# Structure And Binding

## Start

`$ boltz-api predictions:structure-and-binding start`

**post** `/compute/v1/predictions/structure-and-binding`

Submit a prediction job that produces 3D structure coordinates and confidence scores for the input molecular complex, with optional binding metrics.

### Parameters

- `--input: object { entities, binding, bonds, 3 more }`

- `--model: "boltz-2.1"`

  Model to use for prediction

- `--idempotency-key: optional string`

  Client-provided key to prevent duplicate submissions on retries

- `--workspace-id: optional string`

  Target workspace ID (admin keys only; ignored for workspace keys)

### Returns

- `PredictionStructureAndBindingStartResponse: object { id, completed_at, created_at, 12 more }`

  - `id: string`

    Unique prediction identifier

  - `completed_at: string`

  - `created_at: string`

  - `data_deleted_at: string`

    When the input/output data was deleted, or null if still available

  - `error: object { code, message, details }`

    Error details when failed

    - `code: string`

      Machine-readable error code

    - `message: string`

      Human-readable error message

    - `details: optional unknown`

      Additional field-level error details keyed by input path, when available.

  - `expires_at: string`

    When this resource and its associated data will be permanently deleted. Null while still in progress.

  - `input: object { entities, binding, bonds, 3 more }`

    Prediction input (null if data deleted)

    - `entities: array of object { chain_ids, type, value, 2 more }  or object { chain_ids, type, value, 2 more }  or object { chain_ids, type, value, 2 more }  or 2 more`

      Entities (proteins, RNA, DNA, ligands) forming the complex to predict. Order determines chain assignment.

      - `ProteinEntityResponse: object { chain_ids, type, value, 2 more }`

        - `chain_ids: array of string`

          Chain IDs for this entity

        - `type: "protein"`

          - `"protein"`

        - `value: string`

          Amino acid sequence (one-letter codes)

        - `cyclic: optional boolean`

          Whether the sequence is cyclic

        - `modifications: optional array of object { residue_index, type, value }  or object { residue_index, type, value }`

          Post-translational modifications. Optional; defaults to an empty list when omitted.

          - `CCDModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "ccd"`

              - `"ccd"`

            - `value: string`

              CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine)

          - `SmilesModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "smiles"`

              - `"smiles"`

            - `value: string`

              SMILES string for the modification

      - `RNAEntityResponse: object { chain_ids, type, value, 2 more }`

        - `chain_ids: array of string`

          Chain IDs for this entity

        - `type: "rna"`

          - `"rna"`

        - `value: string`

          RNA nucleotide sequence (A, C, G, U, N)

        - `cyclic: optional boolean`

          Whether the sequence is cyclic

        - `modifications: optional array of object { residue_index, type, value }  or object { residue_index, type, value }`

          Chemical modifications. Optional; defaults to an empty list when omitted.

          - `CCDModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "ccd"`

              - `"ccd"`

            - `value: string`

              CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine)

          - `SmilesModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "smiles"`

              - `"smiles"`

            - `value: string`

              SMILES string for the modification

      - `DNAEntityResponse: object { chain_ids, type, value, 2 more }`

        - `chain_ids: array of string`

          Chain IDs for this entity

        - `type: "dna"`

          - `"dna"`

        - `value: string`

          DNA nucleotide sequence (A, C, G, T, N)

        - `cyclic: optional boolean`

          Whether the sequence is cyclic

        - `modifications: optional array of object { residue_index, type, value }  or object { residue_index, type, value }`

          Chemical modifications. Optional; defaults to an empty list when omitted.

