Skip to content
Go to Boltz API

API Reference

Libraries

npm install boltz-api
pip install boltz-api
go get -u 'github.com/boltz-bio/boltz-api-go@v0.0.1'
curl -fsSL https://install.boltz.bio/boltz-api/install.sh | sh

API Overview

Predictions

Run prediction models on molecular inputs. Each application is available as its own endpoint with application-specific inputs and outputs.

PredictionsStructure And Binding

Predict 3D structure coordinates, per-residue confidence scores, and binding metrics for a molecular complex. Supports optional template-guided folding and per-protein MSA control.

Start a structure and binding prediction
POST/compute/v1/predictions/structure-and-binding
List structure and binding predictions
GET/compute/v1/predictions/structure-and-binding
Retrieve a structure and binding prediction
GET/compute/v1/predictions/structure-and-binding/{id}
Delete prediction data
POST/compute/v1/predictions/structure-and-binding/{id}/delete-data
Estimate cost for a structure and binding prediction
POST/compute/v1/predictions/structure-and-binding/estimate-cost

PredictionsAdme

Predict Tier 1 ADME summary values for a batch of small molecules specified by SMILES.

Start an ADME prediction
POST/compute/v1/predictions/adme
List ADME predictions
GET/compute/v1/predictions/adme
Retrieve an ADME prediction
GET/compute/v1/predictions/adme/{id}
Delete ADME prediction data
POST/compute/v1/predictions/adme/{id}/delete-data
Estimate cost for an ADME prediction
POST/compute/v1/predictions/adme/estimate-cost

Small Molecule

Small Molecule Pipeline: design novel small molecules and screen compound libraries against protein targets. Includes de novo generation and virtual screening.

Small MoleculeDesign

Generate novel small molecules optimized for binding to a protein target. Results are scored by binding confidence (likelihood of binding, for hit discovery), optimization score (binding strength ranking, for lead optimization), and structure confidence.

Start a small molecule de novo design run
POST/compute/v1/small-molecule/design
List small molecule design runs
GET/compute/v1/small-molecule/design
Get small molecule design run status
GET/compute/v1/small-molecule/design/{id}
Get generated small molecule designs
GET/compute/v1/small-molecule/design/{id}/results
Stop a running small molecule design run
POST/compute/v1/small-molecule/design/{id}/stop
Resume a stopped small molecule design run
POST/compute/v1/small-molecule/design/{id}/resume
Delete small molecule design run data
POST/compute/v1/small-molecule/design/{id}/delete-data
Estimate cost for a small molecule design run
POST/compute/v1/small-molecule/design/estimate-cost

Small MoleculeLibrary Screen

Screen an existing library of small molecules against a protein target. Results are scored by binding confidence (likelihood of binding, for hit discovery), optimization score (binding strength ranking, for lead optimization), and structure confidence.

Start a small molecule library screen
POST/compute/v1/small-molecule/library-screen
List small molecule library screens
GET/compute/v1/small-molecule/library-screen
Get small molecule library screen status
GET/compute/v1/small-molecule/library-screen/{id}
Get screened small molecule candidates
GET/compute/v1/small-molecule/library-screen/{id}/results
Stop a running small molecule library screen
POST/compute/v1/small-molecule/library-screen/{id}/stop
Resume a stopped small molecule library screen
POST/compute/v1/small-molecule/library-screen/{id}/resume
Delete small molecule library screen data
POST/compute/v1/small-molecule/library-screen/{id}/delete-data
Estimate cost for a small molecule library screen
POST/compute/v1/small-molecule/library-screen/estimate-cost

Protein

Design novel protein binders, redesign selected residues in fixed structures, and screen protein libraries against targets.

ProteinDesign

Generate novel protein binders optimized for binding to a target structure. Binder specifications can be provided directly, uploaded as structure templates, or selected from Boltz-managed curated nanobody and antibody defaults. Results are scored by binding confidence (likelihood of protein-protein interaction) and structure confidence.

Start a protein de novo design run
POST/compute/v1/protein/design
List protein design runs
GET/compute/v1/protein/design
List curated protein design specifications
GET/compute/v1/protein/design/curated-specifications
Get protein design run status
GET/compute/v1/protein/design/{id}
Get generated protein designs
GET/compute/v1/protein/design/{id}/results
Stop a running protein design run
POST/compute/v1/protein/design/{id}/stop
Resume a stopped protein design run
POST/compute/v1/protein/design/{id}/resume
Delete protein design run data
POST/compute/v1/protein/design/{id}/delete-data
Estimate cost for a protein design run
POST/compute/v1/protein/design/estimate-cost

ProteinSequence Redesign

Redesign selected protein residues in one fixed CIF structure. Use the top-level type discriminator to choose binder redesign, with target and binder chain roles, or generic redesign. Every chain in the input structure must be assigned exactly once. Binder results include binding and structure metrics; generic results include structure and secondary-structure metrics.

