# GLM-4.7 Flash

GLM-4.7 Flash er en model fra Z.ai med åbne vægte, først registreret den 2026-09-17; lanceringsdatoen er ikke fastlagt. Kontekstvinduet er 202.752 tokens.

- Udvikler: Z.ai
- Id: zai-org/GLM-4.7-Flash
- Ifølge rapporter: 2026-10-02T14:56:38.000Z
- Observation: 2026-09-17T16:04:11.848Z
  - [kildelink](https://huggingface.co/zai-org/GLM-4.7-Flash)
- Status: Lanceret
- Vægtversion: 2026-01-19
  - [kildelink](https://huggingface.co/api/models/zai-org/GLM-4.7-Flash/paths-info/7dd20894a642a0aa287e9827cb1a1f7f91386b67)
- Kanonisk adresse: https://alexgetman.com/da/models/z-ai/glm-4-7-flash-800/

## Spørgsmål

### Hvor stort er kontekstvinduet for GLM-4.7 Flash?

Kontekstvinduet er 202.752 tokens.

### Er vægtene for GLM-4.7 Flash offentligt tilgængelige?

Ja. Z.ai offentliggør vægtene.

### Hvornår blev GLM-4.7 Flash lanceret?

Lanceringsdatoen er ikke fastlagt. Signal Forge registrerede modellen første gang den 2026-09-17.

## Tidslinje

- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · afjcjsbx/picoclaw · @trufae](https://github.com/afjcjsbx/picoclaw/pull/615)
> model invocation. The local configuration names `nemo` → `glm-4.7-flash`, but that model was not used for an end-to-end image-description test. The model on the gateway
- 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 · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13561)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @umarkovi-amd](https://github.com/vllm-project/vllm/pull/61872)
> inactive since #46009. On Radeon Pro W7900 with GLM-4.7-Flash at concurrency 1, this restores 4.5–10.8 % output throughput and 10–13 % TTFT. Related: #46009, #46381
- 2026-11-15T10:38:52.083Z · [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/428)
> el adaptador **ya existente** `cloudflareWorkersAiProvider.complete` con modelo fijo `@cf/zai-org/glm-4.7-flash`, 384 output tokens, timeout, 1 intento, sin tools, sin web search, sin Vercel/OpenAI fallback. Resultado/uso/hash se
- 2026-11-15T10:38:52.083Z · [GitHub search · Z.ai · pulls · can1357/oh-my-pi · @andrebrait](https://github.com/can1357/oh-my-pi/pull/14458)
> refusal without consent, immediate running state, a real GLM-4.7-Flash cited result, independently confirmed application, idempotent replay, and getter/state equality. Temporary credentials and fixtures were removed.
- 2026-11-15T10:38:52.083Z · [GitHub search · Z.ai · pulls · quiquandon-oss/PulseWorkerV2 · @quiquandon-oss](https://github.com/quiquandon-oss/PulseWorkerV2/pull/135)
> the 2026-11-14 scope lock: RSS/Atom/official feeds only, optional GLM-4.7-flash with a hard daily Neuron budget, and no new providers, models or paid dependencies. The design
- 2026-11-15T10:38:52.083Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @ami-GS](https://github.com/sgl-project/sglang/pull/50557)
> Found while serving `zai-org/GLM-4.7-Flash` with default arguments on an `sm100` target, where the first prefill request immediately crashes in FlashInfer:
- 2026-11-15T10:56:25.456Z · [GitHub search · Z.ai · pulls · GoDanceAi/godance · @SummerTiger](https://github.com/GoDanceAi/godance/pull/34)
> id not in the provider's model list. ernie-5.1, glm-4.7-flash: text only. kimi-k2.6, minimax-m2.7: vision documented for a newer family only. qwen-3.6, qwen-3.6-coder: the documented ids
- 2026-11-15T10:56:25.456Z · [GitHub search · Z.ai · pulls · HYGON-AI/vllm-plugin-das · @alexanderbin123](https://github.com/HYGON-AI/vllm-plugin-das/pull/409)
> Additional GLM-4.7-Flash BF16 TP2 validation on gfx936, same frozen requests, official TRITON_MLA/default Graph/prefix: official baseline and candidate both score **0/32 raw, 30/32 format-normalized**, but the
- 2026-11-15T10:56:25.456Z · [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/731)
> | bumped | — | — | \| GLM-4.7-Flash \| Free \| Free \| Free \| Free \| |
- 2026-11-15T10:56:25.456Z · [GitHub search · Z.ai · pulls · thisishaidee/kivora · @thisishaidee](https://github.com/thisishaidee/kivora/pull/21)
> adapter for Cloudflare Workers AI using the free-tier `@cf/zai-org/glm-4.7-flash` model.
