Black Forest Labs

FLUX.2 DevTerbuka

Open-weight FLUX.2 tier for self-hosting, fine-tuning and LoRA workflows.

#15dirilis 14 Okt 2026·Open Weights·32B
textimage128K ctx
Penyedia APIJalankan Model →vs FLUX.2 ProPeringkat
Inteligensi
90.4 #15
AAQI 90.0
Kecepatan output
28 t/s
ITL 35.7 ms/tok
Harga gabungan (3:1)
$0.03 /1M
Input $0.03/M · Output $0.03/M
Konteks
128K
≈ 320 halaman A4 · output maks 4,096

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

FLUX.2 Dev
Claude Mythos Preview (#1)
Average (68)
Coding (15)Mathematics (15)Hard Science (GPQA) (42)Agentic & Tool Use (28)Knowledge (MMLU) (60)Vision / Multimodal (98.5)

Sumbu radar diaproksimasi dari skor kategori jika pengukuran benchmark langsung tidak tersedia — lihat Metodologi.

Kelebihan & Trade-off

Di mana ia menang

  • Near-Pro image quality you can self-host
  • Fits an RTX 4090 at Q4 — no datacenter needed
  • Thriving LoRA/fine-tune ecosystem
  • ~3× cheaper than Pro on hosted APIs

Hal yang perlu diperhatikan

  • Slightly below Pro on hard prompts
  • Non-commercial terms on some deployments
  • No 4K output in the open checkpoint

Kasus Penggunaan Killer

Self-hosted generation
Own the image stack — no per-image API fees.
Fine-tuned brand styles
LoRA adapters for house styles and characters.
Offline pipelines
Air-gapped rendering for sensitive assets.

Quickstart Developer & API

Atur BFL_API_KEY dulu — dapatkan kunci API
curl -X POST "https://api.bfl.ml/v1/flux-2-dev" \
  -H "x-key: $BFL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Isometric render of a neon data center, sharp typography",
    "width": 1024,
    "height": 1024
  }'

Async image API — the response returns a polling_url; poll it until status is Ready.

Sumber Daya & Tautan Resmi

Deployment API

Bandingkan host & latensi

Throughput, TTFT, dan harga cache di Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock, dan Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Lihat matriks penyedia →

Skor per sumber

Duel Head-to-head Live

Spesifikasi Live & Arsitektur

Di balik kap
FLUX.2 Dev — 32B open rectified-flow transformer
  • Same architecture as Pro, released under open weights
  • Runs on a single 24GB GPU at Q4
  • LoRA / DreamBooth fine-tuning supported
  • Non-commercial-friendly open license
Tanggal rilis
14 Okt 2026
Arsitektur
FLUX.2 Dev — 32B open rectified-flow transformer
Parameter
32B
Lisensi
Open Weights
Jendela konteks
128,000 tokens
Output maks
4,096 tokens
Modalitas
text + image
Harga cache
baca $0.01 · tulis $0.03 /1M
Penalaran
—
Harga input
$0.03/M
Harga output
$0.03/M
Kecepatan output
28 t/s
Waktu ke token pertama
—
Data diperbarui
22 Okt 2026
Perangkat Keras & Inferensi Lokal
Data: Convly AI (CC BY 4.0) ↗
VRAM (4-bit Q4)
20 GB
GPU Min.
RTX 4090 24GB / RTX 5090 32GB

Estimasi tagihan bulanan

Estimasi pengeluaran bulanan
$0.00
Menghitung penghematan vs GPT-4o…

Kutip & sematkan

Badge Markdown GitHub
Loading badge markdown...
BibTeX
@misc{llmpodium2026flux2dev,
  title = {Benchmark Analysis and Intelligence Evaluation of FLUX.2 Dev},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/flux-2-dev}
}

Sematkan Lencana Skor

Tambahkan lencana Podium Score langsung ke README GitHub atau Hugging Face Anda — menautkan ke peringkat langsung.

Pratinjau
FLUX.2 Dev LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

Lainnya dari Black Forest Labs

Model Alternatif

Alternatif terdekat untuk FLUX.2 Dev berdasarkan kemampuan, harga, dan skor benchmark.

0 / 4