          - `CCDModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "ccd"`

              - `"ccd"`

            - `value: string`

              CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine)

          - `SmilesModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "smiles"`

              - `"smiles"`

            - `value: string`

              SMILES string for the modification

      - `LigandCCDEntityResponse: object { chain_ids, type, value }`

        - `chain_ids: array of string`

          Chain IDs for this ligand

        - `type: "ligand_ccd"`

          - `"ligand_ccd"`

        - `value: string`

          CCD code (e.g., ATP, ADP)

      - `LigandSmilesEntityResponse: object { chain_ids, type, value }`

        - `chain_ids: array of string`

          Chain IDs for this ligand

        - `type: "ligand_smiles"`

          - `"ligand_smiles"`

        - `value: string`

          SMILES string representing the ligand

    - `binding: optional object { binder_chain_id, type }  or object { binder_chain_ids, type }`

      - `LigandProteinBindingResponse: object { binder_chain_id, type }`

        - `binder_chain_id: string`

          Chain ID of the ligand binder (must have exactly 1 copy, <50 atoms, and only ligands+proteins in entities)

        - `type: "ligand_protein_binding"`

          - `"ligand_protein_binding"`

      - `ProteinProteinBindingResponse: object { binder_chain_ids, type }`

        - `binder_chain_ids: array of string`

          Chain IDs of the protein binders

        - `type: "protein_protein_binding"`

          - `"protein_protein_binding"`

    - `bonds: optional array of object { atom1, atom2 }`

      Bond constraints between atoms. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported.

      - `atom1: object { atom_name, chain_id, type }  or object { atom_name, chain_id, residue_index, type }`

        Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

        - `LigandAtomResponse: object { atom_name, chain_id, type }`

          Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

          - `chain_id: string`

            Chain ID containing the atom

          - `type: "ligand_atom"`

            - `"ligand_atom"`

        - `PolymerAtomResponse: object { atom_name, chain_id, residue_index, type }`

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB)

          - `chain_id: string`

            Chain ID containing the atom

          - `residue_index: number`

            0-based residue index

          - `type: "polymer_atom"`

            - `"polymer_atom"`

      - `atom2: object { atom_name, chain_id, type }  or object { atom_name, chain_id, residue_index, type }`

        Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

        - `LigandAtomResponse: object { atom_name, chain_id, type }`

          Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

          - `chain_id: string`

            Chain ID containing the atom

          - `type: "ligand_atom"`

            - `"ligand_atom"`

        - `PolymerAtomResponse: object { atom_name, chain_id, residue_index, type }`

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB)

          - `chain_id: string`

            Chain ID containing the atom

          - `residue_index: number`

            0-based residue index

          - `type: "polymer_atom"`

            - `"polymer_atom"`

    - `constraints: optional array of object { binder_chain_id, contact_residues, max_distance_angstrom, 2 more }  or object { max_distance_angstrom, token1, token2, 2 more }`

      Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported.

      - `PocketConstraintResponse: object { binder_chain_id, contact_residues, max_distance_angstrom, 2 more }`

        Constrains the binder to interact with specific pocket residues on the target.

        - `binder_chain_id: string`

          Chain ID of the binder molecule

        - `contact_residues: map[array of number]`

          Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain.

        - `max_distance_angstrom: number`

          Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A.

        - `type: "pocket"`

          - `"pocket"`

        - `force: optional boolean`

          Whether to force the constraint

      - `ContactConstraintResponse: object { max_distance_angstrom, token1, token2, 2 more }`

        Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

        - `max_distance_angstrom: number`

          Maximum distance in Angstroms

        - `token1: object { chain_id, residue_index, type }  or object { atom_name, chain_id, type }`

          Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `PolymerContactTokenResponse: object { chain_id, residue_index, type }`

            - `chain_id: string`

              Chain ID

            - `residue_index: number`

              0-based residue index

            - `type: "polymer_contact"`

              - `"polymer_contact"`

          - `LigandContactTokenResponse: object { atom_name, chain_id, type }`

            Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

            - `atom_name: string`

              Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

            - `chain_id: string`

              Chain ID

            - `type: "ligand_contact"`

              - `"ligand_contact"`

        - `token2: object { chain_id, residue_index, type }  or object { atom_name, chain_id, type }`

          Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `PolymerContactTokenResponse: object { chain_id, residue_index, type }`

            - `chain_id: string`

              Chain ID

            - `residue_index: number`

              0-based residue index

            - `type: "polymer_contact"`

              - `"polymer_contact"`

          - `LigandContactTokenResponse: object { atom_name, chain_id, type }`

            Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

            - `atom_name: string`

              Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

            - `chain_id: string`

              Chain ID

            - `type: "ligand_contact"`

              - `"ligand_contact"`

        - `type: "contact"`

          - `"contact"`

        - `force: optional boolean`

          Whether to force the constraint

    - `model_options: optional object { recycling_steps, sampling_steps, step_scale }`

      - `recycling_steps: optional number`

        The number of recycling steps to use for prediction. Default is 3.

