# GLM-5.3

GLM-5.3 is a model from Z.ai with open weights, released on 18 Aug 2026. The context window is 1,048,576 tokens. The maximum output is 131,072 tokens. Pricing is $1.40 per million input tokens and $4.40 per million output tokens.

- Developer: Z.ai
- Id: zai-org/glm-5.3
- Reported: 2026-08-11T08:44:17.000Z
- Released: 2026-08-18T00:00:00.000Z
- Sighting: 2026-09-15T04:52:10.339Z
  - [evidence link](https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models)
- Status: Released
- Weights version: 2026-08-27
  - [evidence link](https://huggingface.co/api/models/zai-org/GLM-5.3/paths-info/ba32f8c19c8738e2c57c71798c601d477a7bf844)
- Canonical: https://alexgetman.com/models/z-ai/glm-5-3-727-2/

## Questions

### What is the context window of GLM-5.3?

The context window is 1,048,576 tokens. The maximum output is 131,072 tokens.

### How much does GLM-5.3 cost?

Pricing is $1.40 per million input tokens and $4.40 per million output tokens. Cached input is $0.26 per million.

### Are the weights of GLM-5.3 publicly available?

Yes. Z.ai publishes the weights.

### When was GLM-5.3 released?

On 18 Aug 2026.

## Timeline

- 2026-11-05T17:47:34.513Z · [GitHub · MiniMax-AI/minimax-code · code](https://github.com/MiniMax-AI/minimax-code/blob/3c21163c85a9684030cb147bfef48c6284fa3c46/packages/local-runtime-v2/src/service/model-system/catalog/provider-presets/provider-presets.service.test.ts)
> arsePresetsForTest(
>       Object.fromEntries(
>         plans.map(([id, , api]) => [
>           id,
>           {
>             name: 'Ambiguous upstream label',
>             npm: '@ai-sdk/openai-compatible',
>             api,
>             models: { 'glm-5.3': { name: 'GLM-5.3', tool_call: true } },
>           },
>         ]),
>       ),
>     );
>     expect(presets).toHaveLength(4);
>     for (const [providerId, name, baseUrl] of plans) {
>       const preset = presets.find((item) => item.providerId === providerId);
>       expect(preset).toMatchObject({
>         providerId,
>         name,
>         baseUrl,
>         apiFormat: 'openai-completions',
>         models: [{ modelId: 'glm-5.3' }],
>       });
>       expect(providerCompletionUrl('openai-completions', preset!.baseUrl)).toBe(
>         `${baseUrl}/chat/completions`,
>       );
>     }
>   });
> 
>   it('builds each Provider icon URL from the catalog snapshot pr
This code reference does not establish a working model identifier.
- 2026-11-13T18:34:21.803Z · [GitHub search · Z.ai · commits · raspy135/tideLM · @unknown](https://github.com/raspy135/tideLM/commit/2b4598f71fbcebd4118c236e8e290cb1533fb4c8)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · AI-native-Systems-Research/groundwork · @hivecommons-hive[bot]](https://github.com/AI-native-Systems-Research/groundwork/pull/65)
> — hive: agent=quality backend=curvebender model=rits/zai-org/glm-5-3
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · AI-native-Systems-Research/groundwork · @hivecommons-hive[bot]](https://github.com/AI-native-Systems-Research/groundwork/pull/66)
> — hive: agent=quality backend=curvebender model=rits/zai-org/glm-5-3
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · AMD-AGI/AKLR · @zhenhuang12](https://github.com/AMD-AGI/AKLR/pull/194)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · BerriAI/litellm-docs · @jIrwinCline](https://github.com/BerriAI/litellm-docs/pull/2941)
> https://github.com/BerriAI/litellm/pull/51231. It covers SDK and gateway setup for GLM-5.3 and GLM-5.3 Flash, streaming usage, tool-result continuations, model limits, cached-input pricing and timeout handling.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · CYBERSZP0NT/szmelc-router · @sernik77](https://github.com/CYBERSZP0NT/szmelc-router/pull/7)
> | Chutes | `api.chutes.ai/v1` (404) | `llm.chutes.ai/v1`, `zai-org/GLM-5.3` | reaches the API; 402 = $0 balance |
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · HawkBearPig/dgpp · @HawkBearPig](https://github.com/HawkBearPig/dgpp/pull/180)
> Four nodes, GLM-5.3 Mixed346 with its runtime adapter, production's recipe. Twelve prompts of 4K to 12K tokens, sent one at a time, each carrying a
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/pull/11)
> - the text model of GLM-5.3-Flash (glm5_next) and GLM-5.3 (glm_moe_dsa), with a tiny-checkpoint reference check.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Layr-Labs/d-inference · @jonathan308](https://github.com/Layr-Labs/d-inference/pull/2086)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA-NeMo/Megatron-Bridge · @kevalmorabia97](https://github.com/NVIDIA-NeMo/Megatron-Bridge/pull/6910)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @YouNeedCryDear](https://github.com/NVIDIA/hyperflare-inference/pull/172)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NixOS/nixpkgs · @silicalet](https://github.com/NixOS/nixpkgs/pull/563077)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NousResearch/hermes-agent · @glitchbunny0](https://github.com/NousResearch/hermes-agent/pull/137470)
