# GLM-5.3 Flash

GLM-5.3 Flash là mô hình AI từ Z.ai với trọng số mở, phát hành vào 2026-08-26. Cửa sổ ngữ cảnh có độ dài 1.048.576 token. Độ dài đầu ra tối đa là 131.072 token. Giá cho mỗi triệu token là $0,15 cho đầu vào và $0,50 cho đầu ra.

- Nhà phát triển: Z.ai
- Id: zai-org/GLM-5.3-Flash
- Theo báo cáo: 2026-09-10T19:01:51.000Z
- Đã phát hành: 2026-08-26T00:00:00.000Z
- Phát hiện: 2026-09-16T05:09:59.700Z
  - [liên kết bằng chứng](https://models.dev/#GLM-5.3-Flash)
- Trạng thái: Đã phát hành
- Phiên bản trọng số: 2026-08-26
  - [liên kết bằng chứng](https://huggingface.co/api/models/zai-org/GLM-5.3-Flash/paths-info/46a050bec13002ad29ee795c16e61cf4fa3c4a9c)
- Địa chỉ chuẩn: https://alexgetman.com/vi/models/z-ai/glm-5-3-flash-725/

## Câu hỏi

### Cửa sổ ngữ cảnh của GLM-5.3 Flash là gì?

Cửa sổ ngữ cảnh có độ dài 1.048.576 token. Độ dài đầu ra tối đa là 131.072 token.

### GLM-5.3 Flash giá bao nhiêu?

Giá cho mỗi triệu token là $0,15 cho đầu vào và $0,50 cho đầu ra. Đầu vào từ bộ nhớ đệm có giá $0,03 cho mỗi triệu token.

### Trọng số của mô hình GLM-5.3 Flash có được công khai không?

Có. Z.ai công bố trọng số của mô hình.

### GLM-5.3 Flash được phát hành khi nào?

2026-08-26.

