Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Cursor / Composer

Composer 2.5

Current documented Cursor agent model for sustained coding work, with standard and fast serving tiers.

availableClosed weightsCoding
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
9 of 17 specification fields collected
Context window200K200,000 tokens
Maximum outputNot collectedAwaiting source review
Input / 1M tokens$0.50Cursor Composer 2.5 · standard
Output / 1M tokens$2.50USD · observed 15 Oct 2026

Specifications

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

Context / input limit
200,000 tokensSource for Context / input limit (opens in a new tab)

Published 200k context window. No separate maximum output count or expanded Max context is stated.

Maximum input tokens
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Maximum output
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Parameters
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Tool calling
SupportedSource for Tool calling (opens in a new tab)

Trained for the Cursor agent tool harness. Not a claim of arbitrary OpenAI-compatible function-call schemas.

Structured output
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Streaming
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Batch processing
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Fine-tuning
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

Context caching
SupportedSource for Context caching (opens in a new tab)

Cache-read billing is published; TTL and minimum prefix are not established.

Knowledge cutoff
Not collected

Exact version-specific model contract not established. Product capabilities do not automatically establish a standalone inference API feature.

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

Native image support is not established here; agent tools can handle media without proving model-native generation/vision.

Base model
Moonshot Kimi K2.5Source for Base model (opens in a new tab)

Same open-weight starting checkpoint as Composer 2, with a separate Cursor-trained derivative.

Published training method
Targeted RL with textual feedback and on-policy distillation, expanded synthetic tasks, and revised optimization infrastructure.Source for Published training method (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.

Cursor Composer 2.5 · standard

Provider source (opens in a new tab)
API model ID
composer-2.5

Published product model ID. Exact Cloud Agents mode parameters must be discovered for the account; no raw inference API is implied.

Access
Standard serving tier in Cursor. Paid-plan usage pool and account policies apply.
Regions
Default model-specific processing region not established. Enterprise US-only residency can cover Composer when configured; external integrations have separate boundaries.
API endpoint URL
POST https://api.cursor.com/v1/agents; discover supported models and parameters with GET /v1/models.Source for API endpoint URL (opens in a new tab)

Cloud agent workflow API, not a standalone model-inference or chat-completions endpoint.

Authentication
User or service-account API key. HTTP Basic with key as username and empty password, or Bearer token.Source for Authentication (opens in a new tab)
Output formats
Agent run/task state, messages and artifacts. The API includes an event-stream route; that does not establish a standalone model token-stream interface.Source for Output formats (opens in a new tab)
INPUT / 1M TOKENS$0.50
OUTPUT / 1M TOKENS$2.50

standard Composer 2.5 tier; Fast is the product default. Published additional-usage token rates beyond plan allowances. Model-token subtotal only, not a complete agent-run or subscription bill. Cache-write fee/TTL not established. Cursor's third-party Token Rate does not apply to Composer. Cached input price: $0.20 / 1M tokens (base tier).

USD · observed 15 Oct 2026 · Pricing evidence (opens in a new tab)

Data & enterprise terms

With Privacy Mode enabled, code is not used for training by Cursor or model providers. Custom-model inference providers may process it. Cloud Agents store encrypted repository copies during execution, with deletion after completion described by the provider. These claims do not establish unconditional zero retention for every feature or account.

Read the service policy (opens in a new tab)

Cursor Composer 2.5 · fast

Provider source (opens in a new tab)
API model ID
composer-2.5

Published product model ID. Exact Cloud Agents mode parameters must be discovered for the account; no raw inference API is implied.

Access
Default fast tier in Cursor. Paid-plan usage pool and account policies apply.
Regions
Default model-specific processing region not established. Enterprise US-only residency can cover Composer when configured; external integrations have separate boundaries.
API endpoint URL
POST https://api.cursor.com/v1/agents; discover supported models and parameters with GET /v1/models.Source for API endpoint URL (opens in a new tab)

Cloud agent workflow API, not a standalone model-inference or chat-completions endpoint.

Authentication
User or service-account API key. HTTP Basic with key as username and empty password, or Bearer token.Source for Authentication (opens in a new tab)
Output formats
Agent run/task state, messages and artifacts. The API includes an event-stream route; that does not establish a standalone model token-stream interface.Source for Output formats (opens in a new tab)
INPUT / 1M TOKENS$3.00
OUTPUT / 1M TOKENS$15.00

fast Composer 2.5 tier; Fast is the product default. Published additional-usage token rates beyond plan allowances. Model-token subtotal only, not a complete agent-run or subscription bill. Cache-write fee/TTL not established. Cursor's third-party Token Rate does not apply to Composer. Cached input price: $0.50 / 1M tokens (base tier).

USD · observed 15 Oct 2026 · Pricing evidence (opens in a new tab)

Data & enterprise terms

With Privacy Mode enabled, code is not used for training by Cursor or model providers. Custom-model inference providers may process it. Cloud Agents store encrypted repository copies during execution, with deletion after completion described by the provider. These claims do not establish unconditional zero retention for every feature or account.

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.

Cursor Composer 2.5 · standard

composer-2.5
Documented
Support evidence (opens in a new tab)
How it works
Published cache-read token pricingSource for How it works (opens in a new tab)
Minimum reusable input
Not collected

Minimum cacheable prefix not published in the model card.

Lifetime & refresh
Not collected

Cache TTL not published.

How to enable it
Not collected

Exact cache creation/matching controls not established.

Usage fields
Cached input is billed separately from uncached input.Source for Usage fields (opens in a new tab)
Billing rules
$0.2 per million cached input tokens for standard; cache-write column is a dash, not a zero-price guarantee.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Applies to this serving tier. Agent orchestration, subscription allowances and tool charges are separate.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.20 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. standard Composer 2.5 tier; Fast is the product default. Published additional-usage token rates beyond plan allowances. Model-token subtotal only, not a complete agent-run or subscription bill. Cache-write fee/TTL not established. Cursor's third-party Token Rate does not apply to Composer.

Observed 15 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 15 Oct 2026

Cursor Composer 2.5 · fast

composer-2.5
Documented
Support evidence (opens in a new tab)
How it works
Published cache-read token pricingSource for How it works (opens in a new tab)
Minimum reusable input
Not collected

Minimum cacheable prefix not published in the model card.

Lifetime & refresh
Not collected

Cache TTL not published.

How to enable it
Not collected

Exact cache creation/matching controls not established.

Usage fields
Cached input is billed separately from uncached input.Source for Usage fields (opens in a new tab)
Billing rules
$0.5 per million cached input tokens for fast; cache-write column is a dash, not a zero-price guarantee.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Applies to this serving tier. Agent orchestration, subscription allowances and tool charges are separate.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.50 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. fast Composer 2.5 tier; Fast is the product default. Published additional-usage token rates beyond plan allowances. Model-token subtotal only, not a complete agent-run or subscription bill. Cache-write fee/TTL not established. Cursor's third-party Token Rate does not apply to Composer.

Observed 15 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

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

Cursor describes its own post-trained coding model, distributed through its product. Composer 2 is described among proprietary models in its technical report. Private classification for other Composer generations is inferred from this product/research lineage; their exact weight license is not published in the reviewed sources. Public Kimi K2.5 base weights do not constitute a release of the Composer derivative.

Classification evidence (opens in a new tab)

Lifecycle dates

Model release announced18 May 2026Source (opens in a new tab)

Sources reviewed