      - `sampling_steps: optional number`

        The number of sampling steps to use for prediction. Default is 200.

      - `step_scale: optional number`

        Diffusion step scale (temperature). Controls sampling diversity — higher values produce more varied structures. Default is 1.638.

    - `num_samples: optional number`

      Number of structure samples to generate

  - `livemode: boolean`

    Whether this resource was created with a live API key.

  - `model: "boltz-2.1"`

    Model used for prediction

    - `"boltz-2.1"`

  - `output: object { all_sample_results, best_sample, archive, binding_metrics }`

    Prediction output when succeeded

    - `all_sample_results: array of object { metrics, structure }`

      Per-sample structure results

      - `metrics: object { complex_ipde, complex_iplddt, complex_pde, 6 more }`

        - `complex_ipde: number`

          Complex interface predicted distance error. Lower is better.

        - `complex_iplddt: number`

          Complex interface pLDDT (0-1 float). Confidence at inter-chain interfaces.

        - `complex_pde: number`

          Complex predicted distance error. Lower is better.

        - `complex_plddt: number`

          Complex pLDDT (0-1 float). Per-residue confidence averaged over the complex.

        - `iptm: number`

          Interface predicted TM score (0-1). Confidence in domain interfaces.

        - `ligand_iptm: number`

          Ligand interface pTM (0-1). Only present when ligands are included.

        - `protein_iptm: number`

          Protein-protein interface pTM (0-1). Only present for multi-protein complexes.

        - `ptm: number`

          Predicted TM score (0-1). Global structure quality.

        - `structure_confidence: number`

          Overall structure confidence (0-1).

      - `structure: object { url, url_expires_at }`

        - `url: string`

          URL to download the file

        - `url_expires_at: string`

          When the presigned URL expires

    - `best_sample: object { metrics, structure }`

      - `metrics: object { complex_ipde, complex_iplddt, complex_pde, 6 more }`

        - `complex_ipde: number`

          Complex interface predicted distance error. Lower is better.

        - `complex_iplddt: number`

          Complex interface pLDDT (0-1 float). Confidence at inter-chain interfaces.

        - `complex_pde: number`

          Complex predicted distance error. Lower is better.

        - `complex_plddt: number`

          Complex pLDDT (0-1 float). Per-residue confidence averaged over the complex.

        - `iptm: number`

          Interface predicted TM score (0-1). Confidence in domain interfaces.

        - `ligand_iptm: number`

          Ligand interface pTM (0-1). Only present when ligands are included.

        - `protein_iptm: number`

          Protein-protein interface pTM (0-1). Only present for multi-protein complexes.

        - `ptm: number`

          Predicted TM score (0-1). Global structure quality.

        - `structure_confidence: number`

          Overall structure confidence (0-1).

      - `structure: object { url, url_expires_at }`

        - `url: string`

          URL to download the file

        - `url_expires_at: string`

          When the presigned URL expires

    - `archive: optional object { url, url_expires_at }`

      - `url: string`

        URL to download the file

      - `url_expires_at: string`

        When the presigned URL expires

    - `binding_metrics: optional object { binding_confidence, optimization_score, type }  or object { binding_confidence, type }`

      - `LigandProteinBindingMetrics: object { binding_confidence, optimization_score, type }`

        - `binding_confidence: number`

          Confidence that binding occurs (0-1). Primary metric for hit discovery.

