EvolutionaryScale

EvolutionaryScale Embeddings API

Sequence-only tokenization and representation extraction.

GitHub OpenAPI

Operations 1

POST /api/v1/esmc/encode Encode Protein Sequence With ESM C #

Documentation

📖
Documentation
https://forge.evolutionaryscale.ai

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/evolutionaryscale/refs/heads/main/openapi/evolutionaryscale-embeddings-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/evolutionaryscale/refs/heads/main/json-schema/evolutionaryscale-esm-protein-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/evolutionaryscale/refs/heads/main/json-schema/evolutionaryscale-generation-config-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/evolutionaryscale/refs/heads/main/json-schema/evolutionaryscale-logits-output-schema.json

Other Resources

🔗
SourceCode
https://github.com/Biohub/esm
🔗
JSONLD
https://raw.githubusercontent.com/api-evangelist/evolutionaryscale/refs/heads/main/json-ld/evolutionaryscale-context.jsonld

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/evolutionaryscale-embeddings-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

evolutionaryscale-embeddings-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: EvolutionaryScale Forge ESM3 Embeddings API
  description: 'Hosted inference API for the ESM3 multimodal protein language model from EvolutionaryScale. ESM3 reasons jointly across sequence, structure, and function tracks. The Forge API exposes generate, batch_generate, encode, decode, forward_and_sample, and logits operations across small (1.4B), medium (7B), and large (98B) parameter checkpoints. All requests authenticate with a Forge API token obtained from forge.evolutionaryscale.ai. This OpenAPI is reconstructed from the open-source `esm` Python SDK (Biohub/esm) which is the canonical client for the Forge service.

    '
  version: 2024-08-01
  contact:
    name: EvolutionaryScale Forge
    url: https://forge.evolutionaryscale.ai
  license:
    name: Cambrian Inference Clickthrough License Agreement
    url: https://www.evolutionaryscale.ai/policies/cambrian-inference-clickthrough-license-agreement
servers:
- url: https://forge.evolutionaryscale.ai
  description: EvolutionaryScale Forge Production
security:
- BearerAuth: []
tags:
- name: Embeddings
  description: Sequence-only tokenization and representation extraction.
paths:
  /api/v1/esmc/encode:
    post:
      summary: Encode Protein Sequence With ESM C
      description: 'Tokenize an `ESMProtein` (sequence track only) into an `ESMProteinTensor` ready for logits / embedding retrieval. ESM C operates over the sequence track exclusively.

        '
      operationId: esmcEncode
      tags:
      - Embeddings
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ESMCEncodeRequest'
            examples:
              SimpleEncode:
                $ref: '#/components/examples/SimpleEncodeExample'
      responses:
        '200':
          description: Sequence tensor for the supplied protein.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ESMProteinTensor'
        4XX:
          $ref: '#/components/responses/ErrorResponse'
components:
  schemas:
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            type:
              type: string
            message:
              type: string
            code:
              type: string
    ESMProteinTensor:
      type: object
      properties:
        sequence:
          type: array
          items:
            type: integer
    ESMProtein:
      type: object
      properties:
        sequence:
          type: string
          description: Amino acid sequence using one-letter codes.
          example: MKTAYIAKQRQISFVKAHFSRQLEERLGLIEVQ
    ESMCEncodeRequest:
      type: object
      required:
      - model
      - protein
      properties:
        model:
          type: string
          example: esmc-300m-2024-12
          enum:
          - esmc-300m-2024-12
          - esmc-600m-2024-12
          - esmc-6b-2024-12
        protein:
          $ref: '#/components/schemas/ESMProtein'
  examples:
    SimpleEncodeExample:
      summary: Encode a short protein sequence
      value:
        model: esmc-300m-2024-12
        protein:
          sequence: AAAAA
  responses:
    ErrorResponse:
      description: Error returned by the Forge API.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: Forge API token issued via forge.evolutionaryscale.ai.