Cursor Adds GLM 5.3 and GLM 5.3 Flash to Its Model Picker
Cursor lists Z.ai's GLM 5.3 and GLM 5.3 Flash in its model picker. GLM 5.3 is for higher-quality work at $1.4 per million input tokens and $4.4 per million output tokens; Flash is smaller and faster at $0.15 and $0.5. Both support Cursor's agent tools and are third-party models: billed from prepaid credit on The X Subscription, and from the Other Models pool on legacy Cursor plans.
Cursor has added GLM 5.3 and GLM 5.3 Flash to the models available in Cursor. To add either model to the model picker, Cursor's model pages direct users to Cursor Settings > Models. (Cursor announcement; GLM 5.3 documentation; GLM 5.3 Flash documentation)
Both models support a 1M-token context window and have access to all of Cursor's agent tools. Each model supports three reasoning levels, Low, High, and Max, with High as the default. (Cursor's GLM 5.3 documentation; Cursor's GLM 5.3 Flash documentation)
Key Takeaways
- Two models: Cursor added Z.ai's open-weight GLM 5.3 and GLM 5.3 Flash; add either from Cursor Settings > Models.
- Same context and reasoning controls: both support a 1M-token context window and Low, High, and Max reasoning, with High as the default.
- GLM 5.3 for harder tasks: Cursor recommends GLM 5.3 for higher quality on harder tasks; Flash is the smaller, faster option and supports image inputs (Cursor's GLM 5.3 Flash documentation).
- Prices per million tokens: GLM 5.3 costs $1.4 input, $0.26 cache read, and $4.4 output, the same as GLM 5.2; Flash costs $0.15, $0.029, and $0.5 (Cursor models and pricing).
- Billing: both are third-party models, billed from prepaid credit on The X Subscription and from the Other Models pool on legacy Cursor plans, with flat pricing across the full context window.
Which Model to Choose
Cursor describes GLM 5.3 as Z.ai's latest open-weight coding model and the successor to GLM 5.2. GLM 5.3 Flash is the smaller, faster option in the same family. Cursor recommends GLM 5.3 for higher quality on harder tasks. (Cursor's GLM 5.3 documentation; Cursor's GLM 5.3 Flash documentation)
Both model pages describe access to all Cursor agent tools. The models are served by Cursor through its inference partners. (Cursor's GLM 5.3 documentation; Cursor's GLM 5.3 Flash documentation)
Usage and Pricing
As of October 2026, Cursor sells The X Subscription, and third-party models are not part of its included weekly pool: on Premium and above they are billed at API list price from prepaid credit, and Plus and Free do not include them. Both GLM 5.3 models are third-party models. On legacy Cursor plans (Pro, Pro Plus, Ultra, and Teams) they draw from the Other Models pool, charged at each model's API price; the Start plan does not include that pool. (Cursor's GLM 5.3 documentation; Cursor models and pricing; Cursor's legacy plans page)
| Model (per million tokens) | Input | Cache write | Cache read | Output |
|---|---|---|---|---|
| GLM 5.3 | $1.4 | None | $0.26 | $4.4 |
| GLM 5.3 Flash | $0.15 | None | $0.029 | $0.5 |
Cursor's models and pricing page lists GLM 5.3 at $1.4 per million input tokens, $0.26 per million cache-read tokens, and $4.4 per million output tokens, the same per-token rates as GLM 5.2. It lists GLM 5.3 Flash at $0.15 input, $0.029 cache read, and $0.5 output. Both model pages say pricing is flat across the full context window, with no long-context surcharge and no separate cache-write fee. (Cursor models and pricing; Cursor's GLM 5.3 documentation; Cursor's GLM 5.3 Flash documentation)
At those rates, GLM 5.3 Flash costs about a ninth of GLM 5.3 per output token, so it suits high-volume edits where speed matters more than depth. Before a large run, check your prepaid credit (The X Subscription) or your Other Models pool (legacy plans).