> vision tool — e.g. a text-only main model (GLM-5.3) pinned to a vision-capable describer (GLM-5.3-Flash). But `decide_image_input_mode` applies that pin globally: a delegated child spawned
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/pull/104)
> The release validation (C8) ran `/dev-plan` on GLM-5.3 through Z.AI:
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/pull/105)
> During the release validation (C8, C9), `/dev-plan` on GLM-5.3 refused the same plan twice with
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/pull/106)
> During the release validation (C10), `/dev-plan` on GLM-5.3 refused the same plan twice with:
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · PayPerQ/ppq-enclave-proxy · @mattius459](https://github.com/PayPerQ/ppq-enclave-proxy/pull/414)
> Chatwoot 2171 (2026-11-05) — eight non-streaming `private/kimi-k3` / `private/glm-5-3` answers of 9–22 minutes, generated and billed in full ($10.76), delivered to nobody; the same caller's
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Pb314314/vllm · @Pb314314](https://github.com/Pb314314/vllm/pull/35)
> | GLM-5.3 (`GlmMoeDsaForCausalLM`, same class), fp8 KV | Yes, but its default RoPE accepts `key=None`, so it never crashed | GSM8K, 1319 questions | 0.901
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Tencent/LoopForge · @wycocoyu](https://github.com/Tencent/LoopForge/pull/165)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @KevRojo](https://github.com/anomalyco/models.dev/pull/13358)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @jIrwinCline](https://github.com/anomalyco/models.dev/pull/13426)
> approved Unlid backup. Provider entries retain the existing `zhipuai/glm-5.3` and `zhipuai/glm-5.3-flash` lineage while explicitly identifying the served variants.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ashhart/TensorFold · @jayleaton](https://github.com/ashhart/TensorFold/pull/3170)
> (new): Pick a model (keeps the `qualified-models` anchor), GLM-5.3 one machine or two, Models on disk, Model discovery. Table rows are copied verbatim: only relative
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · astrid-runtime/astrid · @joshuajbouw](https://github.com/astrid-runtime/astrid/pull/2213)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · aurora-silicon/mesa · @joshuaswarren](https://github.com/aurora-silicon/mesa/pull/261)
> #36 has two cross-model reviews GREEN (Claude and zai/glm-5.3).
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · blazed/cake · @renovate[bot]](https://github.com/blazed/cake/pull/1384)
> `type: "message"` the Provider API adapter requires for `zai-org/GLM-5.3`, which answered `400 invalid_request: input item is missing type` on the first turn. The rewrite is
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · charlieanna/autocode · @charlieanna](https://github.com/charlieanna/autocode/pull/3405)
> - Models: `zai-coding-plan/glm-5.3` (`low`)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · compute-verification/verity · @danielreuter](https://github.com/compute-verification/verity/pull/9368)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · crewAIInc/crewAI · @ats3v](https://github.com/crewAIInc/crewAI/pull/9316)
> chat models of that catalog on 2026-11-10: `deepseek-ai/DeepSeek-V4.1-Flash`, `zai-org/GLM-5.3-Flash`, `deepseek-ai/DeepSeek-V4-Pro-0813` and `zai-org/GLM-5.3`. The first is small and generally available, as the default has to be.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · duketopceo/open-computer · @duketopceo](https://github.com/duketopceo/open-computer/pull/163)
> Switch High to `z-ai/glm-5.3`, replace the slow Medium fallback and an unreachable worker fallback, refresh every catalog price from the live OpenRouter US models API,
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · eggpeat/oh-my-pi · @robo-egg](https://github.com/eggpeat/oh-my-pi/pull/115)
> Follow-up worker models: zai/glm-5.3 (high thinking), lane glm
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · firas9941/tinygrad · @pull[bot]](https://github.com/firas9941/tinygrad/pull/235)
> a dependency-and-fence graph, drops Windows support, and adds GLM-5.3/Kimi K3 LLM support with fused GPT-OSS kernels.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · fullsend-ai/fullsend · @tpouyer](https://github.com/fullsend-ai/fullsend/pull/9324)
> - Model: enmaas/rits/zai-org/glm-5-3@high
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · fullsend-ai/fullsend · @tpouyer](https://github.com/fullsend-ai/fullsend/pull/9339)