## Dòng thời gian

- 2026-11-13T18:34:21.803Z · [GitHub search · Z.ai · commits · 520042/aigw-gateway-panel · @520042](https://github.com/520042/aigw-gateway-panel/commit/2da0eb83b7759ce9f1b93102cbf9f0f1ee5ac1de)
- 2026-11-13T18:34:21.803Z · [GitHub search · Z.ai · commits · islgit07/zcodebride-for-magpie · @islgit07](https://github.com/islgit07/zcodebride-for-magpie/commit/e8043524682b1d5f91b4dea386c81e5eb603b025)
- 2026-11-13T18:34:21.803Z · [GitHub search · Z.ai · commits · juliolv/portfolio · @juliolv](https://github.com/juliolv/portfolio/commit/8dc315ca3ba91a8a0a5ab477a25ee07feb195cd9)
> paid model; the cheap tier (deepseek-v4.1-flash, glm-5.3-flash, qwen3.8-flash,
- 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 · Augustas11/macprovider · @Augustas11](https://github.com/Augustas11/macprovider/pull/2342)
> M3 Ultra 256 GB, GLM-5.3-Flash, `msb-throughput --engine scheduler --prompt-tokens 1024 --decode-tokens 256 --runs 3`, the provider slice at `3675596d1` against main at `30ea73b89`, interleaved, two
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · BerriAI/litellm · @xinglan163](https://github.com/BerriAI/litellm/pull/51652)
> feat(deepinfra): add GLM-5.3-Flash, MiMo-V2.6-Flash, Nemotron-3.5-Super-VL, and Hy4-preview
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · BerryUIKI/CatCup-Tavern · @BerryUIKI](https://github.com/BerryUIKI/CatCup-Tavern/pull/81)
> ## Verified against the real endpoint (`deepseek-v4.1-flash` / `glm-5.3-flash`, 21 models)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · C2SM/icon4py · @egparedes](https://github.com/C2SM/icon4py/pull/1547)
> models` and shows a red check. gt4py uses `zai-org/GLM-5.3-Flash` with fallbacks `Qwen/Qwen3.8-Flash-Next-FP8,Qwen/Qwen3.8-27B-FP8`.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · CYBERSZP0NT/szmelc-router · @sernik77](https://github.com/CYBERSZP0NT/szmelc-router/pull/7)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · IBM/Evoflux · @renovate[bot]](https://github.com/IBM/Evoflux/pull/12)
- 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),
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Layr-Labs/arena-fortress · @yukon-autoresearch[bot]](https://github.com/Layr-Labs/arena-fortress/pull/187)
> submitted game. The game model remains the challenge's `z-ai/glm-5.3-flash` through the organizer's gateway.
- 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 · Layr-Labs/flock-challenge · @yukon-autoresearch[bot]](https://github.com/Layr-Labs/flock-challenge/pull/5592)
> Model: zai-org/GLM-5.3-Flash Harness: Hermes Agent
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Lore-Hex/quill-router · @jasminelee](https://github.com/Lore-Hex/quill-router/pull/2534)
> Move the Fortanix GLM 5.3 Flash offer from the homepage to its model page and search text
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Max-Health-Inc/config · @quotentiroler](https://github.com/Max-Health-Inc/config/pull/13)
> - Changes the default model to `@cf/zai-org/glm-5.3-flash`, which followed the prompt rules more reliably than the previous default in testing. `RELEASE_NOTES_MODEL` still overrides it.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Max-Health-Inc/config · @quotentiroler](https://github.com/Max-Health-Inc/config/pull/18)
> fix(vite): release notes default to Gemma 4 before glm-5.3-flash retires (4.5.1)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA-NeMo/Megatron-Bridge · @kamran-nvidia](https://github.com/NVIDIA-NeMo/Megatron-Bridge/pull/6909)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/Model-Optimizer · @cjluo-nv](https://github.com/NVIDIA/Model-Optimizer/pull/3351)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/Model-Optimizer · @shengliangxu](https://github.com/NVIDIA/Model-Optimizer/pull/3368)
> - **GLM-5.3-Flash** (`models/glm5_next/modeling_ptq_vllm.py`, a new package): the k-pool indexer with its K-cache writers and DeepGEMM scorer, from `vllm_indexer.py`. Like `kimi_k3`, `glm5_next` has no `specs.py`: it
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux](https://github.com/NVIDIA/TensorRT-LLM/pull/21019)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @ruocheng-nv](https://github.com/NVIDIA/TensorRT-LLM/pull/22254)
> end in #22082: a one-token prompt on the GLM-5.3-Flash FP8 target must not depend on the KDA slot's previous request, and the target is not
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/cudnn-frontend · @Anerudhan](https://github.com/NVIDIA/cudnn-frontend/pull/1847)
> Add pooled DSA forward APIs for Blackwell GLM-5.3-Flash pools index keys before selecting attention tokens. Add forward APIs for gated cache updates, paged scoring, pool
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @YouNeedCryDear](https://github.com/NVIDIA/hyperflare-inference/pull/172)
> The [GLM-5.3-Flash model card](https://huggingface.co/zai-org/GLM-5.3-Flash) documents `reasoning_effort` and `clear_thinking` and no way to turn thinking off. No revision of these three repositories' templates has contained `enable_thinking`.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @original-el8](https://github.com/NVIDIA/hyperflare-inference/pull/217)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @original-el8](https://github.com/NVIDIA/hyperflare-inference/pull/232)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @aarongiuffre](https://github.com/NVIDIA/hyperflare-inference/pull/59)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NousResearch/hermes-agent · @glitchbunny0](https://github.com/NousResearch/hermes-agent/pull/137470)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · OpenHands/OpenHands · @sanchitmonga22](https://github.com/OpenHands/OpenHands/pull/19468)