        - `optimization_score: number`

          Binding strength ranking score for lead optimization. Higher values indicate stronger predicted binding.

        - `type: "ligand_protein_binding_metrics"`

          - `"ligand_protein_binding_metrics"`

      - `ProteinProteinBindingMetrics: object { binding_confidence, type }`

        - `binding_confidence: number`

          Confidence that binding occurs (0-1). Primary metric for hit discovery.

        - `type: "protein_protein_binding_metrics"`

          - `"protein_protein_binding_metrics"`

  - `started_at: string`

  - `status: "pending" or "running" or "succeeded" or "failed"`

    - `"pending"`

    - `"running"`

    - `"succeeded"`

    - `"failed"`

  - `version: string`

    Model version used for prediction

  - `workspace_id: string`

    Workspace ID

  - `idempotency_key: optional string`

    Client-provided idempotency key

### Example

```cli
boltz-api predictions:structure-and-binding start \
  --input '{entities: [{chain_ids: [string], type: protein, value: value, cyclic: true, modifications: [{residue_index: 0, type: ccd, value: value}]}], binding: {binder_chain_id: binder_chain_id, type: ligand_protein_binding}, bonds: [{atom1: {atom_name: atom_name, chain_id: chain_id, type: ligand_atom}, atom2: {atom_name: atom_name, chain_id: chain_id, type: ligand_atom}}], constraints: [{binder_chain_id: binder_chain_id, contact_residues: {A: [42, 43, 44, 67, 68, 69]}, max_distance_angstrom: 0, type: pocket, force: true}], model_options: {recycling_steps: 1, sampling_steps: 1, step_scale: 1.3}, num_samples: 1}' \
  --model boltz-2.1
```

## List

`$ boltz-api predictions:structure-and-binding list`

**get** `/compute/v1/predictions/structure-and-binding`

List structure and binding predictions, optionally filtered by workspace

### Parameters

- `--after-id: optional string`

  Return results after this ID

- `--before-id: optional string`

  Return results before this ID

- `--limit: optional number`

  Max items to return. Defaults to 100.

- `--workspace-id: optional string`

  Filter by workspace ID. Only used with admin API keys. If not provided, defaults to the workspace associated with the API key, or the default workspace for admin keys.

### Returns

- `ListBoltz2PredictionsResponse: object { data, first_id, has_more, last_id }`

  - `data: array of object { id, completed_at, created_at, 10 more }`

    - `id: string`

      Unique prediction identifier

    - `completed_at: string`

    - `created_at: string`

    - `data_deleted_at: string`

      When the input/output data was deleted, or null if still available

    - `error: object { code, message, details }`

      Error details when failed

      - `code: string`

        Machine-readable error code

      - `message: string`

        Human-readable error message

      - `details: optional unknown`

        Additional field-level error details keyed by input path, when available.

    - `expires_at: string`

      When this resource and its associated data will be permanently deleted. Null while still in progress.

    - `livemode: boolean`

      Whether this resource was created with a live API key.

    - `model: "boltz-2.1"`

      Model used for prediction

      - `"boltz-2.1"`

    - `started_at: string`

    - `status: "pending" or "running" or "succeeded" or "failed"`

      - `"pending"`

      - `"running"`

      - `"succeeded"`

      - `"failed"`

    - `version: string`

      Model version used for prediction

    - `workspace_id: string`

      Workspace ID

    - `idempotency_key: optional string`

      Client-provided idempotency key

  - `first_id: string`

    ID of the first item. Use as before_id for the previous page.

  - `has_more: boolean`

  - `last_id: string`

    ID of the last item. Use as after_id for the next page.

### Example

```cli
boltz-api predictions:structure-and-binding list
```

## Retrieve

`$ boltz-api predictions:structure-and-binding retrieve`

**get** `/compute/v1/predictions/structure-and-binding/{id}`

Retrieve a prediction by ID, including its status and results.

### Parameters

- `--id: string`

  Prediction ID

- `--workspace-id: optional string`

  Workspace ID. Only used with admin API keys. Ignored (or validated) for workspace-scoped keys.

