OpenCode and Cursor's Composer 2.5
OpenCode has introduced a new proxy for the Cursor API that allows users to make OpenAI-style requests. This proxy requires a Cursor subscription and authenticates requests using a Bearer token. Standard Agents, the team behind this development, emphasizes that users should still consider using Cursor's official API if it becomes available in the future.
- ▪The new proxy accepts familiar OpenAI-style requests and transforms them for Cursor's use.
- ▪A Cursor subscription is required to utilize this API, starting at $20 per month.
- ▪Requests must be authenticated with a Cursor API key, which is sent as a Bearer token.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Standardagents |
| Canonical URL | https://cursor-api.standardagents.ai |
| Publication time | Fri, 22 May 2026 18:25:26 +0000 |
| Retrieval time | 2026-05-22T18:32:02.758Z |
| Last seen | 2026-05-22T18:32:02.758Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | ToLFbAMlMuVs |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Cursor API Cursor Chat Docs GitHub — OpenAI-SDK compatible The missing Cursor API Cursor does not expose a standard inference API. This does. Open Cursor Chat Read the setup docs View as markdown Setup How to use it Cursor does not expose a standard inference API. This proxy accepts familiar OpenAI-style requests and transforms the formats into something Cursor can use. Use the OpenAI SDK, Vercel AI SDK, or any client that can set a custom base URL. Authenticate every request with your Cursor API key as a Bearer token. FAQ Questions people usually ask How much does it cost? You need a cursor subscription to use this api. Every request must be signed by your api key - cursor plans start at $20/month. We (StandardAgents) are not making any money on this.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Standardagents.
Discussion
0 commentsMore from Standardagents
