Hayz Labs

FLUX 3 Image

Black Forest LabsAI modelReleased 1 OctOfficial site for FLUX 3 Image no referral link

Top 10 image model that takes up to ten reference images, about 5 cents each. Plain prompts: Nano Banana 2.1 is cheaper.

Our callWorth tryingChecked 11 Oct
ScoreNo score yetImages: why there is no number
CostPay as you goPriced per use
Cheaper optionNano Banana 2.1Scores 73 for images, free

Should you use it?

Pick it if

Designers who combine many reference images or need placement control with boxes.

Best for: Designers who combine up to ten reference images or place items with boxes (Image models Top 20)

Skip it if

You just want good images from a text prompt at the lowest price; Nano Banana 2.1 ranks higher and costs less per image.

You give up: Trains on your prompts and outputs unless you email to opt out; no arena rank yet

The short version

What this is
Black Forest Labs' newest image model for making and editing pictures from text and up to ten reference images, sold through its API.
Why it matters
FLUX is a big name in image models; this tells you whether the new version is worth switching to.
  • Top 10 on Artificial Analysis, not yet on arena.ai.
  • About $0.048 per 1K image; Nano Banana 2.1 scores higher for less.
  • Its strength is multi-reference editing and layout control, by BFL's account.

Good at

  • Eighth of 168 on Artificial Analysis's blind text-to-image votes s1.
  • BFL says one endpoint handles generation, editing and up to ten reference images, with bounding-box prompts and output up to 4K s5.

Weak at

  • Nano Banana 2.1 ranks higher on Artificial Analysis and costs less per 1K image s1.
  • No arena.ai rank yet, and no independent editing score s2 s3.
  • Trains on your prompts and outputs unless you email to opt out s6.

Our take

FLUX 3 Image launched on 1 October and already sits eighth of 168 on Artificial Analysis's blind votes s1 s5. That's well above BFL's FLUX.2 models, which sit 24th and lower there s1. It isn't on arena.ai yet, and Artificial Analysis's terms stop us publishing a score from its data, so it has no score yet.

For plain text-to-image work it is hard to recommend over Nano Banana 2.1, which ranks higher and costs less per 1K image s1. Its case is the feature set BFL describes: up to ten references, bounding boxes and pixel-level edits in one endpoint s5. We have no independent editing score for those yet. Note that BFL trains on API prompts and outputs unless you email to opt out s6.

Score

A score from 0 to 100 per job, against everything available today.

New to this? What the scores and labels mean
0 to 100
Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
Our verdict
Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
First look
Just released. We say what it is and whether to bother, and give it a score once public results exist.
No score yet
None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
Best buy
Nothing cheaper scores as well for that job.
Best free
The best score for that job that costs nothing, through a free plan or by running on your own computer.
Pay as you go
No monthly plan: you pay for each use, usually through a developer account.
Checked
The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
AI model
The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
Open source
Free to download and run on your own computer, so nothing leaves your machine.
How we score, in full
–No score yet

Images

No score yet. The leaderboard this rests on does not let us publish numbers from it, so we describe the evidence instead.

1 source so far

Public leaderboardArtificial Analysis text-to-image rank 8 of 168, Elo 1116, rank range 7 to 11 (s1, checked 2026-10-11). Not yet listed on arena.ai Text to Image (82 models) or on Artificial Analysis image editing s2 s3.

Alternatives

Better or cheaper for images, from our scores, then the ones we'd also look at. The same kind of product comes first.

Compare side by side →

Value for money

Where it sits in images: higher is a better score, further left is cheaper to run. Green dots are the best value.

Images: score from 0 to 100 against cost to make 1,000 images (artificial analysis), for 2 scored items, with each Arena score's likely range. The ranking table holds the same data.
100
90
80
70
60
50
40
$0$5$10$20$50
ScoredBest value: nothing cheaper scores as wellLikely range of an Arena scoreThis reviewNothing else is both cheaper and better than these
Up: score, 0 to 100. Across: Cost to make 1,000 images (Artificial Analysis) (spaced to spread out the cheaper end)

Evidence

Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.

How we scored this

Images has no score yet, because none of the public sources we use covers it.

Public leaderboard

Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.

No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score

Sources 6
  1. s1Artificial Analysis text-to-image leaderboard
  2. s2arena.ai Text to Image leaderboard
  3. s3Artificial Analysis image editing leaderboard
  4. s4BFL API pricing
  5. s5BFL release notes
  6. s6Black Forest Labs privacy policy

Something here out of date or wrong? Report a mistake and we will check it against the source.

History 2 changes

Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.

  1. New: Images ratedReviewed: images (Artificial Analysis rank 8; not yet on arena.ai).
  2. Audit: sourced the comparison with FLUX.2. Rating unchanged.
Use it well 4 guides on this site
esc
↑↓ move↵ openesc closeType a product, a job or a question

Keyboard shortcuts

CtrlK
search everything
/
search everything
gr
reviews: all AI, scored
gg
start here
gu
guides
gw
step-by-step workflows
gt
try-it tools
gs
setup
ga
about
[ ]
previous and next entry, or collection
t
theme: auto, light, dark
?
this sheet