- 2026-11-15T11:16:57.851Z · [GitHub search · Z.ai · pulls · LevenST24/galgame2voice · @LevenST24](https://github.com/LevenST24/galgame2voice/pull/518)
- 2026-11-15T11:16:57.851Z · [GitHub search · Z.ai · pulls · chadkhalil21-svg/Plenum-Scientific-Intelligence · @chadkhalil21-svg](https://github.com/chadkhalil21-svg/Plenum-Scientific-Intelligence/pull/731)
> git blob), same signed original Cloudflare Worker, same `glm-4.7-flash` model and original Durable Object 4,000/day local usage bound. Include actual original public source, original bounded
- 2026-11-15T11:16:57.851Z · [GitHub search · Z.ai · pulls · diazMelgarejo/orama-system · @diazMelgarejo](https://github.com/diazMelgarejo/orama-system/pull/507)
> The runner still starts at `glm-4.7-flash`. Success, billing code 1113, credentials, throttle, and uncertain execution stop the chain. A verified model miss is what advances
- 2026-11-15T11:16:57.851Z · [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/724)
- 2026-11-15T11:16:57.851Z · [GitHub search · Z.ai · pulls · salamou1944/Salamou-31 · @salamou1944](https://github.com/salamou1944/Salamou-31/pull/72)
> probe's default `@cf/meta/llama-3.1-8b-instruct` model, deprecated on 2026-05-30, with `@cf/zai-org/glm-4.7-flash`.
- 2026-11-15T11:17:58.987Z · [GitHub search · Z.ai · commits · 1essalion1-sudo/Nexora-exotic · @1essalion1-sudo](https://github.com/1essalion1-sudo/Nexora-exotic/commit/2c785ca7c759604849c408d747eff57326bd8320)
> Document Neora website and GLM-4.7-Flash model credit
- 2026-11-15T11:17:58.987Z · [GitHub search · Z.ai · commits · lettroi/safeshell-pro · @lettroi](https://github.com/lettroi/safeshell-pro/commit/051be91c8ab11836df7f3dad589589aa4c5339d8)
> - 5 enabled free models (glm-4.7-flash disabled by default due to upstream 429)
- 2026-11-15T11:34:45.313Z · [GitHub search · Z.ai · pulls · JoshCLWren/comic-pile · @JoshCLWren](https://github.com/JoshCLWren/comic-pile/pull/5138)
> Model: glm-4.7-flash Source: z-ai
- 2026-11-15T11:34:45.313Z · [GitHub search · Z.ai · pulls · chadkhalil21-svg/Plenum-Scientific-Intelligence · @chadkhalil21-svg](https://github.com/chadkhalil21-svg/Plenum-Scientific-Intelligence/pull/711)
> adds the upstream native `[ai]` binding to free-eligible `@cf/zai-org/glm-4.7-flash`, and routes ORIGINAL owner-authorized OpenHands issue jobs through a narrowly compatible endpoint. No new deployment, host,
- 2026-11-15T11:34:45.313Z · [GitHub search · Z.ai · pulls · diazMelgarejo/orama-system · @diazMelgarejo](https://github.com/diazMelgarejo/orama-system/pull/506)
- 2026-11-15T11:34:45.313Z · [GitHub search · Z.ai · pulls · eaitbrahim/NarratoFlow · @eaitbrahim](https://github.com/eaitbrahim/NarratoFlow/pull/187)
> - llm row: local Ollama GLM-4.7-Flash Q4_K_M, $0. catt row: linux/arm64 Docker container on the same Mac, CPU. No pyproject extra (the universal uv lock
- 2026-11-15T11:34:45.313Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @bvolpato](https://github.com/sgl-project/sglang/pull/48181)
> "stop"`. This happened with Llama-3.2-1B using `pythonic` and GLM-4.7-Flash using `glm47`. Streaming requests already returned the calls in `message.tool_calls`.
