Black Forest Labs: FLUX.2 Klein 4B

FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality. Pricing is based on the output.…

black-forest-labs/flux.2-klein-4b

FLUX.2 [klein] 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality. Pricing is based on the output...

Specifications & capabilities

Input
text, image
Output
image
Context window · tokens
40960
Published model ID
flux-2-klein-4b
Capabilities
imageOutput, multimodal, visionInput

Published prices

1–3 / 3

flux-2-klein-4b ↗

$0.0010

Inference provider
blackForestLabs
Platform
Black Forest Labs
Unit
input_megapixel
Currency
USD
Billing conditions
kind
add-on
variant
FLUX.2 [klein] 4B
rounding
Ceil input and output separately to whole megapixels
price_type
list
pixels_per_megapixel
1048576
Billing label
Per input megapixel (add-on)

flux-2-klein-4b ↗

$0.0010

Inference provider
blackForestLabs
Platform
Black Forest Labs
Unit
output_additional_megapixel
Currency
USD
Billing conditions
kind
add-on
variant
FLUX.2 [klein] 4B
rounding
Ceil input and output separately to whole megapixels
price_type
list
pixels_per_megapixel
1048576
Billing label
Additional output megapixel (add-on)

flux-2-klein-4b ↗

$0.01

Inference provider
blackForestLabs
Platform
Black Forest Labs
Unit
output_first_megapixel
Currency
USD
Billing conditions
kind
base
variant
FLUX.2 [klein] 4B
rounding
Ceil input and output separately to whole megapixels
price_type
list
pixels_per_megapixel
1048576
Billing label
First output megapixel

Provider specifications & access

1–3 / 3

flux.2-klein-4b ↗

source model id
black-forest-labs/flux_2-klein-4b
hosting
nvidia-catalog
platforms
  • NVIDIA Build / NIM
architecture
input_modalities
    output_modalities
      capabilities
      • imageOutput

      FLUX.2 [klein] 4B ↗

      source model id
      flux-2-klein-4b
      hosting
      bfl-hosted
      platforms
      • Black Forest Labs
      architecture
      input_modalities
      • text
      • image
      output_modalities
      • image
      capabilities

        FLUX.2-klein-4B ↗

        source model id
        publishers/black-forest-labs/models/flux-2-klein-4b@flux.2-klein-4b
        hosting
        vertex-self-deployed
        platforms
        • Google Cloud Vertex AI
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          Source specification observations

          1–2 / 2

          openRouter ↗

          field
          context_length
          value
          40960
          normalized value
          40960
          scope
          source-model
          source id
          openRouter
          confidence
          1

          openRouter ↗

          field
          max_output_tokens
          value
          36864
          normalized value
          36864
          scope
          source-model
          source id
          openRouter
          confidence
          1

          Original sources

          1–14 / 14

          Hugging Face · black-forest-labs/FLUX.2-klein-4B ↗

          Google Cloud · Model page ↗

          NVIDIA · Model page ↗

          OpenRouter · Model page ↗

          NVIDIA · Documentation ↗

          Black Forest Labs · Source snapshot ↗

          Black Forest Labs · Model family ↗

          Black Forest Labs · API documentation ↗

          Black Forest Labs · Pricing ↗

          Black Forest Labs · Catalog ↗

          Google Cloud · Catalog ↗

          Hugging Face · Catalog ↗

          NVIDIA · Catalog ↗

          OpenRouter · Catalog ↗

          Source links

          1–7 / 7

          Explore more models

          Models

          Loading
          EVIDENCE / COMPARISON

          Benchmarks

          Explore every benchmark

          Loading

          These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

          Install TensorTrace