### Returns

- `PredictionStructureAndBindingGetResponse: object { id, completed_at, created_at, 12 more }`

  - `id: string`

    Unique prediction identifier

  - `completed_at: string`

  - `created_at: string`

  - `data_deleted_at: string`

    When the input/output data was deleted, or null if still available

  - `error: object { code, message, details }`

    Error details when failed

    - `code: string`

      Machine-readable error code

    - `message: string`

      Human-readable error message

    - `details: optional unknown`

      Additional field-level error details keyed by input path, when available.

  - `expires_at: string`

    When this resource and its associated data will be permanently deleted. Null while still in progress.

  - `input: object { entities, binding, bonds, 3 more }`

    Prediction input (null if data deleted)

    - `entities: array of object { chain_ids, type, value, 2 more }  or object { chain_ids, type, value, 2 more }  or object { chain_ids, type, value, 2 more }  or 2 more`

      Entities (proteins, RNA, DNA, ligands) forming the complex to predict. Order determines chain assignment.

      - `ProteinEntityResponse: object { chain_ids, type, value, 2 more }`

        - `chain_ids: array of string`

          Chain IDs for this entity

        - `type: "protein"`

          - `"protein"`

        - `value: string`

          Amino acid sequence (one-letter codes)

        - `cyclic: optional boolean`

          Whether the sequence is cyclic

        - `modifications: optional array of object { residue_index, type, value }  or object { residue_index, type, value }`

          Post-translational modifications. Optional; defaults to an empty list when omitted.

          - `CCDModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "ccd"`

              - `"ccd"`

            - `value: string`

              CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine)

          - `SmilesModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "smiles"`

              - `"smiles"`

            - `value: string`

              SMILES string for the modification

      - `RNAEntityResponse: object { chain_ids, type, value, 2 more }`

        - `chain_ids: array of string`

          Chain IDs for this entity

        - `type: "rna"`

          - `"rna"`

        - `value: string`

          RNA nucleotide sequence (A, C, G, U, N)

        - `cyclic: optional boolean`

          Whether the sequence is cyclic

        - `modifications: optional array of object { residue_index, type, value }  or object { residue_index, type, value }`

          Chemical modifications. Optional; defaults to an empty list when omitted.

          - `CCDModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "ccd"`

              - `"ccd"`

            - `value: string`

              CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine)

          - `SmilesModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "smiles"`

              - `"smiles"`

            - `value: string`

              SMILES string for the modification

      - `DNAEntityResponse: object { chain_ids, type, value, 2 more }`

        - `chain_ids: array of string`

          Chain IDs for this entity

        - `type: "dna"`

          - `"dna"`

        - `value: string`

          DNA nucleotide sequence (A, C, G, T, N)

        - `cyclic: optional boolean`

          Whether the sequence is cyclic

        - `modifications: optional array of object { residue_index, type, value }  or object { residue_index, type, value }`

          Chemical modifications. Optional; defaults to an empty list when omitted.

          - `CCDModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "ccd"`

              - `"ccd"`

            - `value: string`

              CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine)

          - `SmilesModificationResponse: object { residue_index, type, value }`

            - `residue_index: number`

              0-based index of the residue to modify

            - `type: "smiles"`

              - `"smiles"`

            - `value: string`

              SMILES string for the modification

      - `LigandCCDEntityResponse: object { chain_ids, type, value }`

        - `chain_ids: array of string`

          Chain IDs for this ligand

        - `type: "ligand_ccd"`

          - `"ligand_ccd"`

        - `value: string`

          CCD code (e.g., ATP, ADP)

      - `LigandSmilesEntityResponse: object { chain_ids, type, value }`

        - `chain_ids: array of string`

          Chain IDs for this ligand

        - `type: "ligand_smiles"`

          - `"ligand_smiles"`

        - `value: string`

          SMILES string representing the ligand

    - `binding: optional object { binder_chain_id, type }  or object { binder_chain_ids, type }`