- 2026-11-15T11:34:59.939Z · [GitHub search · Z.ai · commits · aphrody-labs/aphrody · @aphrody-dev](https://github.com/aphrody-labs/aphrody/commit/375b3ff3cdb5765c0bc814b5e71b8d336a237f36)
> packages/design tokens; verified live: pong served by workers-ai glm-4.7-flash after a paid-only model was skipped
- 2026-11-15T11:50:41.426Z · [GitHub search · Z.ai · pulls · diazMelgarejo/Perpetua-Tools · @diazMelgarejo](https://github.com/diazMelgarejo/Perpetua-Tools/pull/506)
- 2026-11-15T12:08:55.383Z · [GitHub search · Z.ai · pulls · SonicStar-Solutions/agentic-inbox · @cvbutani](https://github.com/SonicStar-Solutions/agentic-inbox/pull/1)
> - **Injection scanner (#30).** Default is now `@cf/zai-org/glm-4.7-flash` (ID confirmed against the Workers AI catalog). A reply with no usable verdict now **fails closed** (it
- 2026-11-15T12:08:55.383Z · [GitHub search · Z.ai · pulls · brokespace/seal · @brokespace](https://github.com/brokespace/seal/pull/32)
> Cloudflare Workers AI with the account's saved models (`@cf/zai-org/glm-4.7-flash`, fallback `@cf/google/gemma-4-26b-a4b-it`). Nothing is rewritten on disk, so current users keep working and a downgrade still
- 2026-11-15T12:08:55.383Z · [GitHub search · Z.ai · pulls · methaneex-oss/AURIONS · @methaneex-oss](https://github.com/methaneex-oss/AURIONS/pull/7)
> - Cloudflare GLM-4.7-Flash and Gemma 4 26B model pages: function calling; `max_tokens` deprecated in favor of `max_completion_tokens`; GLM documents `tool_choice: required`.
- 2026-11-15T12:08:55.383Z · [GitHub search · Z.ai · pulls · spiceai/cookbook · @spiceemma](https://github.com/spiceai/cookbook/pull/771)
> Two corrections specific to GLM: GLM-4.7-Flash's GGUF (the recipe's default file, and the abliterated variant's) declares `general.architecture = deepseek2`, not `glm4moe`. So the intro and
- 2026-11-15T12:08:55.383Z · [GitHub search · Z.ai · pulls · szl-holdings/a11oy · @stephenlutar2-hash](https://github.com/szl-holdings/a11oy/pull/3405)
> Both `MODEL_CANDIDATES` (`@cf/zai-org/glm-4.7-flash`, `@cf/google/gemma-4-26b-a4b-it`) are reasoning models that emit hidden `reasoning_content` before `message.content`. With the probe's `max_new_tokens: 96` (sent as `max_completion_tokens`), the entire completion budget
- 2026-11-15T12:25:33.096Z · [GitHub search · Z.ai · pulls · ACROWN-System/AstroCrown-Web · @ASDBradford-HAAN](https://github.com/ACROWN-System/AstroCrown-Web/pull/177)
> latest heartbeat. Groq `gpt-oss-120b`, Gemini `gemini-3.8-flash` and Cloudflare `glm-4.7-flash` remain model/contract-specific blocked. Mistral remains deferred after repeated 429s; Cerebras is blocked under the no-payment-method rule;
- 2026-11-15T12:25:33.096Z · [GitHub search · Z.ai · pulls · ai-advokat/ai-advokat.github.io · @ai-advokat](https://github.com/ai-advokat/ai-advokat.github.io/pull/681)
> the timed-out Qwen recovery model with the already-supported GLM-4.7-Flash fallback with thinking disabled
- 2026-11-15T12:25:33.096Z · [GitHub search · Z.ai · pulls · laurofiorenzani/jarvis · @laurofiorenzani](https://github.com/laurofiorenzani/jarvis/pull/48)
> The chat router now hard-allows only `@cf/google/gemma-4-26b-a4b-it` and `@cf/zai-org/glm-4.7-flash` for the Cloudflare Workers Free pool. Other models, including paid-only Kimi/GLM5 and speech/deprecated models, are rejected
- 2026-11-15T12:25:33.096Z · [GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6025)
- 2026-11-15T12:42:24.308Z · [GitHub search · Z.ai · pulls · brokespace/seal · @brokespace](https://github.com/brokespace/seal/pull/23)
> - **Structured output.** `glm-4.7-flash` is not on Workers AI's JSON Mode list, so the schema is enforced by the host: lenient JSON extraction, zod validation
- 2026-11-15T12:42:24.308Z · [GitHub search · Z.ai · pulls · dannywise093-crypto/ATLAS · @dannywise093-crypto](https://github.com/dannywise093-crypto/ATLAS/pull/4)
> - Connect the open-weight GLM-4.7-Flash model as ATLAS's first hosted foundation model.
