Skip to main content

Z.ai

GLM 5.3

Z.ai's 2026-08-14 Coding Plan flagship — same base as GLM 5.2, with the documented gains from post-training only. Direct token API and open weights are not published yet.

Catalog record checked August 14, 2026; individual provider fields may change.

AI model specification details
SpecificationGLM 5.3
ProviderZ.ai
TierFrontier
Context window1M
Max output128K
Input / 1M tokensNot verified
Output / 1M tokensNot verified
WeightsClosed
ParametersNot disclosed
Modalitiestext
ReleasedAugust 14, 2026

Pricing tiers: Direct `glm-5.3` API is documented as coming soon and is not on the Z.ai per-token table (do not assume GLM 5.2's $1.40/$4.40). Today it is on every GLM Coding Plan: points-based quota (input / cached input / output). Off-peak is 50% of standard points. Peak is Monday–Friday 14:00–18:00 UTC+8. Coding Plan requests for GLM-5.2/5.1 are routed to 5.3.

Best for

  • GLM Coding Plan agent work
  • Long-horizon coding in Claude Code / OpenCode / Cline
  • Teams already on Z.ai subscriptions

Watch out

Thinking cannot be disabled (`thinking.type: disabled` fails); `reasoning_effort` is low / high / max (default max). Open weights are promised about two weeks after launch pending safety review — not a downloadable checkpoint today. Vendor DeepSWE v1.1 66.9 used mini-swe-agent at 400K context, not the public Datacurve v1.1 board (snapshot generated 2026-08-13, before this launch).

Common questions

GLM 5.3

Answered from the verified figures on this page rather than general guidance.

What is GLM 5.3's context window?

GLM 5.3 accepts about 1M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.

What is GLM 5.3 best for?

GLM 5.3 is a frontier tier from Z.ai. It suits glm coding plan agent work, long-horizon coding in claude code / opencode / cline, teams already on z.ai subscriptions. Thinking cannot be disabled (`thinking.type: disabled` fails); `reasoning_effort` is low / high / max (default max). Open weights are promised about two weeks after launch pending safety review — not a downloadable checkpoint today. Vendor DeepSWE v1.1 66.9 used mini-swe-agent at 400K context, not the public Datacurve v1.1 board (snapshot generated 2026-08-13, before this launch).

Compare it

Head-to-head model comparisons

These are the published pairings that put this model against a plausible alternative.