Skip to content

API documentation

JapanFold API

Fold proteins, co-fold complexes with ligands (and get binding affinity), design de novo binders, and compute protein embeddings, over an HTTP API hosted in Japan. Boltz-2, ESMFold-2, OpenFold3, OpenBind-0, RoseTTAFold3, OpenDDE and AF2-IG for structure prediction, BoltzGen, RFdiffusion3 and PXDesign for binder design, ESMC and SaProt for embeddings. Nothing to install and no local GPU. Open an account and it starts with $100.00 of credit.

Base URL https://api.japanfold.aiand.com
Contract /v1/openapi.json OpenAPI 3.1, the source of truth
MCP https://api.japanfold.aiand.com/mcp the same API as agent tools

Fold your first protein API reference Try it in the browser

The model: submit → poll → download

Everything is an async job. Submit work, get back a job id, wait until the status is terminal, then download the results.

POST /v1/predictions   or   POST /v1/designs      →  { "id": "...", "status": "running", ... }
GET  /v1/jobs/{id}?wait=60                         →  held until status is succeeded/failed/canceled (max 60 s)
GET  /v1/jobs/{id}/results                          →  scores + a list of downloadable artifacts
GET  /v1/jobs/{id}/archive                          →  everything as one .zip

Statuses: queued → running → succeeded | failed | canceled.

A job and its files are kept for 30 days after it finishes. Download what you want to keep; see Retention.

Fold your first protein in 3 calls

BASE=https://api.japanfold.aiand.com
KEY=your_key_here    # from japanfold.aiand.com/account/token
H=(-H "Authorization: Bearer $KEY")

# 1. submit: a bare `sequence` is the simplest input
JOB=$(curl -s "${H[@]}" -X POST $BASE/v1/predictions \
  -H 'Content-Type: application/json' \
  -d '{"model":"boltz2","name":"myprotein","sequence":"MKTAYIAKQRQISFVKSHFSRQLEERLGLIEVQ"}' \
  | python3 -c 'import sys,json; r=json.load(sys.stdin); print(r["id"]) if "id" in r else sys.exit(r["detail"])')

# 2. wait. `?wait=60` holds the request until the job finishes or 60 s pass;
#    repeat it while the status is still queued or running. No sleep needed.
curl -s "${H[@]}" "$BASE/v1/jobs/$JOB?wait=60"

# 3. once status=succeeded: read scores, then download the structures
curl -s "${H[@]}" $BASE/v1/jobs/$JOB/results
curl -s "${H[@]}" $BASE/v1/jobs/$JOB/archive -o myprotein.zip && unzip -oq myprotein.zip -d myprotein

Complexes, ligands, affinity, binder design and parameter choice are all variations on these three calls.

Where to go next

  • Authentication

    Every call needs a key. Your account opens with $100.00 of credit.

  • Predictions

    Input shapes, models, co-folding, affinity, params.

  • Designs

    BoltzGen, RFdiffusion3 and PXDesign binder design.

  • Embeddings

    ESMC and SaProt protein embeddings (per-residue + pooled).

  • Jobs

    Polling, listing, cancel/delete, results, logs, artifacts, archive.

  • Models & limits

    The model list, every parameter, and the caps.

  • Accuracy

    Output parity against each model's reference implementation.

  • Errors

    The problem+json shape and the status codes.

  • Examples

    End-to-end fold, co-fold+affinity and design in curl and Python.

  • The JapanFold skill

    Fold and design straight from your AI agent, with the skill or the MCP server.

Network egress

If your environment sandboxes outbound HTTP, allow the host api.japanfold.aiand.com.

Powered by ai& on Tenstorrent