> (166 providers); `GET /api/llm/models?provider=wally` returns 10 models, including `wally/glm-5.3-flash` and `wally/deepseek-v4.1-flash`.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · Pb314314/vllm · @Pb314314](https://github.com/Pb314314/vllm/pull/35)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · QNFO/qnfo-workers · @rwnq8](https://github.com/QNFO/qnfo-workers/pull/11591)
> Draft for #6186: MODEL-AB-REGRESSION-1: qnfo-ai glm-5.3-flash -> standard on grounded-qa: win rate 0 < 0.4
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ROCm/aiter · @sumin-hong](https://github.com/ROCm/aiter/pull/7184)
> every shape. This is what SGLang passes for GLM-5.3-Flash under CUDA graphs: the k-pool indexer's block-table capacity, 1M context / kpool 4 = 4,097 pages
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ROCm/aiter · @sumin-hong](https://github.com/ROCm/aiter/pull/7374)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ROCm/aiter · @eppaneamd](https://github.com/ROCm/aiter/pull/7680)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ROCm/aiter · @eppaneamd](https://github.com/ROCm/aiter/pull/7681)
> - Callers that reach the new default: GLM-5.3-Flash at attention TP 2 (32 heads per rank), bf16 KV cache, gfx950,
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/58)
> - Real model over a PTY (`opencode-go/glm-5.3-flash`) in a temporary home, since deleted. In a first session I stated a codename and a rollback window.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/60)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/61)
> - With the real model (glm-5.3-flash) in the TUI, using temporary homes: a global Program ran by name from another project and recorded its exact
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/62)
> - With the real model (glm-5.3-flash) in the TUI, one temporary home and two projects:
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/63)
> through the real TUI in a PTY with `opencode-go/glm-5.3-flash`. I captured the provider request bodies and read the SQLite rows instead of trusting the model's
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/64)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · TigreGotico/linguonnx · @renovate[bot]](https://github.com/TigreGotico/linguonnx/pull/101)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · agentgateway/agentgateway · @github-actions[bot]](https://github.com/agentgateway/agentgateway/pull/4377)
> json.providers.nebius.models["zai-org/GLM-5.3-Flash"].reasoning.effort[2] = "max";
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · alecpullen/marshal · @alecpullen](https://github.com/alecpullen/marshal/pull/64)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · alexsantossp71-lgtm/remedios_app · @alexsantossp71-lgtm](https://github.com/alexsantossp71-lgtm/remedios_app/pull/14)
> `z-ai/glm-5.3-flash`, `stepfun-ai/step-5-preview`, `meta/muse-glimmer-30b`, `nvidia/nemotron-3.5-super-vl-120b-a12b` e `nvidia/nemotron-3.5-lightning-30b-a3b`. O app consulta o catálogo real da conta e só tenta os IDs retornados quando há correspondência.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ameetmadan/lautli · @renovate[bot]](https://github.com/ameetmadan/lautli/pull/35)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @jIrwinCline](https://github.com/anomalyco/models.dev/pull/13426)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13561)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @NachiketKandari](https://github.com/anomalyco/models.dev/pull/13577)
> v1 (2; new models should usually be v2_only): isoquant/glm-5.3-flash, isoquant/deepseek-v4.1-flash-1017-fast
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ashcoft/document-mcp · @renovate[bot]](https://github.com/ashcoft/document-mcp/pull/966)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ashhart/TensorFold · @Bizuayeu](https://github.com/ashhart/TensorFold/pull/3151)
> as they are. On four GB10s at TP=4 (GLM-5.3-Flash XSFP4, `--context 1048576 --parallel 8`), round time in ms from our own grid client (`"draft": false`,
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ashhart/TensorFold · @Bizuayeu](https://github.com/ashhart/TensorFold/pull/3249)
> On four GB10s at TP=4 (GLM-5.3-Flash XSFP4, `--context 1048576 --parallel 8`), round time in ms from our own grid client (`"draft": false`, greedy, 256 tokens,
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · basetenlabs/baseten-cli · @sanieldalib](https://github.com/basetenlabs/baseten-cli/pull/264)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · cassandre60/ChessSRS · @cassandre60](https://github.com/cassandre60/ChessSRS/pull/658)
> Model: z-ai/glm-5.3-flash
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · crewAIInc/crewAI · @ats3v](https://github.com/crewAIInc/crewAI/pull/9316)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ddalcu/mlx-serve · @davidtai](https://github.com/ddalcu/mlx-serve/pull/1192)
> serve packs an outside quant plugin claims (DeepSeek-V4.1, GLM-5.3-Flash, Qwen3.8, Ling-3.1-flash)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · duketopceo/open-computer · @duketopceo](https://github.com/duketopceo/open-computer/pull/163)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · egonSchiele/agency-lang · @egonSchiele](https://github.com/egonSchiele/agency-lang/pull/1466)
> Anthropic stays at 20,000 from the provider layer; `z-ai/glm-5.3-flash` gets 131,072 from the model layer.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · figranium/fiptcha · @renovate[bot]](https://github.com/figranium/fiptcha/pull/39)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · gcanlin/vllm · @gcanlin](https://github.com/gcanlin/vllm/pull/15)
> Vision tower alone (glm-5.3-bf16 weights, identical to GLM-5.3-Flash's BF16 tower), 1x B200, eager as served by default, FA4. Two interleaved runs per variant, mean of
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ggml-org/llama.cpp · @snakeice](https://github.com/ggml-org/llama.cpp/pull/32212)
