MODEL Academic / Independent Last updated:

RFdiffusion

Generative Protein Design

The Baker Lab's diffusion-based protein design model — released July 2023, the first model that could generate novel proteins that actually fold and bind to specified targets. Spawned an entire wave of design tools: ProteinMPNN, LigandMPNN, RFantibody, BindCraft, RFdiffusion 2/3. Foundation of David Baker's 2024 Nobel-recognized work.

Try demo
Cost
Free
Open weights — self-host
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out

Why it matters

Earned David Baker a share of the 2024 Chemistry Nobel (alongside Hassabis and Jumper for AlphaFold). Established that AI can design novel functional proteins from scratch — a capability biology had been chasing for 50 years.

Core Capabilities

Science
Built for biology, chemistry, materials, weather, or math research.
Generative
Produces images, video, audio, or other media.
Vision
Understands images, scenes, and visual context.
Multimodal
Combines text, vision, and audio in one model.

Context Window

Context window not disclosed.

Availability

API
Not available
Product / App
Not available
Open Source
Released
Enterprise

Pricing Model

Free / self-host
Open weights — pay only for compute.
Self-host

What it feels like

  • Vision-language model from Academic / Independent — see the linked sources below for benchmark and review coverage
  • Vision and multimodal tasks are the typical fit per the published model card

Best use cases

  • Vision tasks (charts, documents, images) per the model card
  • See the model spec and sources block for benchmarked use cases

Not ideal for

  • Tasks far outside the modalities listed in this model's spec
  • Workflows where a more recent successor in the same family scores higher

Watson, J. L. · Juergens, D. · Bennett, N. R. · et al.