      - `LigandProteinBindingResponse: object { binder_chain_id, type }`

        - `binder_chain_id: string`

          Chain ID of the ligand binder (must have exactly 1 copy, <50 atoms, and only ligands+proteins in entities)

        - `type: "ligand_protein_binding"`

          - `"ligand_protein_binding"`

      - `ProteinProteinBindingResponse: object { binder_chain_ids, type }`

        - `binder_chain_ids: array of string`

          Chain IDs of the protein binders

        - `type: "protein_protein_binding"`

          - `"protein_protein_binding"`

    - `bonds: optional array of object { atom1, atom2 }`

      Bond constraints between atoms. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported.

      - `atom1: object { atom_name, chain_id, type }  or object { atom_name, chain_id, residue_index, type }`

        Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

        - `LigandAtomResponse: object { atom_name, chain_id, type }`

          Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

          - `chain_id: string`

            Chain ID containing the atom

          - `type: "ligand_atom"`

            - `"ligand_atom"`

        - `PolymerAtomResponse: object { atom_name, chain_id, residue_index, type }`

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB)

          - `chain_id: string`

            Chain ID containing the atom

          - `residue_index: number`

            0-based residue index

          - `type: "polymer_atom"`

            - `"polymer_atom"`

      - `atom2: object { atom_name, chain_id, type }  or object { atom_name, chain_id, residue_index, type }`

        Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

        - `LigandAtomResponse: object { atom_name, chain_id, type }`

          Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

          - `chain_id: string`

            Chain ID containing the atom

          - `type: "ligand_atom"`

            - `"ligand_atom"`

        - `PolymerAtomResponse: object { atom_name, chain_id, residue_index, type }`

          - `atom_name: string`

            Standardized atom name (verifiable in CIF file on RCSB)

          - `chain_id: string`

            Chain ID containing the atom

          - `residue_index: number`

            0-based residue index

          - `type: "polymer_atom"`

            - `"polymer_atom"`

    - `constraints: optional array of object { binder_chain_id, contact_residues, max_distance_angstrom, 2 more }  or object { max_distance_angstrom, token1, token2, 2 more }`

      Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported.

      - `PocketConstraintResponse: object { binder_chain_id, contact_residues, max_distance_angstrom, 2 more }`

        Constrains the binder to interact with specific pocket residues on the target.

        - `binder_chain_id: string`

          Chain ID of the binder molecule

        - `contact_residues: map[array of number]`

          Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain.

        - `max_distance_angstrom: number`

          Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A.

        - `type: "pocket"`

          - `"pocket"`

        - `force: optional boolean`

          Whether to force the constraint

      - `ContactConstraintResponse: object { max_distance_angstrom, token1, token2, 2 more }`

        Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

        - `max_distance_angstrom: number`

          Maximum distance in Angstroms

        - `token1: object { chain_id, residue_index, type }  or object { atom_name, chain_id, type }`

          Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `PolymerContactTokenResponse: object { chain_id, residue_index, type }`

            - `chain_id: string`

              Chain ID

            - `residue_index: number`

              0-based residue index

            - `type: "polymer_contact"`

              - `"polymer_contact"`

          - `LigandContactTokenResponse: object { atom_name, chain_id, type }`

            Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

            - `atom_name: string`

              Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

            - `chain_id: string`

              Chain ID

            - `type: "ligand_contact"`

              - `"ligand_contact"`

        - `token2: object { chain_id, residue_index, type }  or object { atom_name, chain_id, type }`

          Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

          - `PolymerContactTokenResponse: object { chain_id, residue_index, type }`

            - `chain_id: string`

              Chain ID

            - `residue_index: number`

              0-based residue index

            - `type: "polymer_contact"`

              - `"polymer_contact"`

          - `LigandContactTokenResponse: object { atom_name, chain_id, type }`

            Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported.

            - `atom_name: string`

              Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead.