> - Model: enmaas/rits/zai-org/glm-5-3@high
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · hatai/Pelway · @pelway-dev[bot]](https://github.com/hatai/Pelway/pull/275)
> Implementer: agent=opencode model=zai-coding-plan/glm-5.3 effort=high
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · huggingface/speech-to-speech · @andimarafioti](https://github.com/huggingface/speech-to-speech/pull/829)
> Qwen3.8-2.4T, Qwen3.8-27B, Gemma 4 31B, DeepSeek-V4.1-Flash, DeepSeek-V4-Pro, Kimi-K3.1-Pro, GLM-5.3, MiniMax-M3.1-Flash, Mistral-Large-4, Muse-Spark-Open, Nemotron-3.5-Super, Hy4-preview; small: LFM3-1.7B, Ling-3.0-tiny, granite-4.2-3b, granite-4.2-8b, Qwen3.5-9B, LFM2.5-24B, Nemotron-3.5-Lightning, Gemma 4 26B,
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · j5ik2o/takt · @j5ik2o](https://github.com/j5ik2o/takt/pull/13)
> model: ollama/glm-5.3:cloud
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · jboix/quanthea · @dependabot[bot]](https://github.com/jboix/quanthea/pull/26)
> <li>28e30cd: support low and max reasoning effort for GLM-5.3 models</li>
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · kollaborai/kollab · @kollaborai](https://github.com/kollaborai/kollab/pull/954)
> claude-code 71, codex-cli 46, antigravity 6, openai-oauth 67, glm-5.3-flash 12, glm-5.3 12.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · kudy-vk/KUDY · @vokhandcrafts](https://github.com/kudy-vk/KUDY/pull/282)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · marin-community/marin · @penfever](https://github.com/marin-community/marin/pull/11373)
> conversation, tools, references, prompts, model `glm-5.3`, token budgets, labels
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · maximhq/bifrost · @is911](https://github.com/maximhq/bifrost/pull/6054)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · metorial/metorial-platform · @herber](https://github.com/metorial/metorial-platform/pull/1216)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · muni-works/frog · @ecto](https://github.com/muni-works/frog/pull/322)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · openai/codex-security · @NielsRogge](https://github.com/openai/codex-security/pull/2648)
> SDK scans. Users can select `--provider huggingface --model zai-org/GLM-5.3:novita` with `HF_TOKEN` instead of OpenAI authentication.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · openstack-k8s-operators/prometheus-podman-exporter · @danpawlik](https://github.com/openstack-k8s-operators/prometheus-podman-exporter/pull/13)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · oska-salova/ai-for-developers-project-387 · @oska-salova](https://github.com/oska-salova/ai-for-developers-project-387/pull/28)
> - промпт в `.scratch/prompt.md`, запуск `opencode run --model opencode/glm-5.3 --auto`;
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · paperclipai/paperclip · @b3nnb](https://github.com/paperclipai/paperclip/pull/14346)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · paperclipai/paperclip · @MMTE](https://github.com/paperclipai/paperclip/pull/15465)
> z.ai GLM (Coding Plan), model id `zai/glm-5.3` (approx. 200K context), agentic tool-use mode — used for source analysis, the fix, and the test.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · paperclipai/paperclip · @cryppadotta](https://github.com/paperclipai/paperclip/pull/21241)
> - GLM by Z.ai, model id `z-ai/glm-5.3`, run through opencode by the Paperclip Runner. Extended reasoning enabled, with shell and file tool use.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ranxianglei/billion-context · @john08281](https://github.com/ranxianglei/billion-context/pull/5055)
> even on a cache hit (measured on z.ai glm-5.3; one decide call completed upstream in 25.8s and was billed, while bili had already aborted at
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · renj-arch/dimsred · @renj-arch](https://github.com/renj-arch/dimsred/pull/86)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · zhao-wuyan/llm-info · @github-actions[bot]](https://github.com/zhao-wuyan/llm-info/pull/89)
> (Max)", "Muse Spark 1.3 (Max)", "Gemini 3 Pro", "GLM-5.3 (Max)", "Qwen3.7-Max-Preview", "Kimi K3 (Max)", "Muse Spark", "Qwen3.5-Max-Preview", … (+159 names)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · HawkBearPig/dgpp · @HawkBearPig](https://github.com/HawkBearPig/dgpp/commit/2cd96ed77ed747e381937d0f498e391f65f8506d)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/commit/21c6ab5018477a56ace836cc1852401a6a181181)
> GLM-5.3: catalog entries, docs/glm.md with the measured agreement (transformers on tiny checkpoints, llama.cpp on the real UD-Q2_K_XL), the models table and the README index; glm5_check
