Hive Civilization Arb Compute API

The arb-compute API from Hive Civilization — 3 operation(s) for arb-compute.

Documentation GitHub OpenAPI

Operations 3

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /v1/arb/compute/route Route an LLM call to the cheapest fit model · Route a single LLM call #

Ask an LLM

“How do I send a prompt to the cheapest model that still meets my quality bar?”

“Can I force a quality tier instead of letting the shape decide?”

Tell an agent

Route prompt {prompt} for shape {shape}.

Route {prompt} as a {shape} call at tier {quality_tier}.

GET /v1/arb/compute/savings See cumulative model routing savings · Cumulative savings dashboard #

Ask an LLM

“How much money has cost-based model routing saved so far?”

“How many routed calls failed because every candidate model was exhausted?”

Tell an agent

Show routing savings.

Get total spend and savings from routed calls.

GET /v1/arb/compute/catalog List routable models and their costs · Model catalog with costs #

Ask an LLM

“Which models can calls be routed to, and what does each cost per 1k tokens?”

“What quality tier is each model in?”

Tell an agent

List the model catalog with costs.

Show models grouped by quality tier, cheapest first.

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:thehiveryiq-com-arb-compute-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

openapi: 3.2.0
info:
  title: HiveMorph v0.1 Arb Compute API
  description: 'Polymorphic agent runtime — single shape (Merchant), single supermodel (W2 MERCHANT). Three gates: NEED + YIELD + CLEAN-MONEY.'
  version: 0.1.0
tags:
- name: arb-compute
paths:
  /v1/arb/compute/route:
    post:
      tags:
      - arb-compute
      summary: Route a single LLM call
      description: 'Route a single LLM call to the cheapest model that meets the quality bar.


        - **shape**: HiveMorph shape name — determines default quality tier

        - **prompt**: user message sent to the model

        - **quality_tier**: optional override (T0_CHEAP, T1_STANDARD, T2_HIGH)

        - **system_prompt**: optional system message


        Returns the chosen model, LLM response, per-call cost, and savings versus

        the baseline (most expensive T2 model, gpt_5_5).'
      operationId: route_call_v1_arb_compute_route_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/hivemorph__hive_arb__compute_routes__RouteRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RouteResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/arb/compute/savings:
    get:
      tags:
      - arb-compute
      summary: Cumulative savings dashboard
      description: 'Return cumulative cost-savings accounting for all calls routed through

        this instance since last restart.


        - **calls_routed**: total route attempts

        - **calls_failed**: calls where all candidates were exhausted

        - **total_cost_usd**: actual spend across all successful calls

        - **total_savings_usd**: amount saved vs routing everything to the baseline

        - **avg_cost_reduction_pct**: average percentage cost reduction

        - **baseline_model**: model used as savings reference (gpt_5_5)'
      operationId: get_savings_v1_arb_compute_savings_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SavingsResponse'
  /v1/arb/compute/catalog:
    get:
      tags:
      - arb-compute
      summary: Model catalog with costs
      description: 'Return the full model catalog: all models with their per-token costs,

        quality tiers, providers, and blended cost per 1k tokens.


        Also returns a `tiers` map grouping model IDs by tier, ordered cheapest first.'
      operationId: get_catalog_v1_arb_compute_catalog_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CatalogResponse'
components:
  schemas:
    ModelCatalogEntry:
      properties:
        model_id:
          type: string
          title: Model Id
        display_name:
          type: string
          title: Display Name
        quality_tier:
          type: string
          title: Quality Tier
        cost_per_1k_input:
          type: number
          title: Cost Per 1K Input
        cost_per_1k_output:
          type: number
          title: Cost Per 1K Output
        blended_cost_per_1k:
          type: number
          title: Blended Cost Per 1K
        provider:
          type: string
          title: Provider
        notes:
          type: string
          title: Notes
      type: object
      required:
      - model_id
      - display_name
      - quality_tier
      - cost_per_1k_input
      - cost_per_1k_output
      - blended_cost_per_1k
      - provider
      - notes
      title: ModelCatalogEntry
    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
    SavingsResponse:
      properties:
        calls_routed:
          type: integer
          title: Calls Routed
        calls_failed:
          type: integer
          title: Calls Failed
        total_cost_usd:
          type: number
          title: Total Cost Usd
        total_savings_usd:
          type: number
          title: Total Savings Usd
        avg_cost_reduction_pct:
          type: number
          title: Avg Cost Reduction Pct
        baseline_model:
          type: string
          title: Baseline Model
      type: object
      required:
      - calls_routed
      - calls_failed
      - total_cost_usd
      - total_savings_usd
      - avg_cost_reduction_pct
      - baseline_model
      title: SavingsResponse
    RouteResponse:
      properties:
        chosen_model:
          type: string
          title: Chosen Model
        response:
          additionalProperties: true
          type: object
          title: Response
        cost_usd:
          type: number
          title: Cost Usd
        savings_vs_baseline:
          type: number
          title: Savings Vs Baseline
        tier:
          type: string
          title: Tier
        attempts:
          items:
            type: string
          type: array
          title: Attempts
        latency_ms:
          type: number
          title: Latency Ms
        input_tokens:
          type: integer
          title: Input Tokens
        output_tokens:
          type: integer
          title: Output Tokens
        shape:
          type: string
          title: Shape
      type: object
      required:
      - chosen_model
      - response
      - cost_usd
      - savings_vs_baseline
      - tier
      - attempts
      - latency_ms
      - input_tokens
      - output_tokens
      - shape
      title: RouteResponse
    CatalogResponse:
      properties:
        count:
          type: integer
          title: Count
        models:
          items:
            $ref: '#/components/schemas/ModelCatalogEntry'
          type: array
          title: Models
        tiers:
          additionalProperties:
            items:
              type: string
            type: array
          type: object
          title: Tiers
      type: object
      required:
      - count
      - models
      - tiers
      title: CatalogResponse
    hivemorph__hive_arb__compute_routes__RouteRequest:
      properties:
        shape:
          type: string
          title: Shape
          description: HiveMorph shape name (e.g. 'merchant', 'attestor', 'guardian')
          examples:
          - merchant
        prompt:
          type: string
          title: Prompt
          description: User prompt to send to the LLM
          examples:
          - Classify this transaction as legitimate or suspicious.
        quality_tier:
          anyOf:
          - type: string
          - type: 'null'
          title: Quality Tier
          description: 'Override quality tier: T0_CHEAP | T1_STANDARD | T2_HIGH. If omitted, inferred from shape.'
          examples:
          - T1_STANDARD
        system_prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: System Prompt
          description: Optional system message prepended to the conversation
        extra_params:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Extra Params
          description: Additional gateway parameters (temperature, max_tokens, etc.)
      type: object
      required:
      - shape
      - prompt
      title: RouteRequest
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
x-provenance:
  method: harvested
  publisher: Hive Civilization
  source: https://receipts.thehiveryiq.com/openapi.json
  note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
    stamped by stamp-openapi-provenance.py (roadmap#793)

Hive Civilization Arb Compute API

Operations 3

Documentation

Specifications

Other Resources

Work with this as data

MCP server

Tools for apis

Call it yourself

Get an API key

OpenAPI Specification