Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Morph / Morph

Morph Compact

Context-pruning model that selects whole lines from an agent trace without rewriting them.

availableClosed weightsPrompt processing
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
5 of 16 specification fields collected
Prompt character limitNot collectedAwaiting source review
Component outputNot collectedAwaiting source review
Input billingSee ratesMorph API
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

Exact model-specific contract not established. Unknown is not unsupported.

Maximum input tokens
1,000,000 tokensSource for Maximum input tokens (opens in a new tab)

Provider describes a 1M context window; exact tokenizer boundary is not supplied.

Maximum output
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Parameters
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Release date
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Knowledge cutoff
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Reasoning
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Tool calling
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Structured output
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Streaming
SupportedSource for Streaming (opens in a new tab)

Chat Completions wrapper supports streaming; this is not asserted for every wrapper.

Batch processing
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Fine-tuning
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Context caching
Not collected

Exact model-specific contract not established. Unknown is not unsupported.

Output modalities
Retained text linesSource for Output modalities (opens in a new tab)
Generation controls
compression_ratio defaults to 0.5; preserve_recent to 2; system messages preserved unless requested; keepContext tags protect content.Source for Generation controls (opens in a new tab)

Access & pricing

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

API model ID
morph-compactor
Access
Documented wrapper for the same compaction model.
Regions
Exact serving-region and contractual residency inventory not established.
API endpoint
POST https://api.morphllm.com/v1/compactSource for API endpoint (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Usage pricingInput tokens1$0.201M tokens
Usage pricingRetained output tokens2$0.501M tokens

Rate conditions

  1. Compact product tariff; pricing uses morph-compact, docs morph-compactor. Exact alias resolution remains untested.
  2. Priced retained content; not a standard generated-answer estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Published terms distinguish tiers: PAYG content retention up to 90 days, paid up to 30 days, enterprise zero-retention by agreement. Training is off by default with support/debugging exceptions on ordinary tiers; enterprise terms exclude training. Self-hosted policies depend on configuration. Cache TTL is a separate question.

Read the service policy (opens in a new tab)
API model ID
morph-compactor
Access
Documented wrapper for the same compaction model.
Regions
Exact serving-region and contractual residency inventory not established.
API endpoint
POST https://api.morphllm.com/v1/chat/completionsSource for API endpoint (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Usage pricingInput tokens1$0.201M tokens
Usage pricingRetained output tokens2$0.501M tokens

Rate conditions

  1. Compact product tariff; pricing uses morph-compact, docs morph-compactor. Exact alias resolution remains untested.
  2. Priced retained content; not a standard generated-answer estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Published terms distinguish tiers: PAYG content retention up to 90 days, paid up to 30 days, enterprise zero-retention by agreement. Training is off by default with support/debugging exceptions on ordinary tiers; enterprise terms exclude training. Self-hosted policies depend on configuration. Cache TTL is a separate question.

Read the service policy (opens in a new tab)
API model ID
morph-compactor
Access
Documented wrapper for the same compaction model.
Regions
Exact serving-region and contractual residency inventory not established.
API endpoint
POST https://api.morphllm.com/v1/responsesSource for API endpoint (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Usage pricingInput tokens1$0.201M tokens
Usage pricingRetained output tokens2$0.501M tokens

Rate conditions

  1. Compact product tariff; pricing uses morph-compact, docs morph-compactor. Exact alias resolution remains untested.
  2. Priced retained content; not a standard generated-answer estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Published terms distinguish tiers: PAYG content retention up to 90 days, paid up to 30 days, enterprise zero-retention by agreement. Training is off by default with support/debugging exceptions on ordinary tiers; enterprise terms exclude training. Self-hosted policies depend on configuration. Cache TTL is a separate question.

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.

Morph API

morph-compactor
Not verified

No exact prompt-cache contract established for this specialized model.

How it works
Not collected

No exact prompt-cache contract established for this specialized model.

Minimum reusable input
Not collected

No exact prompt-cache contract established for this specialized model.

Lifetime & refresh
Not collected

No exact prompt-cache contract established for this specialized model.

How to enable it
Not collected

No exact prompt-cache contract established for this specialized model.

Usage fields
Not collected

No exact prompt-cache contract established for this specialized model.

Billing rules
Not collected

No exact prompt-cache contract established for this specialized model.

Limits & data boundaries
Not collected

No exact prompt-cache contract established for this specialized model.

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

Caching reviewed 15 Oct 2026

Morph API

morph-compactor
Not verified

No exact prompt-cache contract established for this specialized model.

How it works
Not collected

No exact prompt-cache contract established for this specialized model.

Minimum reusable input
Not collected

No exact prompt-cache contract established for this specialized model.

Lifetime & refresh
Not collected

No exact prompt-cache contract established for this specialized model.

How to enable it
Not collected

No exact prompt-cache contract established for this specialized model.

Usage fields
Not collected

No exact prompt-cache contract established for this specialized model.

Billing rules
Not collected

No exact prompt-cache contract established for this specialized model.

Limits & data boundaries
Not collected

No exact prompt-cache contract established for this specialized model.

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

Caching reviewed 15 Oct 2026

Morph API

morph-compactor
Not verified

No exact prompt-cache contract established for this specialized model.

How it works
Not collected

No exact prompt-cache contract established for this specialized model.

Minimum reusable input
Not collected

No exact prompt-cache contract established for this specialized model.

Lifetime & refresh
Not collected

No exact prompt-cache contract established for this specialized model.

How to enable it
Not collected

No exact prompt-cache contract established for this specialized model.

Usage fields
Not collected

No exact prompt-cache contract established for this specialized model.

Billing rules
Not collected

No exact prompt-cache contract established for this specialized model.

Limits & data boundaries
Not collected

No exact prompt-cache contract established for this specialized model.

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

Caching reviewed 15 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

Morph describes in-house specialized model training, retains rights to models and restricts weight extraction. These specialized offerings are distinct from its explicitly open-weight third-party hosting catalogue.

Classification evidence (opens in a new tab)

Sources reviewed