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/commit/3976e5cf47e89b6c7563b3738f4bb4b12834b160)
> GLM-5.3: the chat template (reasoning effort line, thinking, tool calls) and the command line, engine and streaming wiring.
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/commit/dd6c4c3ced42bb12cf763bd30fc23ae65905134f)
> GLM-5.3: the text model of GLM-5.3-Flash (glm5_next) and GLM-5.3 (glm_moe_dsa), with a tiny-checkpoint reference check.
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/commit/87928896169f6500647b0efcf70c9e5c362d1243)
> The release validation ran /dev-plan on GLM-5.3 (Z.AI): at MaxTokens 24576
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/commit/8a10ecece72e6581be80a1b5f540b834eeea6efd)
> refused twice (release validation C8/C9 on GLM-5.3). The refusal now quotes
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/08a51f4306c3448ce3180db5ce06286e4160b5d9)
> Model: GLM-5.3 (zai-individual-coding-plan)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/6522ead9b5d951373c78c385dfa49330badfc118)
> Model: account:zai-individual-coding-plan/GLM-5.3 Operator-request: step 3 of #451 — split src/tg/mod.ts with pure moves
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/8b31b922a09a81102efa7422a023779c92d87a72)
> Model: GLM-5.3 (account:zai-individual-coding-plan)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/faa84f6ce6c0005ac2db5c32d6c3d422e3003992)
> Model: GLM-5.3 (zai-individual-coding-plan)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · celestia-island/hikari · @langyo](https://github.com/celestia-island/hikari/commit/b6312a41332fceeee0fd3c124acf3bb2ff80e742)
> AI-generated: developed with the DeepSeek Harness agent (model GLM-5.3 Flash); human-directed — SySL-1.0 §2.3 disclosure.
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · duketopceo/open-computer · @duketopceo](https://github.com/duketopceo/open-computer/commit/0da9832129f7fd0239e5562e9f01a27fd1fbfa5a)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · henjicc/Henji-AI · @henjicc](https://github.com/henjicc/Henji-AI/commit/5d5381e7d574b752b1170388e668168c5af9347e)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · jolpindo96/llamacpp-hip · @jolpindo96](https://github.com/jolpindo96/llamacpp-hip/commit/1c4123afafb721384653645589827ce4cb6366f0)
> Qwen models, 2.6-3.5% slower decode for DeepSeek-V4 and GLM-5.3, and 1-3%
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · kimkon1011/orgiast-claude-rules · @seisaku-team-org](https://github.com/kimkon1011/orgiast-claude-rules/commit/81ed029aea83a03f82c86fe43a2dde355f788e88)
> Claude SDK が --model glm-5.3 フラグを検証して unrecognized_model で失敗する。
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · leonistor/my-opencode-config · @leonistor](https://github.com/leonistor/my-opencode-config/commit/39e547cca95b902d03e52dee257349adf12c583e)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · magpie-community/plugins · @yetone](https://github.com/magpie-community/plugins/commit/c95e20a3525a1e832a2bd4c1daac26d1680b370f)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · nearai/cvm-compose-files · @henrypark133](https://github.com/nearai/cvm-compose-files/commit/feb813c2ac6ed3f9af2b9f4a69336b92fa4db619)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · paperclipai/paperclip · @cryppadotta](https://github.com/paperclipai/paperclip/commit/9d9ee92d156153eaf16b7ae0fbd70f535175358d)
> - GLM by Z.ai, model id `z-ai/glm-5.3`, run through opencode by the
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · phuchello2811-web/GLM · @doanbaphu](https://github.com/phuchello2811-web/GLM/commit/3ad6c14b98481b86a53ba5bc72144d77e50d0c23)
> Add Titan 4 Mega (GLM-5.3 Flash) as the new default and strongest model
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · phuchello2811-web/GLM · @phuchello2811-web](https://github.com/phuchello2811-web/GLM/commit/c175b75967d7853118493ee787abd1df54d9f08b)
> Thêm Titan 4 Mega (GLM-5.3 Flash) làm model mạnh nhất, mặc định
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · psyb0t/peen · @psyb0t](https://github.com/psyb0t/peen/commit/920df856db2c14dd9b510f302a99838a929b5e55)
> model, the task passed 5 of 5 on GLM-5.3 and 5 of 5 on GLM-5.3-Flash, compared with 4 of 5 and 2 of 5 before.
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · roobie/skelly · @unknown](https://github.com/roobie/skelly/commit/88fba522762729fcf4fff495712ce7e1095d1cb5)
> Model: glm-5.3
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · unixmonks/gpu · @unixmonks](https://github.com/unixmonks/gpu/commit/3f5cd7b12a59244e4ccb4350687a7326e9dd62fe)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · xenoterracide/agent-skills · @xenoterracide-bot](https://github.com/xenoterracide/agent-skills/commit/ab3fbcf2d5f2f402977373eb19d9cb134df86aa6)