- 2026-11-15T12:58:53.386Z · [GitHub search · Z.ai · pulls · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/pull/402)
- 2026-11-15T12:58:53.386Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13603)
> - updated: `/home/runner/_work/models.dev/models.dev/providers/nano-gpt/models/z-ai/glm-4.7-flash:thinking.toml`
- 2026-11-15T13:15:13.117Z · [GitHub search · Z.ai · pulls · JoshCLWren/comic-pile · @JoshCLWren](https://github.com/JoshCLWren/comic-pile/pull/5038)
> Cloudflare Workers AI Free adapter and workers **119** (`@cf/zai-org/glm-4.7-flash`) and **120** (`@cf/google/gemma-4-26b-a4b-it`). These require `CLOUDFLARE_API_TOKEN` repository secret and `CLOUDFLARE_ACCOUNT_ID` repository variable. Absent credentials, workers remain
- 2026-11-15T13:15:13.117Z · [GitHub search · Z.ai · pulls · eltmon/overdeck · @eltmon](https://github.com/eltmon/overdeck/pull/5216)
> here. On 1.5.2, `models.json` received only `glm-5.3-flashx`, `glm-5.1`, `glm-4.7-flash`, `mimo-v2.6-pro-ultraspeed` and `grok-build-0.1`.
- 2026-11-15T13:15:13.117Z · [GitHub search · Z.ai · pulls · hale-lang/voice · @rileyr](https://github.com/hale-lang/voice/pull/221)
> put their thinking inline: the R1 distill, Qwen3-0.6B, GLM-4.7-Flash, MiMo's distill, OpenReasoning-Nemotron and Phi-4-mini-reasoning. vLLM v0.29.0 registers `deepseek_r1`, `qwen3`, `glm47` and `mimo`; each model needs
- 2026-11-15T13:15:13.117Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @Pb314314](https://github.com/vllm-project/vllm/pull/66799)
- 2026-11-15T13:31:17.785Z · [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/411)
> Supabase conservó la respuesta `LISTO`, route/provider `cloudflare-workers-ai`, modelo `@cf/zai-org/glm-4.7-flash`, `1481` tokens entrada/`3` salida y trace ID `9d09f050-695f-4628-9d7b-3fd35b2d97be`, un solo intento exitoso y ~740 ms de
- 2026-11-15T13:31:17.785Z · [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/412)
> E2E en Preview; `agi_messages` de Supabase registró modelo `@cf/zai-org/glm-4.7-flash`, respuesta `LISTO`, mismo trace ID e inferencia real. No se renueva artificialmente esa prueba.
- 2026-11-15T13:31:17.785Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @lihzamd](https://github.com/vllm-project/vllm/pull/60822)
> | Model | GLM-4.7-Flash (`Glm4MoeLiteForCausalLM`) |
- 2026-11-15T13:31:32.863Z · [GitHub search · Z.ai · commits · AmsyarAmran/Studyhub-stpm · @AmsyarAmran](https://github.com/AmsyarAmran/Studyhub-stpm/commit/595661565192032554995fb908f434bffaf7f2fe)
> Use GLM-4.7-Flash as Syar default model
- 2026-11-15T13:31:32.863Z · [GitHub search · Z.ai · commits · AmsyarAmran/Studyhub-stpm · @AmsyarAmran](https://github.com/AmsyarAmran/Studyhub-stpm/commit/b84a256df9087df2b16f9e2bae07ae25ce881d72)
> Set Syar model to GLM-4.7-Flash Set Syar model to GLM-4.7-Flash
- 2026-11-15T13:46:55.245Z · [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/77ee0cdd64b90b5a45d35155e167cadcdc89c125)
> - GLM-4.7-Flash (Reasoning)
- 2026-11-15T13:46:55.245Z · [GitHub search · Z.ai · commits · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/commit/f5e9aebda2acdaab729401d4c4391656f93399a6)
- 2026-11-15T13:46:55.245Z · [GitHub search · Z.ai · commits · rodrigueztaylor87/rod · @rodrigueztaylor87](https://github.com/rodrigueztaylor87/rod/commit/88a4dbdbf70aeeb1ade2f2fa9112403a1a007942)
> 本文详解GLM-4.7-Flash在4张RTX 4090 D上的低成本、高性能部署实践，涵盖MoE架构优势、OpenAI兼容API集成、日志驱动故障诊断、配置热更新及典型并发与服务隔离问题排查。重点突出其针对中文场景的原生理解能力、低显存占用（单卡24GB可运行）、高吞吐推理（115 tokens/s）及开箱即用特性，适用于文案生成、知识问答、技术文档辅助等真实业务。
- 2026-11-15T14:18:43.644Z · [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/410)
> proof. Reuses existing `hocker-agi` gateway and fixed native `@cf/zai-org/glm-4.7-flash`; no Worker/Pages/DNS/SQL, no account spend configuration or live inference. Cloudflare account billing permissions returned 403 and
- 2026-11-15T14:18:43.644Z · [GitHub search · Z.ai · pulls · Prool-bot/ngo-grants-facebook · @Prool-bot](https://github.com/Prool-bot/ngo-grants-facebook/pull/94)
> on explicit Workers-Free allowlist (also includes unselected free GLM-4.7-Flash; no automatic fallback or paid usage).