> necessary step for running large MoE models (e.g. GLM-5.3-Flash 320B, 157 GB GGUF) on consumer hardware (32 GB RAM, single GPU) where CPU offloading makes
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · harbor-framework/terminal-bench-science · @RishabhPatil](https://github.com/harbor-framework/terminal-bench-science/pull/2266)
> (`harbor run`) with `gemini/gemini-3.1-pro-preview` via `gemini-cli` (5 trials), `zai-org/GLM-5.3-Flash` via `terminus-2` (5 trials), and `Qwen/Qwen3.8-27B` via `terminus-2` (5 trials), plus Oracle (`1.0` reward, 4/4 pytest
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · kaina-visualsoftware/QA-Hub · @kaina-visualsoftware](https://github.com/kaina-visualsoftware/QA-Hub/pull/114)
> logs de produção mostram interrupções por `TimeoutError` no `z-ai/glm-5.3-flash`; houve também HTTP 502 no endpoint separado `qa-ai`.
- 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 · leptoskit/leptoskit · @ifiokjr](https://github.com/leptoskit/leptoskit/pull/828)
> Created on behalf of Ifiok Jr. (@ifiokjr), GLM-5.3-Flash (zai-coding-plan/glm-5.3-flash), high reasoning.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · lidge-jun/opencodex · @andrew05060414](https://github.com/lidge-jun/opencodex/pull/8708)
> showed prices. `cn:deepseek-v4.1-flash` came from OpenRouter (0.3/1.2). `cn:kimi-k3.1-pro`, `cn:glm-5.3-flash`, `zd/gpt-6-sol` and `zd/gemini-4-argon` came from models.dev.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · maximhq/bifrost · @sidbharth](https://github.com/maximhq/bifrost/pull/8751)
> | `z-ai/glm-5.3-flash` | reasoning, fallback | NEAR AI-hosted reasoning model; too slow for the 30s chat-stream timeout |
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · misospace/courier · @itsmiso-ai](https://github.com/misospace/courier/pull/831)
> separate reviewer session on the same model family (GLM-5.3-Flash, no model diversity available). Four findings fixed: ownership cross-validation lives in `charts/courier/templates/common.yaml.tpl` (not `secure.yaml.tpl`), isolation test
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · pytorch/pytorch · @oonyshch](https://github.com/pytorch/pytorch/pull/204800)
> | router softmax, 288 experts (GLM-5.3-Flash) | 16 tokens | 1.75x | 1.01x | 1.7x at 16384 tokens (14.1 to 8.1 us) |
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · renj-arch/dimsred · @renj-arch](https://github.com/renj-arch/dimsred/pull/86)
> 200 on 2026-11-13 (`nemotron-3-ultra`, `nemotron-3.5-super-vl`, `nemotron-3.5-lightning`, `nemotron-3.5-bolt`, `minimax-m3.1-flash`, `glm-5.3-flash`). Default is `nvidia/nemotron-3-ultra-550b-a55b`. Retired ids are recorded in the file as a comment with EOL dates,
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · rodkisten/photointel · @renovate[bot]](https://github.com/rodkisten/photointel/pull/145)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sadabaevb/ainek · @sadabaevb](https://github.com/sadabaevb/ainek/pull/105)
> - **#84** is for `z-ai/glm-5.3-flash`: the same key and the same launcher our verifiers log, with release marks.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sammasak/nixos-config · @sammasak](https://github.com/sammasak/nixos-config/pull/17)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sgl-project/sglang-torchtpu · @lk-chen](https://github.com/sgl-project/sglang-torchtpu/pull/2050)
> On GLM-5.3-Flash with attention DP8 (one TPU v7x 2x2x1 host, AgentX trace replay), round robin caches 0.22 of prompt tokens at c16, against a theoretical
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sgl-project/sglang-torchtpu · @HarutMov](https://github.com/sgl-project/sglang-torchtpu/pull/2132)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sgl-project/sglang-torchtpu · @Bob-Chen222](https://github.com/sgl-project/sglang-torchtpu/pull/2139)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @eppaneamd](https://github.com/sgl-project/sglang/pull/46578)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @siliangchen-amd](https://github.com/sgl-project/sglang/pull/50196)
> mHC models (the DeepSeek-V4 family, GLM-5.3-Flash) run the unfused mHC path: a chain of small kernels
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @ischencheng](https://github.com/sgl-project/sglang/pull/50213)
> no longer fit next to the running requests. GLM-5.3-Flash NVFP4 on 2x B200 (TP2, the 0.9 split that was its default before #50018: 2,969,600 KV
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · uwuclxdy/ai-pricelog · @cldbot](https://github.com/uwuclxdy/ai-pricelog/pull/921)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @HollowMan6](https://github.com/vllm-project/vllm/pull/56327)
> [LoRA][Model] Add LoRA support for GLM-5.3-Flash <!-- markdownlint-disable -->
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @MIR-AMD](https://github.com/vllm-project/vllm/pull/60783)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @cjackal](https://github.com/vllm-project/vllm/pull/62515)
> In conjunction with #60229, support adaptive verification for GLM-5.3-Flash on Hopper GPUs by overriding `FlashInferMLASparseSM90Builder.get_varlen_cudagraph_max_query_len`.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @kirillbilchenko](https://github.com/vllm-project/vllm/pull/65240)
> compressed scale format (CSF) in GPU memory. On GLM-5.3-Flash with TP2, each rank uses 3.53 GiB less memory, and the KV cache holds 30.6% more
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @jpvillam-amd](https://github.com/vllm-project/vllm/pull/65716)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @tuukkjs](https://github.com/vllm-project/vllm/pull/66563)
> (open) edits the deprecated shared sizes. #63070 (draft, GLM-5.3-Flash) and #66320 (Qwen3.5) would move more models to breakable graphs on gfx950, which then get these
