro" The same GPTProto balance then covers FLUX Kontext Max, Seedream, gpt-image-2 and 200+ other models — one key, one invoice, no separate BFL credit top-ups and no per-provider sign-up. 

Prompt tips for FLUX Kontext Pro

Kontext follows edit instructions literally, so specificity beats length:

  • Name the subject, don't use pronouns: "the woman with short black hair",
    not "her".
  • State what must NOT change: "…while keeping the same face and pose".
  • To reposition without redrawing: "maintain the original composition".
  • For background swaps: "change the background to a beach, keep the person in
    the exact same position".

Keep multi-turn sessions short — BFL notes quality can drift after roughly six consecutive edits, so restart from a clean base image if artifacts appear.