Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Milo / Family scheduling

Milo Scheduling RFT

Historical private model trained to turn family scheduling requests into consistent calendar and list updates.

Language models (LLMs)
historicalClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 16 Oct 2026
4 of 18 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedMilo historical family assistant
Output billingNot collectedNo inferred price

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

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Maximum input tokens
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Maximum output
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Parameters
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Release date
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Knowledge cutoff
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Tool calling
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Structured output
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Streaming
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Batch processing
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Fine-tuning
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Reasoning
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Context caching
Not collected

No reviewed model-specific inference contract. Unknown does not mean unsupported.

Input modalities
TextSource for Input modalities (opens in a new tab)

The application also handled newsletters and email, but native multimodal model input is not established.

Output modalities
TextSource for Output modalities (opens in a new tab)
Base model
Not collected

GPT-4o prompting and SFT are cited as earlier approaches. The exact base of the RFT model is not named.

Architecture
Reinforcement fine-tuning with grading for item completeness, classification, duplicate detection and scheduling conflicts.Source for Architecture (opens in a new tab)
Output formats
Calendar-event and list-item objects, including recurrence, update and deletion decisions.Source for Output formats (opens in a new tab)

No public JSON schema, native function-calling API or selector is established.

Access & pricing

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

Milo historical family assistant

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

No public model API selector contract established.

Access
Historical private RFT experiment; current inference access unverified. Official investor profile marks company inactive.
Regions
Model-specific processing and deployment regions not established.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

No current model-specific data policy verified. The unavailable provider homepage and inactive investor profile do not authorize borrowing policies from unrelated Milo companies.

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.

Milo historical family assistant

Not verified

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

How it works
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

Minimum reusable input
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

Lifetime & refresh
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

How to enable it
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

Usage fields
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

Billing rules
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

Limits & data boundaries
Not collected

No reviewed inference-cache contract. Project history, calendar state and service-data retention do not establish prompt caching.

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

Caching reviewed 16 Oct 2026

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

Official OpenAI case study documents Milo reinforcement fine-tuning for scheduling tasks. The private derivative is not exposed as public weights or a standalone checkpoint selector.

Classification evidence (opens in a new tab)

Sources reviewed