Composer Models by Cursor (Anysphere)
2 models2026Up to 1m ctxFrom $0.5/1M input
Capabilities
Function CallingAll models
Tool UseAll models
Code ExecutionAll models
Links
WebsiteAbout
Cursor's proprietary family of agentic coding models, designed for long-horizon software engineering inside the Cursor IDE. Each generation is trained with reinforcement learning on real engineering tasks and evaluated on CursorBench and Terminal-Bench. Generations: Composer (Oct 2025), Composer 1.5, Composer 2 (Mar 2026), Composer 2.5 (May 2026). All models are Cursor-native; not available as standalone third-party APIs.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
Composer 2.5Current
Use when the workload needs code, 1m context, and tool use.
2026-05code1m contexttool use
Composer 2Current
Use when the workload needs code, 200k context, and tool use.
2026-03code200k contexttool use
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Composer 2.5 | Use when the workload needs code, 1m context, and tool use. | 2026-05 | code1m contexttool use | Current |
| Composer 2 | Use when the workload needs code, 200k context, and tool use. | 2026-03 | code200k contexttool use | Current |
Release Timeline
2 release groups2026-05
1 current
Composer 2.5
Currentcode1m contexttool use
2026-03
1 current
Composer 2
Currentcode200k contexttool use
Specifications(2 models)
| Model | Released | Context | Fn Calling | Tool Use | Code Exec |
|---|---|---|---|---|---|
| Composer 2.5 | 2026-05 | 1m | Yes | Yes | Yes |
| Composer 2 | 2026-03 | 200k | Yes | Yes | Yes |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Composer 2.5 | Cursor | $0.5 | $2.5 | Serverless |
| Composer 2 | Cursor | $0.5 | $2.5 | Provisioned |
Popular comparisons in this family
- Claude Sonnet 4.6 vs Composer 2.53K
- Composer 2.5 vs Grok Build 0.13K
- Composer 2.5 vs Gemini 3.5 Flash1K
- Composer 2.5 vs DeepSeek V4 Pro1K
- Composer 2.5 vs GPT-5.51K
- Composer 2.5 vs Kimi K2.6995
- Claude Opus 4.7 vs Composer 2.5903
- Composer 2.5 vs Grok 4712
- Composer 2.5 vs Kimi K2.5612
- Composer 2.5 vs DeepSeek V4 Flash477
Comparisons
- GLM-5.2 vs Composer 2.5
- Claude Opus 4.8 vs Composer 2.5
- Composer 2.5 vs Kimi K2.7-Code
- Composer 2.5 vs GPT-5.5
- Composer 2.5 vs GPT-5.5 Pro
- Composer 2.5 vs Kimi K2.6
- Composer 2.5 vs Kimi K2.5
- Composer 2.5 vs Claude Opus 4.7
Frequently Asked Questions
- What is Composer used for?
- Composer is used for code, agent workflows and tool use, and code execution. The family description and listed model capabilities point to those workloads as the best fit.
- How does Composer compare to Claude 3?
- Composer by Cursor (Anysphere) is strongest where you need code, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. Composer has 2 listed variants and reaches up to 1m context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which Composer model should I use?
- For the lowest listed input price, start with Composer 2.5 through Cursor at $0.5/1M input tokens. For the most capable/latest local choice, evaluate Composer 2.5 with 1m context and tool use and function calling.