## Evidence links

- [Artificial Analysis · benchmarks](https://artificialanalysis.ai/models)
- [vertex-model-garden](https://console.cloud.google.com/vertex-ai/publishers/zai-org/model-garden/glm-5-3)
- [dashscope](https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models)
- [zai-model-index](https://docs.z.ai/api-reference/llm/chat-completion)
- [review](https://docs.z.ai/guides/llm/glm-5.3)
- [zai-pricing](https://docs.z.ai/guides/overview/pricing)
- [GitHub search · Z.ai · pulls · AI-native-Systems-Research/groundwork · @hivecommons-hive[bot]](https://github.com/AI-native-Systems-Research/groundwork/pull/65)
- [GitHub search · Z.ai · pulls · AI-native-Systems-Research/groundwork · @hivecommons-hive[bot]](https://github.com/AI-native-Systems-Research/groundwork/pull/66)
- [GitHub search · Z.ai · pulls · AMD-AGI/AKLR · @zhenhuang12](https://github.com/AMD-AGI/AKLR/pull/194)
- [GitHub search · Z.ai · pulls · BerriAI/litellm-docs · @jIrwinCline](https://github.com/BerriAI/litellm-docs/pull/2941)
- [GitHub search · Z.ai · pulls · CYBERSZP0NT/szmelc-router · @sernik77](https://github.com/CYBERSZP0NT/szmelc-router/pull/7)
- [GitHub search · Z.ai · commits · HawkBearPig/dgpp · @HawkBearPig](https://github.com/HawkBearPig/dgpp/commit/2cd96ed77ed747e381937d0f498e391f65f8506d)
- [GitHub search · Z.ai · pulls · HawkBearPig/dgpp · @HawkBearPig](https://github.com/HawkBearPig/dgpp/pull/180)
- [GitHub search · Z.ai · commits · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/commit/21c6ab5018477a56ace836cc1852401a6a181181)
- [GitHub search · Z.ai · commits · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/commit/3976e5cf47e89b6c7563b3738f4bb4b12834b160)
- [GitHub search · Z.ai · commits · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/commit/dd6c4c3ced42bb12cf763bd30fc23ae65905134f)
- [GitHub search · Z.ai · pulls · KarpelesLab/oxinfer · @MagicalTux](https://github.com/KarpelesLab/oxinfer/pull/11)
- [GitHub search · Z.ai · pulls · Layr-Labs/d-inference · @jonathan308](https://github.com/Layr-Labs/d-inference/pull/2086)
- [GitHub · MiniMax-AI/minimax-code · code](https://github.com/MiniMax-AI/minimax-code/blob/3c21163c85a9684030cb147bfef48c6284fa3c46/packages/local-runtime-v2/src/service/model-system/catalog/provider-presets/provider-presets.service.test.ts)
- [GitHub search · Z.ai · pulls · NVIDIA-NeMo/Megatron-Bridge · @kevalmorabia97](https://github.com/NVIDIA-NeMo/Megatron-Bridge/pull/6910)
- [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @YouNeedCryDear](https://github.com/NVIDIA/hyperflare-inference/pull/172)
- [GitHub search · Z.ai · pulls · NixOS/nixpkgs · @silicalet](https://github.com/NixOS/nixpkgs/pull/563077)
- [GitHub search · Z.ai · pulls · NousResearch/hermes-agent · @glitchbunny0](https://github.com/NousResearch/hermes-agent/pull/137470)
- [GitHub search · Z.ai · commits · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/commit/87928896169f6500647b0efcf70c9e5c362d1243)
- [GitHub search · Z.ai · commits · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/commit/8a10ecece72e6581be80a1b5f540b834eeea6efd)
