Cursor
Researched 94d agoPlatformTier 2Cursor offers 2 tracked models (2 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 5 workload areas across 2 tracked models; last verified 2026-06-30.
Use it for
- Teams comparing token and batch pricing across this provider's models
- Operators routing coding, rag, and agents workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
Tracked models
2
Models available through this provider
Priced output routes
2
Models with output token pricing tracked
Cheapest output
$2.50
Composer 2.5 on this route
Batch-ready models
0
No batch pricing tracked
Latest model release
2026-05-18
137d since newest release
Freshness
2026-06-30
Researched 94d ago
Information
Cursor is an AI-powered coding platform and IDE from Anysphere, focused on agentic software engineering workflows.
Read more ->Where this host wins
- Coding: 2 tracked models with SWE-bench / HumanEval-style scores.
- RAG: 2 tracked models with ruler / needle retrieval benchmarks.
- Agentic: 2 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 2 tracked models with context-token or InfiniteBench-class signal.
Getting started
Platform Overview
Cursor provides a code-first development environment with integrated AI coding models, context-aware agentic workflows, and plan-based token usage for built-in model access. It is not primarily a model provider API, so model access is typically via the Cursor platform.
Available Models(2)
View all →| Model | Input (per 1M) | Output (per 1M) | Type |
|---|---|---|---|
| Composer 2.5 | $0.50 | $2.50 | Serverless |
| Composer 2 | $0.5 | $2.5 |