Post

generate_tensor

/api/v1/generate_tensor

(ESM3) Generates an output track conditioned on inputs. Accepts and returns raw tokens.

Request

Include your API key in the Authorization header as a Bearer token.
Bodyapplication/json
modelstring
required

You may have access to additional, private models as well. These will be visible on the Rate Limits page under the Developer Console

Allowed value:esm3-open-2024-03
potential_sequence_of_concernboolean

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
trackstring
required

Track to generate: sequence, structure, secondary_structure, sasa, or function.

invalid_idsarray[integer]

Token indices that should not be sampled.

schedulestring

Unmasking schedule for generation. Controls the number of tokens to unmask during each round of iterative generation.

Default:cosineAllowed values:cosinelinear
strategystring

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:randomAllowed values:randomentropy
num_stepsinteger

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:20Range:[1, 100]
temperaturenumber

Temperature for sampling. Default was 1.0. Updated on 02/14/2025.

Default:0.5Range:[0, ∞)
temperature_annealingboolean

Whether temperature should be annealed during generation. Default was False. Updated on 02/14/2025.

Default:true
top_pnumber

Top-p sampling.

Default:1Range:(0, 1]
condition_on_coordinates_onlyboolean

Use coordinates instead of structure tokens as generation conditioning.

Default:true
inputsTokens
required