- [GitHub search · Z.ai · pulls · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/pull/104)
- [GitHub search · Z.ai · pulls · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/pull/105)
- [GitHub search · Z.ai · pulls · Orkeon/orkeon-code · @arion-orkeon](https://github.com/Orkeon/orkeon-code/pull/106)
- [GitHub search · Z.ai · pulls · PayPerQ/ppq-enclave-proxy · @mattius459](https://github.com/PayPerQ/ppq-enclave-proxy/pull/414)
- [GitHub search · Z.ai · pulls · Pb314314/vllm · @Pb314314](https://github.com/Pb314314/vllm/pull/35)
- [GitHub search · Z.ai · pulls · Tencent/LoopForge · @wycocoyu](https://github.com/Tencent/LoopForge/pull/165)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @KevRojo](https://github.com/anomalyco/models.dev/pull/13358)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @jIrwinCline](https://github.com/anomalyco/models.dev/pull/13426)
- [GitHub search · Z.ai · pulls · ashhart/TensorFold · @jayleaton](https://github.com/ashhart/TensorFold/pull/3170)
- [GitHub search · Z.ai · pulls · astrid-runtime/astrid · @joshuajbouw](https://github.com/astrid-runtime/astrid/pull/2213)
- [GitHub search · Z.ai · pulls · aurora-silicon/mesa · @joshuaswarren](https://github.com/aurora-silicon/mesa/pull/261)
- [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/08a51f4306c3448ce3180db5ce06286e4160b5d9)
- [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/6522ead9b5d951373c78c385dfa49330badfc118)
- [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/8b31b922a09a81102efa7422a023779c92d87a72)
- [GitHub search · Z.ai · commits · bermudi/little-goblin · @bermudi](https://github.com/bermudi/little-goblin/commit/faa84f6ce6c0005ac2db5c32d6c3d422e3003992)
- [GitHub search · Z.ai · pulls · blazed/cake · @renovate[bot]](https://github.com/blazed/cake/pull/1384)
- [GitHub search · Z.ai · commits · celestia-island/hikari · @langyo](https://github.com/celestia-island/hikari/commit/b6312a41332fceeee0fd3c124acf3bb2ff80e742)
- [GitHub search · Z.ai · pulls · charlieanna/autocode · @charlieanna](https://github.com/charlieanna/autocode/pull/3405)
- [GitHub search · Z.ai · pulls · compute-verification/verity · @danielreuter](https://github.com/compute-verification/verity/pull/9368)
- [GitHub search · Z.ai · pulls · crewAIInc/crewAI · @ats3v](https://github.com/crewAIInc/crewAI/pull/9316)
- [GitHub search · Z.ai · commits · duketopceo/open-computer · @duketopceo](https://github.com/duketopceo/open-computer/commit/0da9832129f7fd0239e5562e9f01a27fd1fbfa5a)
- [GitHub search · Z.ai · pulls · duketopceo/open-computer · @duketopceo](https://github.com/duketopceo/open-computer/pull/163)
- [GitHub search · Z.ai · pulls · eggpeat/oh-my-pi · @robo-egg](https://github.com/eggpeat/oh-my-pi/pull/115)
- [GitHub search · Z.ai · pulls · firas9941/tinygrad · @pull[bot]](https://github.com/firas9941/tinygrad/pull/235)
- [GitHub search · Z.ai · pulls · fullsend-ai/fullsend · @tpouyer](https://github.com/fullsend-ai/fullsend/pull/9324)