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @cjluo-nv](https://github.com/vllm-project/vllm/pull/66717)
> by ModelOpt itself (NVIDIA/Model-Optimizer#3176), large MoE models (e.g. GLM-5.3-Flash), lm-eval accuracy, layerwise weight reload, EPLB, experts with biases.
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · 183600/dyn_csa_experiment · @github-actions[bot]](https://github.com/183600/dyn_csa_experiment/commit/3fa3c6d2d0ec744d007ebed9e6c815f530a9732d)
> auto: iteration 1-bug [model: nvidia/z-ai/glm-5.3-flash]
- 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),
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · agentgateway/agentgateway · @github-actions[bot]](https://github.com/agentgateway/agentgateway/commit/b7f833ec371abdb5a58fe64c9a7409a51cd1d11c)
> json.providers.nebius.models["zai-org/GLM-5.3-Flash"].reasoning.effort[2] = "max";
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/27ce09d31ed2708b956c634158f2f5c00ebec40f)
> Generated-By: pi 1.5.2 (glm-5.3-flash @ zhipuai-coding-plan, reasoning=max)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/3f4217612dff93c50b0922462516a5393bddcd74)
> Generated-By: pi 1.5.2 (glm-5.3-flash @ zhipuai-coding-plan, reasoning=max)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/9ac4b4936a73448bef1341f00c3b4d81c5371244)
> Generated-By: pi 1.5.2 (glm-5.3-flash @ zhipuai-coding-plan, reasoning=max)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/9c7d39f3bcea8136b1bb137672c28f694bc83c8e)
> Generated-By: pi 1.5.2 (glm-5.3-flash @ zhipuai-coding-plan, reasoning=max)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · databricks/unity-gateway · @lilly-luo](https://github.com/databricks/unity-gateway/commit/d20e4156877a491ce4d0916a677e603fc1748291)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · detrin/202611_AI_tinkers · @detrin](https://github.com/detrin/202611_AI_tinkers/commit/aff272d811b6c7dc6b41695baddb2b0a8b8a5143)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · g00cey/tluna · @g00cey](https://github.com/g00cey/tluna/commit/99d9fdb75f38230aeb80c5ac98af6c36ffdc8a8f)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · imoes/CentralStation · @unknown](https://github.com/imoes/CentralStation/commit/6a48ff09c3f065874f517c7e1e8fbf58305a1cc7)
> After the global LLM connector moved to llmbase.ai (z-ai/glm-5.3-flash), every tool call
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · ishan-parihar/artificial-route · @ishan-parihar](https://github.com/ishan-parihar/artificial-route/commit/fdff2e86534f31c7da83308617b41736d2a4839f)
> breaker then cooled every healthy sibling model — glm-5.3-flash never failed yet was blocked by is_cooling_for ORing
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · isotope13-dev/traits-dev · @unknown](https://github.com/isotope13-dev/traits-dev/commit/07bfaf73b5088ebfdb6e28964c1c30752f48a4f1)
> Model: opencode:zai-coding-plan/glm-5.3-flash@high
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · isotope13-dev/traits-dev · @unknown](https://github.com/isotope13-dev/traits-dev/commit/0a346523603a8deb5a4000b5a7c3658d58bd6b11)
> Model: opencode:zai-coding-plan/glm-5.3-flash@high
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · isotope13-dev/traits-dev · @unknown](https://github.com/isotope13-dev/traits-dev/commit/1ca3382cd05866d16f2252c742298608bc700406)
> Model: opencode:zai-coding-plan/glm-5.3-flash@high
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · juliolv/portfolio · @juliolv](https://github.com/juliolv/portfolio/commit/c9dec90b7e4aa08f93b00499648bcf8909939564)
> build (deepseek-v4.1-flash) -> audit (qwen3.8-flash) -> review (glm-5.3-flash as mandated) -> design (gpt-6-luna). The auditor is a different model family
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · leshicorn/email-bot · @unknown](https://github.com/leshicorn/email-bot/commit/820e8c6aa70466ee24eefd5d236f35c763b214ca)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · metaviews/jessehirsh.com · @metaviews](https://github.com/metaviews/jessehirsh.com/commit/6d2c5cfdf5cff5d07842a663d22995042028da78)
> z-ai/glm-5.3-flash as fallback, and a 404 'no provider serves this model'
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · nsbradley88/talus-public · @nsbradley88](https://github.com/nsbradley88/talus-public/commit/e5edb0e9eb2b505e3f936702706a344b6abb81b6)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · opencrabs/opencrabs · @adolfousier](https://github.com/opencrabs/opencrabs/commit/202df15feaba2058666b2c014a438f6c6bb919b8)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · phuchello2811-web/GLM · @doanbaphu](https://github.com/phuchello2811-web/GLM/commit/c2e584b529438b6545990d989949d33eb721b741)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · psyb0t/peen · @psyb0t](https://github.com/psyb0t/peen/commit/920df856db2c14dd9b510f302a99838a929b5e55)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · raidenyn/veles-android · @raidenyn-shadow](https://github.com/raidenyn/veles-android/commit/8de11f6ee3a51b450b7e4b885ef2894bef753d9c)
> the B5/v4 implementation and all integrations by actual ollama-cloud/glm-5.3-flash sessions (opencode-db safe metadata in package1-b5-v2-20261028/provenance/finish-phase-model-metadata.json); the earlier reviews were actually GPT (openai/gpt-5.6-sol high: windows-strict 520c2edd…,
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]](https://github.com/renj-arch/dimsred/commit/308c451102a20ff7d19923ae1a9c969a60f7b1d7)
- 2026-11-13T19:02:22.635Z · [GitHub search · Z.ai · commits · sgl-project/sglang-torchtpu · @Lumosis](https://github.com/sgl-project/sglang-torchtpu/commit/fc6c485b93f57712c78f47ded07788b7134f8d09)
- 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 · zlxlabs/ci-infra-canary · @unknown](https://github.com/zlxlabs/ci-infra-canary/commit/806d01b3c555f7ffe529d3c2be3eb949143f7fd0)
> Agent-Model: glm-5.3-flash Agent-Effort: high

