---
type: "post"
id: "glm-5-3-and-glm-5-3-flash-454abe"
slug: "glm-5-3-and-glm-5-3-flash-454abe"
title: "GLM 5.3 and GLM 5.3 Flash are now available in Cursor!"
description: "Thesis: Cursor's listing of GLM 5.3 Flash makes a long-context, tool-enabled model from Z.ai selectable inside its agent environment."
retrieval_nugget: "Thesis: Cursor's listing of GLM 5.3 Flash makes a long-context, tool-enabled model from Z.ai selectable inside its agent environment."
published_at: "2026-10-01"
updated_at: "2026-10-01"
record_date: "2026-10-01"
date_kind: "published_at"
topics: []
source_urls: ["https://cursor.com/docs/models/glm-5-3-flash"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:glm-5-3-and-glm-5-3-flash-454abe"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:dd75ee59de80cd8903c70497e1e89d6456e2ce24e0221926cd524bf731c24781","reviewed_at":"2026-10-01T23:02:40.573Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Cursor's listing of GLM 5.3 Flash makes a long-context, tool-enabled model from Z.ai selectable inside its agent environment.","observed_facts":[{"text":"Cursor's documentation says GLM 5.3 Flash can be added from Cursor Settings > Models.","source_urls":["https://cursor.com/docs/models/glm-5-3-flash"]},{"text":"The page specifies a 1M-token context window, image inputs, and Low, High, and Max reasoning levels, with High as the default.","source_urls":["https://cursor.com/docs/models/glm-5-3-flash"]},{"text":"The listed price is $0.15 per million input tokens and $0.50 per million output tokens, flat across the context window.","source_urls":["https://cursor.com/docs/models/glm-5-3-flash"]}],"mechanism":"Cursor's model picker exposes Flash with image inputs, a 1M-token context window, and Low, High, and Max reasoning levels, with High as the default. Cursor also states it can use all agent tools, including file search, editing, web access, shell commands, and browser control.","why_now":"The model documentation now provides an actionable configuration path and pricing, so developers can assess it as an option within an existing agent workflow rather than as a model announcement alone.","implications":["Teams can evaluate a model with a stated 1M-token context window and agent-tool access without leaving Cursor's model selection flow.","The published pricing gives teams a basis for assessing input and output costs, but not a performance comparison."],"evidence_boundary":"The supplied page documents Flash, but does not establish comparative speed or quality through benchmarks, nor does it independently verify the separate GLM 5.3 model's availability.","watch_conditions":["Watch for Cursor or Z.ai to publish comparable task-quality and latency results, or clarify the separate GLM 5.3 model's availability and terms."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this item, so this begins a distinct analytical record focused on Cursor's documented GLM 5.3 Flash integration."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/glm-5-3-and-glm-5-3-flash-454abe/","markdown":"https://newruntime.com/posts/glm-5-3-and-glm-5-3-flash-454abe.md","json":"https://newruntime.com/posts/glm-5-3-and-glm-5-3-flash-454abe.json"}
---

# GLM 5.3 and GLM 5.3 Flash are now available in Cursor!

## Retrieval answer

Thesis: Cursor's listing of GLM 5.3 Flash makes a long-context, tool-enabled model from Z.ai selectable inside its agent environment.

Thesis: Cursor's listing of GLM 5.3 Flash makes a long-context, tool-enabled model from Z.ai selectable inside its agent environment. The documentation identifies GLM 5.3 Flash as the smaller, faster member of Z.ai's GLM 5.3 family and says it can be added from Cursor Settings > Models.

Mechanism: Cursor's model picker exposes Flash with image inputs, a 1M-token context window, and Low, High, and Max reasoning levels, with High as the default. Cursor also states it can use all agent tools, including file search, editing, web access, shell commands, and browser control. Why now: The model documentation now provides an actionable configuration path and pricing, so developers can assess it as an option within an existing agent workflow rather than as a model announcement alone.

First implication: Teams can evaluate a model with a stated 1M-token context window and agent-tool access without leaving Cursor's model selection flow. The page lists $0.15 per million input tokens and $0.50 per million output tokens, with flat pricing across the context window and no long-context surcharge. Evidence boundary: The supplied page documents Flash, but does not establish comparative speed or quality through benchmarks, nor does it independently verify the separate GLM 5.3 model's availability. First watch condition: Watch for Cursor or Z.ai to publish comparable task-quality and latency results, or clarify the separate GLM 5.3 model's availability and terms.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)