Start a protein sequence redesign run
POST/compute/v1/protein/sequence-redesign
List protein sequence redesign runs
GET/compute/v1/protein/sequence-redesign
Get protein sequence redesign run status
GET/compute/v1/protein/sequence-redesign/{id}
Get redesigned protein sequences
GET/compute/v1/protein/sequence-redesign/{id}/results
Stop a running protein sequence redesign run
POST/compute/v1/protein/sequence-redesign/{id}/stop
Resume a stopped protein sequence redesign run
POST/compute/v1/protein/sequence-redesign/{id}/resume
Delete protein sequence redesign run data
POST/compute/v1/protein/sequence-redesign/{id}/delete-data
Estimate cost for a protein sequence redesign run
POST/compute/v1/protein/sequence-redesign/estimate-cost

ProteinLibrary Screen

Screen an existing library of proteins against a target structure. Results are scored by binding confidence (likelihood of protein-protein interaction) and structure confidence.

Start a protein library screen
POST/compute/v1/protein/library-screen
List protein library screens
GET/compute/v1/protein/library-screen
Get protein library screen status
GET/compute/v1/protein/library-screen/{id}
Get screened protein candidates
GET/compute/v1/protein/library-screen/{id}/results
Stop a running protein library screen
POST/compute/v1/protein/library-screen/{id}/stop
Resume a stopped protein library screen
POST/compute/v1/protein/library-screen/{id}/resume
Delete protein library screen data
POST/compute/v1/protein/library-screen/{id}/delete-data
Estimate cost for a protein library screen
POST/compute/v1/protein/library-screen/estimate-cost

Share read-only access to predictions and pipeline runs by issuing time-limited links that visitors can open without an API key or, for email-restricted links, after signing in with an allowed email. A share link is scoped to a single workspace and bundles one or more predictions and pipeline runs. The link ID is itself the bearer credential; treat it as a secret. Create, retrieve, and archive require a workspace-scoped API key with read permission on every referenced resource. Retrieving metadata remains available after expiry or archive. Viewing content and listing shared pipeline results are gated by the link ID and the link’s access mode. Archiving a link revokes public access immediately; subsequent content reads return 404. The underlying predictions and pipelines are unaffected and remain accessible through their own authenticated endpoints.

Create a share link
POST/compute/v1/share-links
Retrieve a share link
GET/compute/v1/share-links/{id}
Archive a share link
POST/compute/v1/share-links/{id}/archive
List pipeline results from a share link
GET/compute/v1/share/{id}/pipelines/{pipelineId}/results

Admin

Manage workspaces and API keys. Requires an admin API key. Admin keys have full access to all management and compute operations across all workspaces in the organization.

AdminWorkspaces

Workspaces provide isolated environments for organizing predictions and pipeline runs across teams, projects, or customers. Each workspace has independent data retention settings and can be associated with workspace API keys.

Create a workspace
POST/compute/v1/admin/workspaces
List workspaces
GET/compute/v1/admin/workspaces
Get a workspace
GET/compute/v1/admin/workspaces/{workspace_id}
Update a workspace
POST/compute/v1/admin/workspaces/{workspace_id}
Archive a workspace
POST/compute/v1/admin/workspaces/{workspace_id}/archive
Get a workspace spending limit
GET/compute/v1/admin/workspaces/{workspace_id}/spending-limit
Set a workspace spending limit
PUT/compute/v1/admin/workspaces/{workspace_id}/spending-limit

AdminAPI Keys

API keys authenticate requests to the Boltz API. There are two key types: admin keys have full access to all management and compute operations across the organization, while workspace keys are scoped to a single workspace and can only perform compute operations (predictions, protein design, small molecule design) within that workspace. Keys can be created in live or test mode. Test keys (prefixed sk_bc_*_test_) create test-mode resources with synthetic data and no GPU cost. Every resource includes a livemode field indicating its mode.

Create a workspace API key
POST/compute/v1/admin/api-keys
List API keys
GET/compute/v1/admin/api-keys
Revoke an API key
POST/compute/v1/admin/api-keys/{api_key_id}/revoke

AdminUsage

Retrieve aggregated usage data for the organization. Usage can be grouped by workspace and/or application, and filtered by time range, workspace, and application.

Get usage data
GET/compute/v1/admin/usage

Cli

Check the installed boltz-api CLI version against the currently published CLI release and the minimum version supported by the Boltz API.

CLI version metadata
GET/compute/v1/cli/version

Auth

Inspect the authentication context for the current credential, including the organization or workspace scope for API keys and the available organization memberships for OAuth bearer tokens. OAuth callers can use this information to choose which organization to send with future requests.

Get current compute auth context
GET/compute/v1/auth/me