> ## Documentation Index > Fetch the complete documentation index at: https://docs.biohub.ai/llms.txt > Use this file to discover all available pages before exploring further. # generate > (ESM3) Generates an output track conditioned on inputs ## OpenAPI ````yaml openapi/biohub-platform-openapi.json POST /api/v1/generate openapi: 3.1.0 info: title: Biohub Platform API version: 1.0.0 servers: - url: https://biohub.ai security: [] paths: /api/v1/generate: post: tags: - v1 summary: (ESM3) Generates an output track conditioned on inputs operationId: generate_api_v1_generate_post parameters: - name: accept in: header required: false schema: anyOf: - type: string - type: 'null' title: Accept requestBody: content: application/json: schema: $ref: '#/components/schemas/GenerateRequest' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/GenerateResponse' application/vnd.evolutionaryscale.pickle: schema: type: string format: binary '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: GenerateRequest: properties: model: type: string enum: - esm3-open-2024-03 description: >- You may have access to additional, private models as well. These will be visible on the Rate Limits page under the Developer Console potential_sequence_of_concern: type: boolean description: >- Disclose potential sequences of concern. For approved users, such sequences will not go through additional safety filtering. Reach out if you are interested in using this. default: false track: type: string description: >- Track to generate: sequence, structure, secondary_structure, sasa, or function. invalid_ids: items: type: integer type: array description: Token indices that should not be sampled. default: [] schedule: type: string enum: - cosine - linear description: >- Unmasking schedule for generation. Controls the number of tokens to unmask during each round of iterative generation. default: cosine strategy: type: string enum: - random - entropy description: >- Unmasking strategy to use. Controls which tokens to unmask during each round of iterative generation. 'random' will unmask a correct number of tokens randomly. 'entropy' will unmask the tokens with the lowest logit entropy first. Default was random. Updated on 02/14/2025. default: random num_steps: type: integer maximum: 100 minimum: 1 description: >- Number of steps for generation. There is diminishing return for decoding steps more than 20. Note that this needs to be less than or equal to the sequence length. Default was 8. Updated on 02/14/2025. default: 20 temperature: type: number minimum: 0 description: Temperature for sampling. Default was 1.0. Updated on 02/14/2025. default: 0.5 temperature_annealing: type: boolean description: >- Whether temperature should be annealed during generation. Default was False. Updated on 02/14/2025. default: true top_p: type: number maximum: 1 exclusiveMinimum: 0 description: Top-p sampling. default: 1 condition_on_coordinates_only: type: boolean description: >- Use coordinates instead of structure tokens as generation conditioning. default: true inputs: $ref: '#/components/schemas/Tracks' only_compute_backbone_rmsd: type: boolean description: >- Only compute the RMSD of the backbone atoms. Affects the returned crmsd. default: false include_pae: type: boolean description: >- Whether to include Predicted Aligned Error (PAE) matrix in the response. Local inference ignores this flag. default: false type: object required: - model - track - inputs GenerateResponse: properties: model: type: string enum: - esm3-open-2024-03 description: >- You may have access to additional, private models as well. These will be visible on the Rate Limits page under the Developer Console created: type: string description: ISO formatted date time potential_sequence_of_concern: type: boolean description: Indicate that the returned sequence may be of potential concerns. default: false warning_messages: anyOf: - items: type: string type: array - type: 'null' description: Warning messages returned by FastAPI. outputs: anyOf: - $ref: '#/components/schemas/Tracks' - type: 'null' type: object required: - model - created - tokens_used HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array type: object Tracks: properties: sequence: anyOf: - type: string - type: 'null' description: >- Sequence of amino acids. As input, this can be partially masked out with `_`, for example to get logprob over masked positions secondary_structure: anyOf: - type: string - type: 'null' description: Secondary structure in 8-class DSSP format. sasa: anyOf: - items: anyOf: - type: integer - type: number - type: 'null' type: array - type: 'null' description: >- Solvent accessible surface area (SASA) as a list of floats. Nones are replaced with padding. 03/18/2025: A bug was fixed where 'inf' prior to this date was returned encoded as '-1', it will instead be 1000 going forward function: anyOf: - items: prefixItems: - type: string - type: integer - type: integer type: array maxItems: 3 minItems: 3 type: array - type: 'null' description: >- Function annotations, as a list of 3-tuples: (interpro tag, start, end). Start and end are 1-indexed, inclusive. We support interpro tags from version 95.0. coordinates: anyOf: - items: items: items: anyOf: - type: number - type: 'null' type: array type: array type: array - type: 'null' description: Coordinates of the N, CA, C atom sequence as a Nx37x3 array. plddt: anyOf: - items: type: number type: array - type: 'null' description: >- Per position plddt predictions for a protein. Usually produced by structure decoder. ptm: anyOf: - type: number - type: 'null' description: >- Predicted TM score of a protein. Usually produced by structure decoder. crmsd: anyOf: - type: number - type: 'null' description: >- Constrained RMSD between the generated protein coordinates and the input protein coordinates. Produced by the generate endpoint. globularity: anyOf: - type: number - type: 'null' description: >- Globularity of the generated protein. Produced by the generate endpoint. interface: anyOf: - items: type: string type: array - type: 'null' description: Annotations on residues that participate in a multimer interface. interface_ptm: anyOf: - type: number - type: 'null' description: Interface TM score of a protein. pae: anyOf: - items: items: type: number type: array type: array - type: 'null' description: >- Predicted Aligned Error matrix for the protein. Shape is L x L. Values are rounded to 2 decimals (well within 0.5 A bin width) type: object ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array msg: type: string type: type: string input: {} ctx: type: object type: object required: - loc - msg - type securitySchemes: HTTPBearer: type: http scheme: bearer ````