## Liên kết bằng chứng

- [Arena](https://arena.ai)
- [Arena · leaderboards](https://arena.ai/leaderboard)
- [Artificial Analysis · benchmarks](https://artificialanalysis.ai/models)
- [Command Code · models](https://commandcode.ai/docs/reference/cli/models)
- [zai-model-index](https://docs.z.ai/api-reference/llm/chat-completion)
- [zai-pricing](https://docs.z.ai/guides/overview/pricing)
- [review](https://docs.z.ai/guides/vlm/glm-5.3-flash)
- [GitHub search · Z.ai · commits · 183600/dyn_csa_experiment · @github-actions[bot]](https://github.com/183600/dyn_csa_experiment/commit/3fa3c6d2d0ec744d007ebed9e6c815f530a9732d)
- [GitHub search · Z.ai · commits · 520042/aigw-gateway-panel · @520042](https://github.com/520042/aigw-gateway-panel/commit/2da0eb83b7759ce9f1b93102cbf9f0f1ee5ac1de)
- [GitHub search · Z.ai · pulls · Augustas11/macprovider · @Augustas11](https://github.com/Augustas11/macprovider/pull/2342)
- [GitHub search · Z.ai · pulls · BerriAI/litellm · @xinglan163](https://github.com/BerriAI/litellm/pull/51652)
- [GitHub search · Z.ai · pulls · BerryUIKI/CatCup-Tavern · @BerryUIKI](https://github.com/BerryUIKI/CatCup-Tavern/pull/81)
- [GitHub search · Z.ai · pulls · C2SM/icon4py · @egparedes](https://github.com/C2SM/icon4py/pull/1547)
- [GitHub search · Z.ai · pulls · CYBERSZP0NT/szmelc-router · @sernik77](https://github.com/CYBERSZP0NT/szmelc-router/pull/7)
- [GitHub search · Z.ai · pulls · IBM/Evoflux · @renovate[bot]](https://github.com/IBM/Evoflux/pull/12)
- [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/arena-fortress · @yukon-autoresearch[bot]](https://github.com/Layr-Labs/arena-fortress/pull/187)
- [GitHub search · Z.ai · pulls · Layr-Labs/d-inference · @jonathan308](https://github.com/Layr-Labs/d-inference/pull/2086)
- [GitHub search · Z.ai · pulls · Layr-Labs/flock-challenge · @yukon-autoresearch[bot]](https://github.com/Layr-Labs/flock-challenge/pull/5592)
- [GitHub search · Z.ai · pulls · Lore-Hex/quill-router · @jasminelee](https://github.com/Lore-Hex/quill-router/pull/2534)
- [GitHub search · Z.ai · pulls · Max-Health-Inc/config · @quotentiroler](https://github.com/Max-Health-Inc/config/pull/13)
- [GitHub search · Z.ai · pulls · Max-Health-Inc/config · @quotentiroler](https://github.com/Max-Health-Inc/config/pull/18)
- [GitHub search · Z.ai · pulls · NVIDIA-NeMo/Megatron-Bridge · @kamran-nvidia](https://github.com/NVIDIA-NeMo/Megatron-Bridge/pull/6909)
- [GitHub search · Z.ai · pulls · NVIDIA/Model-Optimizer · @cjluo-nv](https://github.com/NVIDIA/Model-Optimizer/pull/3351)
- [GitHub search · Z.ai · pulls · NVIDIA/Model-Optimizer · @shengliangxu](https://github.com/NVIDIA/Model-Optimizer/pull/3368)
- [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux](https://github.com/NVIDIA/TensorRT-LLM/pull/21019)
- [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @ruocheng-nv](https://github.com/NVIDIA/TensorRT-LLM/pull/22254)
- [GitHub search · Z.ai · pulls · NVIDIA/cudnn-frontend · @Anerudhan](https://github.com/NVIDIA/cudnn-frontend/pull/1847)
- [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @YouNeedCryDear](https://github.com/NVIDIA/hyperflare-inference/pull/172)
- [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @original-el8](https://github.com/NVIDIA/hyperflare-inference/pull/217)
- [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @original-el8](https://github.com/NVIDIA/hyperflare-inference/pull/232)
- [GitHub search · Z.ai · pulls · NVIDIA/hyperflare-inference · @aarongiuffre](https://github.com/NVIDIA/hyperflare-inference/pull/59)
- [GitHub search · Z.ai · pulls · NousResearch/hermes-agent · @glitchbunny0](https://github.com/NousResearch/hermes-agent/pull/137470)
- [GitHub search · Z.ai · pulls · OpenHands/OpenHands · @sanchitmonga22](https://github.com/OpenHands/OpenHands/pull/19468)
- [GitHub search · Z.ai · pulls · Pb314314/vllm · @Pb314314](https://github.com/Pb314314/vllm/pull/35)
- [GitHub search · Z.ai · pulls · QNFO/qnfo-workers · @rwnq8](https://github.com/QNFO/qnfo-workers/pull/11591)
- [GitHub search · Z.ai · pulls · ROCm/aiter · @sumin-hong](https://github.com/ROCm/aiter/pull/7184)
- [GitHub search · Z.ai · pulls · ROCm/aiter · @sumin-hong](https://github.com/ROCm/aiter/pull/7374)
- [GitHub search · Z.ai · pulls · ROCm/aiter · @eppaneamd](https://github.com/ROCm/aiter/pull/7680)
- [GitHub search · Z.ai · pulls · ROCm/aiter · @eppaneamd](https://github.com/ROCm/aiter/pull/7681)
- [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/58)
- [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/60)
- [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/61)
- [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/62)
- [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/63)
- [GitHub search · Z.ai · pulls · SwarnimWalavalkar/noesis · @SwarnimWalavalkar](https://github.com/SwarnimWalavalkar/noesis/pull/64)
- [GitHub search · Z.ai · pulls · TigreGotico/linguonnx · @renovate[bot]](https://github.com/TigreGotico/linguonnx/pull/101)
- [GitHub search · Z.ai · commits · agentgateway/agentgateway · @github-actions[bot]](https://github.com/agentgateway/agentgateway/commit/b7f833ec371abdb5a58fe64c9a7409a51cd1d11c)
- [GitHub search · Z.ai · pulls · agentgateway/agentgateway · @github-actions[bot]](https://github.com/agentgateway/agentgateway/pull/4377)
- [GitHub search · Z.ai · pulls · alecpullen/marshal · @alecpullen](https://github.com/alecpullen/marshal/pull/64)