- 2026-11-15T14:18:43.644Z · [GitHub search · Z.ai · pulls · gorfreee/clasica_madrid · @gorfreee](https://github.com/gorfreee/clasica_madrid/pull/419)
> | IA: requests por modelo | cloudflare:@cf/zai-org/glm-4.7-flash: 5, gemini:gemini-3-flash-preview: 2, gemini:gemini-3.1-flash-lite: 1, gemini:gemini-3.5-flash: 2, gemini:gemini-3.5-flash-lite: 2, gemini:gemini-3.6-flash: 2, gemini:gemini-3.7-flash: 2, gemini:gemini-3.8-flash: 2, gemini:gemma-4-26b-a4b-it: 1, gemini:gemma-4-31b-it:
- 2026-11-15T14:18:43.644Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @hyjuunn](https://github.com/vllm-project/vllm/pull/67541)
> export MODEL=zai-org/GLM-4.7-Flash
- 2026-11-15T14:20:46.237Z · [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/d5b473e2c542a2ab30983f6c2f520723cb14a6e8)
> GLM-4.7-Flash (Reasoning) [Z AI]
- 2026-11-15T14:20:46.237Z · [GitHub search · Z.ai · commits · Nitjsefnie/claudit · @github-actions[bot]](https://github.com/Nitjsefnie/claudit/commit/7d6ca9692df859c0172871ef80de2aaa9462c08c)
> t, openai/gpt-5.2-codex, openai/gpt-oss-120b, openai/gpt-oss-20b, openai/gpt-oss-safeguard-20b, tencent/hy3-preview, xiaomi/mimo-v2.5, xiaomi/mimo-v2.5-pro, z-ai/glm-4.7-flash, z-ai/glm-5.3-prime
- 2026-11-15T14:33:20.735Z · [GitHub search · Z.ai · pulls · AlexsJones/llmfit · @jayhemnani9910](https://github.com/AlexsJones/llmfit/pull/1145)
> with Multi-head Latent Attention (DeepSeek-V2/V3, Kimi-K2, Moonlight, Kimi-VL, GLM-4.7-Flash) don't keep per-head K and V. They cache one latent of `kv_lora_rank + qk_rope_head_dim` = 512
- 2026-11-15T14:33:20.735Z · [GitHub search · Z.ai · pulls · Danish797035/harness-agent · @Danish797035](https://github.com/Danish797035/harness-agent/pull/13)
> Gemini 2.5 Flash, Groq Llama 3.3 70B, Z.ai GLM-4.7-Flash, Gemini 3.1 Flash Lite; Kimi K2 strictly excluded). Tests added: RouterPreferencesTest, ToolCallProbeAndUnifiedPoolTest. CI run 43719307999 on
- 2026-11-15T14:33:20.735Z · [GitHub search · Z.ai · pulls · kahnwong/self-hosted · @renovate[bot]](https://github.com/kahnwong/self-hosted/pull/800)
> Add PowerTokens (`api.powertokens.ai`) as an OpenAI-compatible provider. Its `glm-4.7-flash` model is listed at $0 (0 Credits); chat, streaming and tool calling were tested through the
- 2026-11-15T14:33:20.735Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @HollowMan6](https://github.com/sgl-project/sglang/pull/48716)
> - `glm4_moe_lite.py` (GLM-4.7-Flash and its NextN draft): drop the three `q/k/v_proj -> qkv_proj` entries from `stacked_params_mapping`, which the MLA attention has no parameter for and
- 2026-11-15T14:49:13.217Z · [GitHub search · Z.ai · pulls · NovaSky-AI/SkyRL · @ArturNiederfahrenhorst](https://github.com/NovaSky-AI/SkyRL/pull/2734)
> suite on 4×L4, and the Kimi K2.5 and GLM-4.7-Flash rows on 4×H100. Megatron-only; FSDP does not use Megatron-Bridge.
