Hive Civilization Smsh Learned API

The smsh-learned API from Hive Civilization — 2 operation(s) for smsh-learned.

Operations 2

POST /v1/smsh/judge Score span importance via live judge #
POST /v1/smsh/learned_prune Learned token-importance pruning #

Documentation

Specifications

Other Resources

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/thehiveryiq-com-smsh-learned-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.

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

OpenAPI Specification

thehiveryiq-com-smsh-learned-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: HiveMorph v0.1 Smsh Learned API
  description: 'Polymorphic agent runtime — single shape (Merchant), single supermodel (W2 MERCHANT). Three gates: NEED + YIELD + CLEAN-MONEY.'
  version: 0.1.0
tags:
- name: smsh-learned
paths:
  /v1/smsh/judge:
    post:
      tags:
      - smsh-learned
      summary: Score span importance via live judge
      description: 'Split the input text into spans and ask a live frontier model to score each span 0-100 for how critical it is to the downstream answer. Tier2 call: $0.005 + judge model cost. Powered by smsh-judge-v1 prompt. LLMLingua-2 family.'
      operationId: smsh_judge_v1_smsh_judge_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/hivemorph__hive_smsh___judge_routes_patch__JudgeRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/smsh/learned_prune:
    post:
      tags:
      - smsh-learned
      summary: Learned token-importance pruning
      description: 'Run judge_span_importance then drop lowest-importance spans until target compression ratio is hit. Returns pruned text and full audit trail. Tier2 call: $0.005 + judge model cost. This is the smsh-v2 learned pruning layer — drop-in complement to smsh-std rule-based.'
      operationId: smsh_learned_prune_v1_smsh_learned_prune_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/LearnedPruneRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    hivemorph__hive_smsh___judge_routes_patch__JudgeRequest:
      properties:
        text:
          type: string
          title: Text
          description: The prompt text to judge for span importance.
        max_spans:
          type: integer
          maximum: 200.0
          minimum: 1.0
          title: Max Spans
          description: Maximum number of spans to segment into. Default 60.
          default: 60
        model:
          type: string
          title: Model
          description: 'Model alias for the judge. ''auto'' uses mistral-7b (cheapest). Options: mistral-7b, llama-3-8b, gemini-2-0-flash, gpt-4o-mini, qwen-2-5-72b, mixtral-8x7b, llama-3-70b, claude-3-5-haiku, claude-3-5-sonnet, gpt-4o, claude-3-opus.'
          default: auto
      type: object
      required:
      - text
      title: JudgeRequest
    LearnedPruneRequest:
      properties:
        text:
          type: string
          title: Text
          description: The prompt text to prune.
        target_ratio:
          type: number
          maximum: 0.99
          minimum: 0.1
          title: Target Ratio
          description: Target compression ratio (output tokens / input tokens). Default 0.5 = 50 percent of original.
          default: 0.5
        importance_floor:
          type: integer
          maximum: 100.0
          minimum: 0.0
          title: Importance Floor
          description: Spans with importance below this floor are eligible to drop. Default 30. Raise to 40-50 for higher fidelity.
          default: 30
        model:
          type: string
          title: Model
          description: Model alias for the judge. See /v1/smsh/judge for options.
          default: auto
      type: object
      required:
      - text
      title: LearnedPruneRequest