- [GitHub search · Z.ai · pulls · alexsantossp71-lgtm/remedios_app · @alexsantossp71-lgtm](https://github.com/alexsantossp71-lgtm/remedios_app/pull/14)
- [GitHub search · Z.ai · pulls · ameetmadan/lautli · @renovate[bot]](https://github.com/ameetmadan/lautli/pull/35)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @jIrwinCline](https://github.com/anomalyco/models.dev/pull/13426)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13561)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @NachiketKandari](https://github.com/anomalyco/models.dev/pull/13577)
- [GitHub search · Z.ai · pulls · ashcoft/document-mcp · @renovate[bot]](https://github.com/ashcoft/document-mcp/pull/966)
- [GitHub search · Z.ai · pulls · ashhart/TensorFold · @Bizuayeu](https://github.com/ashhart/TensorFold/pull/3151)
- [GitHub search · Z.ai · pulls · ashhart/TensorFold · @Bizuayeu](https://github.com/ashhart/TensorFold/pull/3249)
- [GitHub search · Z.ai · pulls · basetenlabs/baseten-cli · @sanieldalib](https://github.com/basetenlabs/baseten-cli/pull/264)
- [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/27ce09d31ed2708b956c634158f2f5c00ebec40f)
- [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/3f4217612dff93c50b0922462516a5393bddcd74)
- [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/9ac4b4936a73448bef1341f00c3b4d81c5371244)
- [GitHub search · Z.ai · commits · brightmeows/bmsrs · @brightmeows](https://github.com/brightmeows/bmsrs/commit/9c7d39f3bcea8136b1bb137672c28f694bc83c8e)
- [GitHub search · Z.ai · pulls · cassandre60/ChessSRS · @cassandre60](https://github.com/cassandre60/ChessSRS/pull/658)
- [GitHub search · Z.ai · pulls · crewAIInc/crewAI · @ats3v](https://github.com/crewAIInc/crewAI/pull/9316)
- [GitHub search · Z.ai · commits · databricks/unity-gateway · @lilly-luo](https://github.com/databricks/unity-gateway/commit/d20e4156877a491ce4d0916a677e603fc1748291)
- [GitHub search · Z.ai · pulls · ddalcu/mlx-serve · @davidtai](https://github.com/ddalcu/mlx-serve/pull/1192)
- [GitHub search · Z.ai · commits · detrin/202611_AI_tinkers · @detrin](https://github.com/detrin/202611_AI_tinkers/commit/aff272d811b6c7dc6b41695baddb2b0a8b8a5143)
- [GitHub search · Z.ai · pulls · duketopceo/open-computer · @duketopceo](https://github.com/duketopceo/open-computer/pull/163)
- [GitHub search · Z.ai · pulls · egonSchiele/agency-lang · @egonSchiele](https://github.com/egonSchiele/agency-lang/pull/1466)
- [GitHub search · Z.ai · pulls · figranium/fiptcha · @renovate[bot]](https://github.com/figranium/fiptcha/pull/39)
- [GitHub search · Z.ai · commits · g00cey/tluna · @g00cey](https://github.com/g00cey/tluna/commit/99d9fdb75f38230aeb80c5ac98af6c36ffdc8a8f)
- [GitHub search · Z.ai · pulls · gcanlin/vllm · @gcanlin](https://github.com/gcanlin/vllm/pull/15)
- [GitHub search · Z.ai · pulls · ggml-org/llama.cpp · @snakeice](https://github.com/ggml-org/llama.cpp/pull/32212)
- [GitHub search · Z.ai · pulls · harbor-framework/terminal-bench-science · @RishabhPatil](https://github.com/harbor-framework/terminal-bench-science/pull/2266)
- [GitHub search · Z.ai · commits · imoes/CentralStation · @unknown](https://github.com/imoes/CentralStation/commit/6a48ff09c3f065874f517c7e1e8fbf58305a1cc7)
- [GitHub search · Z.ai · commits · ishan-parihar/artificial-route · @ishan-parihar](https://github.com/ishan-parihar/artificial-route/commit/fdff2e86534f31c7da83308617b41736d2a4839f)
- [GitHub search · Z.ai · commits · islgit07/zcodebride-for-magpie · @islgit07](https://github.com/islgit07/zcodebride-for-magpie/commit/e8043524682b1d5f91b4dea386c81e5eb603b025)
- [GitHub search · Z.ai · commits · isotope13-dev/traits-dev · @unknown](https://github.com/isotope13-dev/traits-dev/commit/07bfaf73b5088ebfdb6e28964c1c30752f48a4f1)
- [GitHub search · Z.ai · commits · isotope13-dev/traits-dev · @unknown](https://github.com/isotope13-dev/traits-dev/commit/0a346523603a8deb5a4000b5a7c3658d58bd6b11)
- [GitHub search · Z.ai · commits · isotope13-dev/traits-dev · @unknown](https://github.com/isotope13-dev/traits-dev/commit/1ca3382cd05866d16f2252c742298608bc700406)
- [GitHub search · Z.ai · commits · juliolv/portfolio · @juliolv](https://github.com/juliolv/portfolio/commit/8dc315ca3ba91a8a0a5ab477a25ee07feb195cd9)
- [GitHub search · Z.ai · commits · juliolv/portfolio · @juliolv](https://github.com/juliolv/portfolio/commit/c9dec90b7e4aa08f93b00499648bcf8909939564)
- [GitHub search · Z.ai · pulls · kaina-visualsoftware/QA-Hub · @kaina-visualsoftware](https://github.com/kaina-visualsoftware/QA-Hub/pull/114)
- [GitHub search · Z.ai · pulls · kollaborai/kollab · @kollaborai](https://github.com/kollaborai/kollab/pull/954)
- [GitHub search · Z.ai · pulls · leptoskit/leptoskit · @ifiokjr](https://github.com/leptoskit/leptoskit/pull/828)
- [GitHub search · Z.ai · commits · leshicorn/email-bot · @unknown](https://github.com/leshicorn/email-bot/commit/820e8c6aa70466ee24eefd5d236f35c763b214ca)
- [GitHub search · Z.ai · pulls · lidge-jun/opencodex · @andrew05060414](https://github.com/lidge-jun/opencodex/pull/8708)
- [GitHub search · Z.ai · pulls · maximhq/bifrost · @sidbharth](https://github.com/maximhq/bifrost/pull/8751)
- [GitHub search · Z.ai · commits · metaviews/jessehirsh.com · @metaviews](https://github.com/metaviews/jessehirsh.com/commit/6d2c5cfdf5cff5d07842a663d22995042028da78)
- [GitHub search · Z.ai · pulls · misospace/courier · @itsmiso-ai](https://github.com/misospace/courier/pull/831)