- [GitHub search · Z.ai · pulls · fullsend-ai/fullsend · @tpouyer](https://github.com/fullsend-ai/fullsend/pull/9339)
- [GitHub search · Z.ai · pulls · hatai/Pelway · @pelway-dev[bot]](https://github.com/hatai/Pelway/pull/275)
- [GitHub search · Z.ai · commits · henjicc/Henji-AI · @henjicc](https://github.com/henjicc/Henji-AI/commit/5d5381e7d574b752b1170388e668168c5af9347e)
- [GitHub search · Z.ai · pulls · huggingface/speech-to-speech · @andimarafioti](https://github.com/huggingface/speech-to-speech/pull/829)
- [GitHub search · Z.ai · pulls · j5ik2o/takt · @j5ik2o](https://github.com/j5ik2o/takt/pull/13)
- [GitHub search · Z.ai · pulls · jboix/quanthea · @dependabot[bot]](https://github.com/jboix/quanthea/pull/26)
- [GitHub search · Z.ai · commits · jolpindo96/llamacpp-hip · @jolpindo96](https://github.com/jolpindo96/llamacpp-hip/commit/1c4123afafb721384653645589827ce4cb6366f0)
- [GitHub search · Z.ai · commits · kimkon1011/orgiast-claude-rules · @seisaku-team-org](https://github.com/kimkon1011/orgiast-claude-rules/commit/81ed029aea83a03f82c86fe43a2dde355f788e88)
- [GitHub search · Z.ai · pulls · kollaborai/kollab · @kollaborai](https://github.com/kollaborai/kollab/pull/954)
- [GitHub search · Z.ai · pulls · kudy-vk/KUDY · @vokhandcrafts](https://github.com/kudy-vk/KUDY/pull/282)
- [GitHub search · Z.ai · commits · leonistor/my-opencode-config · @leonistor](https://github.com/leonistor/my-opencode-config/commit/39e547cca95b902d03e52dee257349adf12c583e)
- [GitHub search · Z.ai · commits · magpie-community/plugins · @yetone](https://github.com/magpie-community/plugins/commit/c95e20a3525a1e832a2bd4c1daac26d1680b370f)
- [GitHub search · Z.ai · pulls · marin-community/marin · @penfever](https://github.com/marin-community/marin/pull/11373)
- [GitHub search · Z.ai · pulls · maximhq/bifrost · @is911](https://github.com/maximhq/bifrost/pull/6054)
- [GitHub search · Z.ai · pulls · metorial/metorial-platform · @herber](https://github.com/metorial/metorial-platform/pull/1216)
- [GitHub search · Z.ai · pulls · muni-works/frog · @ecto](https://github.com/muni-works/frog/pull/322)
- [GitHub search · Z.ai · commits · nearai/cvm-compose-files · @henrypark133](https://github.com/nearai/cvm-compose-files/commit/feb813c2ac6ed3f9af2b9f4a69336b92fa4db619)
- [GitHub search · Z.ai · pulls · openai/codex-security · @NielsRogge](https://github.com/openai/codex-security/pull/2648)
- [GitHub search · Z.ai · pulls · openstack-k8s-operators/prometheus-podman-exporter · @danpawlik](https://github.com/openstack-k8s-operators/prometheus-podman-exporter/pull/13)
- [GitHub search · Z.ai · pulls · oska-salova/ai-for-developers-project-387 · @oska-salova](https://github.com/oska-salova/ai-for-developers-project-387/pull/28)
- [GitHub search · Z.ai · commits · paperclipai/paperclip · @cryppadotta](https://github.com/paperclipai/paperclip/commit/9d9ee92d156153eaf16b7ae0fbd70f535175358d)
- [GitHub search · Z.ai · pulls · paperclipai/paperclip · @b3nnb](https://github.com/paperclipai/paperclip/pull/14346)