- 2026-11-15T14:49:13.217Z · [GitHub search · Z.ai · pulls · antonellof/frink · @antonellof](https://github.com/antonellof/frink/pull/516)
> and `drop_thinking`. frink set none of them, so GLM-4.7-Flash, LFM3, LFM2.5 and Nemotron-3-Nano always dropped earlier turns' reasoning, Laguna-S-2.1 did with thinking off, and DeepSeek-V4
- 2026-11-15T14:49:13.217Z · [GitHub search · Z.ai · pulls · leehack/llamadart · @leehack](https://github.com/leehack/llamadart/pull/1976)
> contentOnly, and for the structured-output route with the GLM-4.7-Flash template (`<think>Plan.</think>{"a":1}` gives reasoning `<think>Plan.`, as the oracle) (`chat_format_registry_test.dart`).
- 2026-11-15T14:49:13.217Z · [GitHub search · Z.ai · pulls · rolexdkscreation-max/DK2.0 · @rolexdkscreation-max](https://github.com/rolexdkscreation-max/DK2.0/pull/236)
> - नए providers: `zai` (https://api.z.ai/api/paas/v4, default glm-4.7-flash) और `nvidia` (https://integrate.api.nvidia.com/v1, default meta/llama-3.3-70b-instruct)।
- 2026-11-15T14:49:13.217Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @divakantpandey](https://github.com/sgl-project/sglang/pull/50292)
> only, no model forward changes. GPU check on GLM-4.7-Flash (before/after, logs) is in a comment below.
- 2026-11-15T14:51:30.734Z · [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/c9c79ddf9760de4789e8c76e5c9e98147d9f057e)
> GLM-4.7-Flash (Non-reasoning) [Z AI]
- 2026-11-15T15:04:59.120Z · [GitHub search · Z.ai · pulls · B-E-L-I-E-V-E/Personal-AI-Router-Plus · @B-E-L-I-E-V-E](https://github.com/B-E-L-I-E-V-E/Personal-AI-Router-Plus/pull/25)
> - [ ] Live: **Apply now** on the GLM-4.7-Flash plan for Ultron (131,072 × 5). Needs this build on Ultron and the user's OK to
- 2026-11-15T15:04:59.120Z · [GitHub search · Z.ai · pulls · cheaper-inference/OmniRoute · @kainatquaderee](https://github.com/cheaper-inference/OmniRoute/pull/18313)
> doubled closer (D10), on three different models** (`deepseek-v4-flash-0731`, `glm-4.7-flash`, `llama-4-scout-17b-16e-instruct`): `<write>{…}</path>` and `<write>{…}</write></path>` both come back as `finish_reason: "tool_calls"`, `write`, with the arguments intact and
- 2026-11-15T15:20:21.008Z · [GitHub search · Z.ai · pulls · JingbiaoMei/Tokdash · @JingbiaoMei](https://github.com/JingbiaoMei/Tokdash/pull/290)
> | `glm-4.7-flash` | price_change | additions-only automation: existing model prices require a manual update |
- 2026-11-15T15:20:21.008Z · [GitHub search · Z.ai · pulls · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/pull/974)
> for them. A generation model there, such as `@cf/zai-org/glm-4.7-flash`, still gets "is a generation model".
- 2026-11-15T15:35:59.277Z · [GitHub search · Z.ai · pulls · ROCm/aiter · @hyjuunn](https://github.com/ROCm/aiter/pull/7476)
> backend calling this AITER kernel showed 1.17x faster GLM-4.7-Flash TP4 decode steps versus AITER `16979d757` (geomean of 10 workload shapes). This is not an upstream-vLLM
- 2026-11-15T15:35:59.277Z · [GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @ishandhanani](https://github.com/ai-dynamo/dynamo/pull/18443)
> own Modal node: two `dynamo.sglang` TP2 workers of GLM-4.7-Flash on 4x H200 (1,767,648 KV tokens per worker, 3.5M total), `dynamo.frontend --router-mode kv --router-session-affinity-mode soft`, one
- 2026-11-15T15:35:59.277Z · [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/717)
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · 1StepMore/Omni_Localizer · @1StepMore](https://github.com/1StepMore/Omni_Localizer/pull/194)
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · 1bit-MONSTER/llama.cpp · @bong-water-water-bong](https://github.com/1bit-MONSTER/llama.cpp/pull/70)
> ggml-hrx: no V transpose for MLA strided V (GLM-4.7-Flash prompts >= 512 tokens: PPL 315,664 -> 5.92)
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · 1bit-MONSTER/llama.cpp · @bong-water-water-bong](https://github.com/1bit-MONSTER/llama.cpp/pull/72)
> - GLM-4.7-Flash Q4_K_M, ~750-token prompt through the prefill kernel with #70's row-major V, 4 runs with a different request in between: bit-identical logits. Before: up
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · AndresYepez23/PRISMA · @AndresYepez23](https://github.com/AndresYepez23/PRISMA/pull/105)
> - Assert the official general Z.AI endpoint and GLM-4.7-Flash model remain configured.