- [GitHub search · Z.ai · commits · nsbradley88/talus-public · @nsbradley88](https://github.com/nsbradley88/talus-public/commit/e5edb0e9eb2b505e3f936702706a344b6abb81b6)
- [GitHub search · Z.ai · commits · opencrabs/opencrabs · @adolfousier](https://github.com/opencrabs/opencrabs/commit/202df15feaba2058666b2c014a438f6c6bb919b8)
- [GitHub search · Z.ai · commits · phuchello2811-web/GLM · @doanbaphu](https://github.com/phuchello2811-web/GLM/commit/c2e584b529438b6545990d989949d33eb721b741)
- [GitHub search · Z.ai · commits · psyb0t/peen · @psyb0t](https://github.com/psyb0t/peen/commit/920df856db2c14dd9b510f302a99838a929b5e55)
- [GitHub search · Z.ai · pulls · pytorch/pytorch · @oonyshch](https://github.com/pytorch/pytorch/pull/204800)
- [GitHub search · Z.ai · commits · raidenyn/veles-android · @raidenyn-shadow](https://github.com/raidenyn/veles-android/commit/8de11f6ee3a51b450b7e4b885ef2894bef753d9c)
- [GitHub search · Z.ai · commits · raspy135/tideLM · @unknown](https://github.com/raspy135/tideLM/commit/2b4598f71fbcebd4118c236e8e290cb1533fb4c8)
- [GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]](https://github.com/renj-arch/dimsred/commit/308c451102a20ff7d19923ae1a9c969a60f7b1d7)
- [GitHub search · Z.ai · pulls · renj-arch/dimsred · @renj-arch](https://github.com/renj-arch/dimsred/pull/86)
- [GitHub search · Z.ai · pulls · rodkisten/photointel · @renovate[bot]](https://github.com/rodkisten/photointel/pull/145)
- [GitHub search · Z.ai · pulls · sadabaevb/ainek · @sadabaevb](https://github.com/sadabaevb/ainek/pull/105)
- [GitHub search · Z.ai · pulls · sammasak/nixos-config · @sammasak](https://github.com/sammasak/nixos-config/pull/17)
- [GitHub search · Z.ai · commits · sgl-project/sglang-torchtpu · @Lumosis](https://github.com/sgl-project/sglang-torchtpu/commit/fc6c485b93f57712c78f47ded07788b7134f8d09)
- [GitHub search · Z.ai · pulls · sgl-project/sglang-torchtpu · @lk-chen](https://github.com/sgl-project/sglang-torchtpu/pull/2050)
- [GitHub search · Z.ai · pulls · sgl-project/sglang-torchtpu · @HarutMov](https://github.com/sgl-project/sglang-torchtpu/pull/2132)
- [GitHub search · Z.ai · pulls · sgl-project/sglang-torchtpu · @Bob-Chen222](https://github.com/sgl-project/sglang-torchtpu/pull/2139)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @eppaneamd](https://github.com/sgl-project/sglang/pull/46578)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @siliangchen-amd](https://github.com/sgl-project/sglang/pull/50196)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @ischencheng](https://github.com/sgl-project/sglang/pull/50213)
- [GitHub search · Z.ai · commits · unixmonks/gpu · @unixmonks](https://github.com/unixmonks/gpu/commit/3f5cd7b12a59244e4ccb4350687a7326e9dd62fe)
- [GitHub search · Z.ai · pulls · uwuclxdy/ai-pricelog · @cldbot](https://github.com/uwuclxdy/ai-pricelog/pull/921)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @HollowMan6](https://github.com/vllm-project/vllm/pull/56327)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @MIR-AMD](https://github.com/vllm-project/vllm/pull/60783)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @cjackal](https://github.com/vllm-project/vllm/pull/62515)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @kirillbilchenko](https://github.com/vllm-project/vllm/pull/65240)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @jpvillam-amd](https://github.com/vllm-project/vllm/pull/65716)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @tuukkjs](https://github.com/vllm-project/vllm/pull/66563)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @cjluo-nv](https://github.com/vllm-project/vllm/pull/66717)
- [GitHub search · Z.ai · commits · zlxlabs/ci-infra-canary · @unknown](https://github.com/zlxlabs/ci-infra-canary/commit/806d01b3c555f7ffe529d3c2be3eb949143f7fd0)
- [hf-author-artifacts:zai-org](https://huggingface.co/api/models/zai-org/GLM-5.3-Flash/paths-info/46a050bec13002ad29ee795c16e61cf4fa3c4a9c)
- [Hugging Face · nvidia](https://huggingface.co/nvidia/GLM-5.3-Flash-NVFP4)
- [huggingface-router](https://huggingface.co/zai-org/GLM-5.3-Flash)
- [models-dev](https://models.dev/#GLM-5.3-Flash)
- [models.dev · catalogue](https://models.dev/#GLM-5.3-Flash-NVFP4)
- [models.dev · catalogue](https://models.dev/#glm-5-3-flash)
- [models.dev · catalogue](https://models.dev/#glm-5.3-flash)
- [models.dev · catalogue](https://models.dev/#glm-5.3-flash-fp4)
- [models.dev · catalogue](https://models.dev/#glm-5.3-flash-free)
- [models.dev · catalogue](https://models.dev/#glm-5p3-flash)
- [models.dev · catalogue](https://models.dev/#glm5.3-flash)
- [models.dev · catalogue](https://models.dev/#morph-glm53flash)
- [models.dev · catalogue](https://models.dev/#umans-glm-5.3-flash)
- [models.dev · catalogue](https://models.dev/#z-ai-glm-5-3-flash)
- [models.dev · catalogue](https://models.dev/#zai-glm-5-3-flash)
- [OpenCode · discovery](https://opencode.ai/data/zhipuai/glm-5-3-flash)
- [opencode-go](https://opencode.ai/inference/go/v1/models)
- [OpenCode Zen · models](https://opencode.ai/zen)
- [OpenRouter](https://openrouter.ai/api/v1/models)
- [OpenRouter](https://openrouter.ai/z-ai/glm-5.3-flash)
- [OpenRouter](https://openrouter.ai/z-ai/glm-5.3-flash:batch)
- [Vercel AI Gateway](https://vercel.com/ai-gateway)
- [Arena · leaderboards](https://z.ai/blog/glm-5.3)

## Tín hiệu

- [GLM-5.3 Flash được phát hiện trên OpenRouter](https://alexgetman.com/vi/signals/2026/09/08/z-ai-glm-5-3-flash/)