Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Resemble AI / Resemble detection and provenance

Resemble Agent Detection

Managed behavioral classifier for distinguishing human sessions from automated browser and computer-use agents.

Agent detection
availableClosed weightsAgent detection
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
5 of 18 specification fields collected
Signals analyzedBehavioral telemetrySee specification notes below
Analysis outputSession classificationSee specification notes below
Input billingSee ratesResemble AI
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Behavioral telemetrySource for Input modalities (opens in a new tab)
Output modalities
Session classificationSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Server-side behavioral model; exact scoring and parameter count not publicly detailed in the reviewed product descriptionSource for Architecture (opens in a new tab)
Languages
Not collected
Context caching
Not collected
Published price
$1 per 1,000 decided sessions after the free allowanceSource for Published price (opens in a new tab)
Usage metering
10,000 decided visits per team per UTC day are free; undecided visits are not billedSource for Usage metering (opens in a new tab)

API documentation gives a daily allowance; marketing describes the first 10,000 visitors without the reset detail.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Resemble AI

Provider source (opens in a new tab)
API model ID
Not collected

No public request selector pins this model version.

Access
Configure an integration for an allowed domain. Client telemetry uses a publishable integration key; management APIs use private API credentials.
Regions
Region and data residency not established for this access path.
API endpoint URL
https://app.resemble.ai/api/v2/agent_detection/telemetrySource for API endpoint URL (opens in a new tab)
Classification labels
human, agent, reviewSource for Classification labels (opens in a new tab)
Generation controls
Visitor classes: human, computer_use_agent, browser_automation, scripted_clientSource for Generation controls (opens in a new tab)
Request mode
Browser telemetry followed by a verdict event/callbackSource for Request mode (opens in a new tab)

Event delivery is not token streaming.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Detection / provenanceDecided sessions1$1.001,000 sessions

Rate conditions

  1. 10,000 decided visits per team per UTC day are free according to API documentation. One charge per decided visit; visits without a verdict are not billed.
Pricing source (opens in a new tab)

Data & enterprise terms

Docs say key categories/timing are collected, not typed text or page contents; raw IPs are hashed before storage. Browser/device signals and session identifiers are still collected. No universal legal-compliance or anonymity guarantee is inferred.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Resemble AI

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Provider documentation establishes the named native model or managed composition. Terms expressly reserve proprietary voice/detection technology and prohibit reverse engineering of models. Public-weight Chatterbox, original PerTh and Resemblyzer are excluded; enterprise on-premises delivery is not treated as a public weight release.

Classification evidence (opens in a new tab)

Sources reviewed