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · hireymage/voice-agent-mcp · @hireymage](https://github.com/hireymage/voice-agent-mcp/pull/5)
> Tried on a device: ending by voice with GLM-4.7-Flash ("Ukonči se", "Zatím se měj", "Vypni se" ended 2/2; "Počkej chvilku" 0/2). Whether a "be quiet"
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · judecutler/wugs · @judecutler](https://github.com/judecutler/wugs/pull/64)
> 4 sections by BM25, and asks Workers AI `@cf/zai-org/glm-4.7-flash` (Cloudflare's replacement for the Llama 3.x models it retires on Nov 20) to answer from those
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · marromugi/iris · @marromugi](https://github.com/marromugi/iris/pull/37)
> `Model: <名前>.` が付く。`MODEL_PROVIDER` が `anthropic` なら `claude-haiku-5-5`、`workers-ai` なら `@cf/zai-org/glm-4.7-flash`。
- 2026-11-15T16:10:08.437Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @mgoin](https://github.com/vllm-project/vllm/pull/67267)
> - GSM8K, `zai-org/GLM-4.7-Flash`, full 1319 questions, 5-shot chat, thinking off, max 2048 generated tokens, `--quantization lut_b_moe` on the native SM107 path (`tcgen05.mma.kind::mxf8f6f4.block_scale.decompress::lut::b.block32`, MXFP8 activations):
- 2026-11-15T16:25:22.958Z · [GitHub search · Z.ai · pulls · kennedy-blip/Julesown · @kennedy-blip](https://github.com/kennedy-blip/Julesown/pull/6)
- 2026-11-15T16:25:22.958Z · [GitHub search · Z.ai · pulls · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/pull/962)
> Chat Completions request and stream through Workers AI (`@cf/zai-org/glm-4.7-flash`), costs and `cf-aig-log-id` in the request log, and the same requests visible in Cloudflare's own gateway
- 2026-11-15T16:25:22.958Z · [GitHub search · Z.ai · pulls · rasikur077-arch/lili-bilingual-companion · @rasikur077-arch](https://github.com/rasikur077-arch/lili-bilingual-companion/pull/3)
> - Use Workers AI model `@cf/zai-org/glm-4.7-flash` when the binding is present.
- 2026-11-15T16:25:22.958Z · [GitHub search · Z.ai · pulls · vllm-project/vllm · @mgoin](https://github.com/vllm-project/vllm/pull/67281)
> `ops.lut_b_moe_gemm` timing, GLM-4.7-Flash expert shapes, cold L2 (1 GiB memset before each launch), CUDA events, median of 30, µs, before → after. The instruction is
- 2026-11-15T16:28:24.870Z · [GitHub search · Z.ai · commits · Ogires/horoscopo-de-bardo · @Ogires](https://github.com/Ogires/horoscopo-de-bardo/commit/3b4094bbb4fe7bde3e62bdfdfdddd02b1713e799)
> En la prueba real, GLM-4.7-Flash con thinking gastó los 4.096 tokens de
- 2026-11-15T16:28:24.870Z · [GitHub search · Z.ai · commits · PowerTokens/video-studio · @PowerTokens](https://github.com/PowerTokens/video-studio/commit/a555fb44c18ad951ac60a96e1de8aea33952e2cf)
> catalog. The pickers now share four models, with glm-4.7-flash still the free default. A saved selection of the removed model falls back to that default.
- 2026-11-15T16:41:19.450Z · [GitHub search · Z.ai · pulls · Cap-go/Capve · @TorichanCapgo](https://github.com/Cap-go/Capve/pull/61)
> Adcash zone bid-change recommendations from Cloudflare Workers AI (GLM-4.7-Flash). Every existing and new campaign remains disabled by default.