            - `chain_id: string`

              Chain ID

            - `type: "ligand_contact"`

              - `"ligand_contact"`

        - `type: "contact"`

          - `"contact"`

        - `force: optional boolean`

          Whether to force the constraint

    - `model_options: optional object { recycling_steps, sampling_steps, step_scale }`

      - `recycling_steps: optional number`

        The number of recycling steps to use for prediction. Default is 3.

      - `sampling_steps: optional number`

        The number of sampling steps to use for prediction. Default is 200.

      - `step_scale: optional number`

        Diffusion step scale (temperature). Controls sampling diversity — higher values produce more varied structures. Default is 1.638.

    - `num_samples: optional number`

      Number of structure samples to generate

  - `livemode: boolean`

    Whether this resource was created with a live API key.

  - `model: "boltz-2.1"`

    Model used for prediction

    - `"boltz-2.1"`

  - `output: object { all_sample_results, best_sample, archive, binding_metrics }`

    Prediction output when succeeded

    - `all_sample_results: array of object { metrics, structure }`

      Per-sample structure results

      - `metrics: object { complex_ipde, complex_iplddt, complex_pde, 6 more }`

        - `complex_ipde: number`

          Complex interface predicted distance error. Lower is better.

        - `complex_iplddt: number`

          Complex interface pLDDT (0-1 float). Confidence at inter-chain interfaces.

        - `complex_pde: number`

          Complex predicted distance error. Lower is better.

        - `complex_plddt: number`

          Complex pLDDT (0-1 float). Per-residue confidence averaged over the complex.

        - `iptm: number`

          Interface predicted TM score (0-1). Confidence in domain interfaces.

        - `ligand_iptm: number`

          Ligand interface pTM (0-1). Only present when ligands are included.

        - `protein_iptm: number`

          Protein-protein interface pTM (0-1). Only present for multi-protein complexes.

        - `ptm: number`

          Predicted TM score (0-1). Global structure quality.

        - `structure_confidence: number`

          Overall structure confidence (0-1).

      - `structure: object { url, url_expires_at }`

        - `url: string`

          URL to download the file

        - `url_expires_at: string`

          When the presigned URL expires

    - `best_sample: object { metrics, structure }`

      - `metrics: object { complex_ipde, complex_iplddt, complex_pde, 6 more }`

        - `complex_ipde: number`

          Complex interface predicted distance error. Lower is better.

        - `complex_iplddt: number`

          Complex interface pLDDT (0-1 float). Confidence at inter-chain interfaces.

        - `complex_pde: number`

          Complex predicted distance error. Lower is better.

        - `complex_plddt: number`

          Complex pLDDT (0-1 float). Per-residue confidence averaged over the complex.

        - `iptm: number`

          Interface predicted TM score (0-1). Confidence in domain interfaces.

        - `ligand_iptm: number`

          Ligand interface pTM (0-1). Only present when ligands are included.

        - `protein_iptm: number`

          Protein-protein interface pTM (0-1). Only present for multi-protein complexes.

        - `ptm: number`

          Predicted TM score (0-1). Global structure quality.

        - `structure_confidence: number`

          Overall structure confidence (0-1).

      - `structure: object { url, url_expires_at }`

        - `url: string`

          URL to download the file

        - `url_expires_at: string`

          When the presigned URL expires

    - `archive: optional object { url, url_expires_at }`

      - `url: string`

        URL to download the file

      - `url_expires_at: string`

        When the presigned URL expires

    - `binding_metrics: optional object { binding_confidence, optimization_score, type }  or object { binding_confidence, type }`

      - `LigandProteinBindingMetrics: object { binding_confidence, optimization_score, type }`

        - `binding_confidence: number`

          Confidence that binding occurs (0-1). Primary metric for hit discovery.

        - `optimization_score: number`

          Binding strength ranking score for lead optimization. Higher values indicate stronger predicted binding.

        - `type: "ligand_protein_binding_metrics"`

          - `"ligand_protein_binding_metrics"`

      - `ProteinProteinBindingMetrics: object { binding_confidence, type }`

        - `binding_confidence: number`

          Confidence that binding occurs (0-1). Primary metric for hit discovery.