Bottom Line
Start with GLM 5.3 Flash for quick, cheap edits and switch to GLM 5.3 when a task needs more reasoning. For a quick comparison, pick a task from your backlog, run it with both models, and check your remaining credit or pool before using either for longer work.
Sources
- Cursor, "GLM 5.3"
- Cursor, "GLM 5.3 Flash"
- Cursor, "Models & Pricing" (per-token prices and plans; checked October 15, 2026)
- Cursor, "Legacy Cursor plans" (usage pools on Pro, Pro Plus, Ultra, Teams and Start; checked October 15, 2026)
- Cursor, "GLM 5.3 and GLM 5.3 Flash are now available in Cursor"
Read next
Related coverage- Cursor
Cursor Adds GPT-5.6 Sol, Terra, and Luna
Cursor added OpenAI's GPT-5.6 Sol, Terra, and Luna on July 9, 2026, and as of October 2026 they are still the newest OpenAI models Cursor lists. Cursor offers no GPT-6 model, and OpenAI has proposed ending Cursor's direct access to its models on November 12, 2026. Sol scores 67.2% on CursorBench 3.2.
- Cursor
Cursor Router: Auto Balance, Auto Intelligence, and Cost Modes
Cursor Router is the routing system behind Auto, and Cursor documents it as available only on Teams and Enterprise plans. Open the model picker, select Auto, and pick Cost, Balance, or Intelligence under Optimize For. Cost mode bills as a Cursor-model request from the weekly pool; Balance and Intelligence bill at the list price of whichever model the request is routed to.
- Cursor
Cursor Welcomes Firetiger to Connect Coding Agents to Production
Cursor says the Firetiger team joined Cursor to bring production-operation agents closer to coding agents. Firetiger's agents monitor rollouts, catch regressions, investigate incidents, and pass findings back to coding agents. The Change Monitors the announcement called coming soon shipped on September 23, 2026 as Cursor Rollouts, on Teams and Enterprise plans.
- OpenAI
OpenAI Brings GPT-5.6 Model Family to Kiro for Spec-Driven Coding
OpenAI says the GPT-5.6 model family, including Sol, Terra, and Luna, is now available in Kiro. The OpenAI-AWS update targets structured, long-running software work and reports roughly an 82% cost reduction per successful Terminal-Bench 2.1 task for GPT-5.6 Terra in Kiro's spec-driven environment.
Frequently Asked Questions
How do I add GLM 5.3 in Cursor?
Open Cursor Settings, go to Models, and add GLM 5.3 or GLM 5.3 Flash to the model picker. Cursor's models and pricing page marks both as hidden by default, so add them before you pick them. Each supports Low, High, and Max reasoning, with High as the default.
What is the difference between GLM 5.3 and GLM 5.3 Flash?
GLM 5.3 Flash is the smaller, faster member of the family, and its page lists image inputs. Cursor recommends GLM 5.3 for higher quality on harder tasks. GLM 5.3 costs $1.4 per million input tokens and $4.4 per million output tokens, against $0.15 and $0.5 for Flash.
Do GLM 5.3 models support Cursor's agent tools?
Yes. Cursor's documentation says both GLM 5.3 and GLM 5.3 Flash have access to all agent tools when used with Cursor. Both also support a 1M-token context window, and Cursor serves these open-weight Z.ai models through its inference partners.
Which Cursor usage pool do these models use?
As of October 2026, both are third-party models outside the usage included with Cursor plans. On The X Subscription they are billed at API list price from prepaid credit on Premium and above; Plus and Free do not include third-party models. On legacy Cursor plans (Pro, Pro Plus, Ultra, and Teams) they draw from the Other Models pool, which Start does not include. Pricing is flat across the full context window, with no long-context surcharge and no separate cache-write fee. Check your account's usage details before running them at scale.
Get an email when Cursor changes its plans, prices or limits
We check every change against Cursor's own pages before we send. You also get the weekly AI Catchup; one click unsubscribes.