How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

APIClaw auto router API

The auto router API from APIClaw — 8 operation(s) for auto router.

APIClaw auto router API is one of 113 APIs that APIClaw publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include auto router. The published artifact set on APIs.io includes an OpenAPI specification.

This API exposes 8 operations across 8 paths, and defines 17 schemas. It is described by OpenAPI 3.2.0, at version 1.102.1.

Requests are made against the base URL https://apiclaw.biz/v1/.

8 operations 8 paths 17 schemas 6 GET2 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.102.1
Base URL
https://apiclaw.biz/v1/
Authentication
API Key
Resource Areas
1

Authentication & Security 1

APIClaw auto router API declares 1 security scheme for authenticating requests. An API key is passed in the header as x-litellm-api-key (APIKeyHeader).

  • APIKeyHeader — Bearer token

Paths & Operations 8

Across 8 paths, the API surfaces 8 operations — 6 GET, 2 POST. Each is listed below with its method, path, parameters, and response codes.

auto router 8
GET
/public/complexity_router/scorer_defaults
Get Complexity Scorer Defaults
get_complexity_scorer_defaults_public_complexity_router_scorer_defaults_get → 200
GET
/public/autorouter_presets
Get Public Autorouter Presets
get_public_autorouter_presets_public_autorouter_presets_get → 200
GET
/auto_router/benchmarks
Get Auto Router Benchmarks
get_auto_router_benchmarks_auto_router_benchmarks_get 3 params → 200422
GET
/auto_router/session
Get Auto Router Session
get_auto_router_session_auto_router_session_get 1 param → 200422
POST
/auto_router/shadow_eval/start
Start Shadow Eval
start_shadow_eval_auto_router_shadow_eval_start_post body → 201422
GET
/auto_router/shadow_eval
List Shadow Eval Jobs
list_shadow_eval_jobs_auto_router_shadow_eval_get 3 params → 200422
GET
/auto_router/shadow_eval/{job_id}
Get Shadow Eval Job
get_shadow_eval_job_auto_router_shadow_eval__job_id__get 1 param → 200422
POST
/auto_router/shadow_eval/{job_id}/stop
Stop Shadow Eval Job
stop_shadow_eval_job_auto_router_shadow_eval__job_id__stop_post 1 param → 200422

Schemas 17

The contract defines 17 schemas that model the data the API accepts and returns. The most detailed are ShadowEvalJobResponse (18 properties), AutoRouterBenchmarkGroup (15 properties), StartShadowEvalRequest (12 properties), AutoRouterBenchmarkTotals (12 properties). Each schema is shown below with its type and property counts.

ShadowEvalJobResponse
object
A shadow-eval job over one or more targets, each with its own budget and stop state; status is derived from stoppedby, the targets' stop and budget state, and…
18 properties 9 required
StartShadowEvalRequest
object
Start duplicating one or more targets' traffic for blind comparison against an auto-router. A target is a virtual key, a team, or a user; each becomes its own…
12 properties 1 required
ComplexityScorerDefaults
object
The complexity router's shipped heuristic scorer defaults. The dashboard prefills its Advanced scoring controls from these rather than keeping its own copy, so…
3 properties 3 required
AutoRouterBenchmarkTotals
object
Session-shape and savings aggregates over auto-routed traffic in the window.
12 properties 12 required
AutoRouterPresetRecord
object
One auto-router preset as served to the dashboard's template picker.
3 properties 3 required
ShadowEvalJobTargetResponse
object
One target a job shadows (a key, team, or user), with its own budget and stop state.
10 properties 3 required
AutoRouterBenchmarksResponse
object
Benchmarks for the auto-router dashboard, aggregated from the per-session rollup.
5 properties 5 required
AutoRouterCacheStats
object
Prompt-caching behaviour of auto-routed turns, bucketed by what the router did. Every in-order turn falls in exactly one bucket: the session stayed on the same…
11 properties 11 required
AutoRouterPresetConfig
object
The complexityrouterconfig a preset prefills. Only tiers is validated, because every dashboard consumer dereferences it; everything else passes through verbati…
1 property 1 required
ShadowEvalResult
object
Stratified results of a shadow-eval job's verdicts so far.
11 properties 4 required
AutoRouterCacheBucket
object
One prompt-caching bucket of turns, with how often those turns hit the cache.
3 properties 3 required
AutoRouterBenchmarkGroup
object
One auto-router's slice of the benchmarks.
15 properties 14 required
ValidationError
object
5 properties 3 required
AutoRouterSessionResponse
object
One auto-routed session as its own key sees it: what the last turn ran on, and what the session cost against the router's savings baseline (the priciest model…
10 properties 10 required
AutoRouterPresetTiers
object
Exactly the four built-in tiers the dashboard's preset prefill can apply. extra="forbid" on purpose: a tier name this dashboard cannot apply would grey out or…
4 properties 4 required
ShadowEvalSlice
object
Judge outcomes for one slice of a job's verdicts: a router tier, one of the models that served the real arm, or one scoped target (embedded on that target's ow…
9 properties 6 required
HTTPValidationError
object
1 property

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

apiclaw-auto-router-api-openapi.yml Raw ↑

Other APIs APIClaw publishes across the network.

APIClaw A2a API
APIClaw A2a Registration API
APIClaw Access Groups API
APIClaw Adaptive Router API
APIClaw Agent Management API
APIClaw Agents API
APIClaw Anthropic Passthrough API
APIClaw Anthropic Skills API
APIClaw APIClaw Admin Overview API
APIClaw APIClaw Announcements API
APIClaw APIClaw Billing API
Where this information came from

This is an independent, third-party profile of APIClaw auto router API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.