        - `type: "protein_protein_binding_metrics"`

          - `"protein_protein_binding_metrics"`

  - `started_at: string`

  - `status: "pending" or "running" or "succeeded" or "failed"`

    - `"pending"`

    - `"running"`

    - `"succeeded"`

    - `"failed"`

  - `version: string`

    Model version used for prediction

  - `workspace_id: string`

    Workspace ID

  - `idempotency_key: optional string`

    Client-provided idempotency key

### Example

```cli
boltz-api predictions:structure-and-binding retrieve \
  --id sab_pred_2X7Ab9Cd3Ef6Gh1JkLmN
```

## Delete Data

`$ boltz-api predictions:structure-and-binding delete-data`

**post** `/compute/v1/predictions/structure-and-binding/{id}/delete-data`

Permanently delete the input, output, and result data associated with this prediction. The prediction record itself is retained with a `data_deleted_at` timestamp. This action is irreversible.

### Parameters

- `--id: string`

  Prediction ID

### Returns

- `PredictionStructureAndBindingDeleteDataResponse: object { id, data_deleted, data_deleted_at }`

  - `id: string`

    ID of the resource whose data was deleted

  - `data_deleted: true`

    - `true`

  - `data_deleted_at: string`

    When the data was deleted

### Example

```cli
boltz-api predictions:structure-and-binding delete-data \
  --id sab_pred_2X7Ab9Cd3Ef6Gh1JkLmN
```

## Estimate Cost

`$ boltz-api predictions:structure-and-binding estimate-cost`

**post** `/compute/v1/predictions/structure-and-binding/estimate-cost`

Estimate the cost of a prediction without creating any resource or consuming GPU.

### Parameters

- `--input: object { entities, binding, bonds, 3 more }`

- `--model: "boltz-2.1"`

  Model to use for prediction

- `--idempotency-key: optional string`

  Client-provided key to prevent duplicate submissions on retries

- `--workspace-id: optional string`

  Target workspace ID (admin keys only; ignored for workspace keys)

### Returns

- `PredictionStructureAndBindingEstimateCostResponse: object { breakdown, disclaimer, estimated_cost_usd }`

  Estimate response with monetary values encoded as decimal strings to preserve precision.

  - `breakdown: object { application, cost_per_unit_usd, num_units }`

    Cost breakdown for the billed application.

    - `application: "structure_and_binding" or "small_molecule_design" or "small_molecule_library_screen" or 3 more`

      - `"structure_and_binding"`

      - `"small_molecule_design"`

      - `"small_molecule_library_screen"`

      - `"protein_design"`

      - `"protein_library_screen"`

      - `"adme"`

    - `cost_per_unit_usd: string`

      Estimated cost per displayed unit as a decimal string, rounded up to 4 decimal places. This may include token-size multipliers or generation overhead; estimated_cost_usd is the authoritative total.

    - `num_units: number`

      Number of units shown for the estimate. For structure-and-binding, this is the requested number of samples. For protein and small-molecule design/screen endpoints, this is the requested number of proteins or molecules.

  - `disclaimer: string`

  - `estimated_cost_usd: string`

    Estimated total cost as a decimal string

### Example

```cli
boltz-api predictions:structure-and-binding estimate-cost \
  --input '{entities: [{chain_ids: [string], type: protein, value: value, cyclic: true, modifications: [{residue_index: 0, type: ccd, value: value}]}], binding: {binder_chain_id: binder_chain_id, type: ligand_protein_binding}, bonds: [{atom1: {atom_name: atom_name, chain_id: chain_id, type: ligand_atom}, atom2: {atom_name: atom_name, chain_id: chain_id, type: ligand_atom}}], constraints: [{binder_chain_id: binder_chain_id, contact_residues: {A: [42, 43, 44, 67, 68, 69]}, max_distance_angstrom: 0, type: pocket, force: true}], model_options: {recycling_steps: 1, sampling_steps: 1, step_scale: 1.3}, num_samples: 1}' \
  --model boltz-2.1
```