- [GitHub search · Z.ai · pulls · paperclipai/paperclip · @MMTE](https://github.com/paperclipai/paperclip/pull/15465)
- [GitHub search · Z.ai · pulls · paperclipai/paperclip · @cryppadotta](https://github.com/paperclipai/paperclip/pull/21241)
- [GitHub search · Z.ai · commits · phuchello2811-web/GLM · @doanbaphu](https://github.com/phuchello2811-web/GLM/commit/3ad6c14b98481b86a53ba5bc72144d77e50d0c23)
- [GitHub search · Z.ai · commits · phuchello2811-web/GLM · @phuchello2811-web](https://github.com/phuchello2811-web/GLM/commit/c175b75967d7853118493ee787abd1df54d9f08b)
- [GitHub search · Z.ai · commits · psyb0t/peen · @psyb0t](https://github.com/psyb0t/peen/commit/920df856db2c14dd9b510f302a99838a929b5e55)
- [GitHub search · Z.ai · pulls · ranxianglei/billion-context · @john08281](https://github.com/ranxianglei/billion-context/pull/5055)
- [GitHub search · Z.ai · commits · raspy135/tideLM · @unknown](https://github.com/raspy135/tideLM/commit/2b4598f71fbcebd4118c236e8e290cb1533fb4c8)
- [GitHub search · Z.ai · pulls · renj-arch/dimsred · @renj-arch](https://github.com/renj-arch/dimsred/pull/86)
- [GitHub search · Z.ai · commits · roobie/skelly · @unknown](https://github.com/roobie/skelly/commit/88fba522762729fcf4fff495712ce7e1095d1cb5)
- [GitHub search · Z.ai · commits · unixmonks/gpu · @unixmonks](https://github.com/unixmonks/gpu/commit/3f5cd7b12a59244e4ccb4350687a7326e9dd62fe)
- [GitHub search · Z.ai · commits · xenoterracide/agent-skills · @xenoterracide-bot](https://github.com/xenoterracide/agent-skills/commit/ab3fbcf2d5f2f402977373eb19d9cb134df86aa6)
- [GitHub search · Z.ai · pulls · zhao-wuyan/llm-info · @github-actions[bot]](https://github.com/zhao-wuyan/llm-info/pull/89)
- [hf-author-artifacts:zai-org](https://huggingface.co/api/models/zai-org/GLM-5.3/paths-info/ba32f8c19c8738e2c57c71798c601d477a7bf844)
- [huggingface-router](https://huggingface.co/zai-org/GLM-5.3)
- [models.dev · catalogue](https://models.dev/#GLM-5.3)
- [models.dev · catalogue](https://models.dev/#glm-5-3)
- [models.dev · catalogue](https://models.dev/#glm-5.3)
- [models.dev · catalogue](https://models.dev/#glm-5.3-free)
- [models.dev · catalogue](https://models.dev/#glm-5p3)
- [models.dev · catalogue](https://models.dev/#glm5.3)
- [models.dev · catalogue](https://models.dev/#glm5.3-754b)
- [models.dev · catalogue](https://models.dev/#morph-glm53-744b)
- [models.dev · catalogue](https://models.dev/#umans-glm-5.3)
- [models.dev · catalogue](https://models.dev/#z-ai-glm-5-3)
- [OpenCode · discovery](https://opencode.ai/data/zhipuai/glm-5-3)
- [opencode-go](https://opencode.ai/inference/go/v1/models)
- [OpenRouter](https://openrouter.ai/api/v1/models)
- [OpenRouter](https://openrouter.ai/z-ai/glm-5.3)
- [OpenRouter](https://openrouter.ai/z-ai/glm-5.3:batch)
- [VoxelBench · leaderboard](https://voxelbench.ai/leaderboard)
- [Alibaba Model Studio API](https://www.alibabacloud.com/help/en/model-studio/models)

## Signals

- [Glm 5.3](https://alexgetman.com/signals/2026/09/15/glm-5-3/)
- [GLM-5.3 spotted on OpenRouter](https://alexgetman.com/signals/2026/09/08/glm-5-3-us/)