- 2026-11-15T16:41:19.450Z · [GitHub search · Z.ai · pulls · NousResearch/hermes-agent · @DevvGwardo](https://github.com/NousResearch/hermes-agent/pull/153629)
> sent to `api.surplusintelligence.ai` (model `glm-4.7-flash`) to compress
- 2026-11-15T16:41:19.450Z · [GitHub search · Z.ai · pulls · Sys64k/ai-swarm-orchestrator · @Sys64k](https://github.com/Sys64k/ai-swarm-orchestrator/pull/179)
> - **Correction:** the page said only qwen3-coder and glm-4.7-flash ran partly on the CPU. Every model did at the test's context. The column is renamed
- 2026-11-15T16:41:19.450Z · [GitHub search · Z.ai · pulls · Sys64k/hardwarestack · @Sys64k](https://github.com/Sys64k/hardwarestack/pull/15)
> - **Calculator:** adds Qwen3-Coder 30B-A3B, GLM-4.7-Flash 30B-A3B (new `GLM` family, MLA KV cache like DeepSeek), Devstral Small 24B (2507) and Qwen2.5-Coder 14B. Architecture is from
- 2026-11-15T16:41:19.450Z · [GitHub search · Z.ai · pulls · fumitakaojima/ai-frontier-news · @fumitakaojima](https://github.com/fumitakaojima/ai-frontier-news/pull/8)
> Cloudflareモデル仕様：https://developers.cloudflare.com/workers-ai/models/glm-4.7-flash/
- 2026-11-15T16:41:19.450Z · [GitHub search · Z.ai · pulls · paracha34/zara · @paracha34](https://github.com/paracha34/zara/pull/2)
> Gemini chat path with Cloudflare Workers AI model `@cf/zai-org/glm-4.7-flash`.
- 2026-11-15T16:43:34.549Z · [GitHub search · Z.ai · commits · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/commit/190b909579892ed841dbcb52fda2110e767a6d0e)
> `@cf/zai-org/glm-4.7-flash`, still gets "is a generation model".
- 2026-11-15T16:57:13.523Z · [GitHub search · Z.ai · pulls · Sys64k/ai-swarm-orchestrator · @Sys64k](https://github.com/Sys64k/ai-swarm-orchestrator/pull/178)
> its weights fit in 16 GB. qwen3-coder and glm-4.7-flash don't, so part of each ran on the CPU. That makes them slower but shouldn't change
- 2026-11-15T16:57:13.523Z · [GitHub search · Z.ai · pulls · wwoosshh/GeulPUv2 · @wwoosshh](https://github.com/wwoosshh/GeulPUv2/pull/355)
> (1,299 / 30,076 rows) plus 8 greedy tokens. GLM-4.7-Flash · Kanana-2 30B-A3B
- 2026-11-15T16:59:09.643Z · [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/f90ccb022763e0192eb32cf610f6c8ce72e5080b)
> GLM-4.7-Flash (Reasoning) [Z AI]
- 2026-11-15T17:12:00.428Z · [GitHub search · Z.ai · pulls · diazMelgarejo/Perpetua-Tools · @diazMelgarejo](https://github.com/diazMelgarejo/Perpetua-Tools/pull/514)
> `_resolve_candidates()`. Isolated reproduction on the pre-fix tree: both `glm-4.7-flash` and `openrouter/free` returned ready while the qualification gate denied them, and the probe-failure fallback (`resolved or
- 2026-11-15T17:12:00.428Z · [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/713)
> | bumped | — | — | \| GLM-4.7-Flash \| Free \| Free \| Free \| Free \| |
- 2026-11-15T17:12:00.428Z · [GitHub search · Z.ai · pulls · praveens6050-afk/Fashion_Fussion · @praveens6050-afk](https://github.com/praveens6050-afk/Fashion_Fussion/pull/449)
> - Preview uses @cf/zai-org/glm-4.7-flash, selected for Workers Free compatibility.
- 2026-11-15T17:27:29.365Z · [GitHub search · Z.ai · pulls · sgl-project/sglang · @1195343015](https://github.com/sgl-project/sglang/pull/46766)
> --model-path ZhipuAI/GLM-4.7-Flash \
- 2026-11-15T17:27:29.365Z · [GitHub search · Z.ai · pulls · sourceplane/pdf-quiz-generator · @pullely](https://github.com/sourceplane/pdf-quiz-generator/pull/1)
> the Worker's binding, env.AI.toMarkdown for the PDF and @cf/zai-org/glm-4.7-flash for the quiz and title, through createAI from agents/models/ai-sdk, which replaced the deprecated workers-ai-provider and needs
- 2026-11-15T17:27:29.365Z · [GitHub search · Z.ai · pulls · sourceplane/pdf-quiz-generator · @pullely](https://github.com/sourceplane/pdf-quiz-generator/pull/2)
> Workers AI through createAI (agents/models/ai-sdk) over the binding, @cf/zai-org/glm-4.7-flash, or Gemini 2.5 Pro and Flash when GOOGLE_GENERATIVE_AI_API_KEY is set — and its schemaInPromptMiddleware moves a
- 2026-11-15T17:29:38.307Z · [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/54a1117fb028017bf94a326efe7abe711df01f2c)
> GLM-4.7-Flash (Reasoning) [Z AI]
- 2026-11-15T17:45:46.295Z · [GitHub search · Z.ai · pulls · ivanmlnnn/sentinel · @ivanmlnnn](https://github.com/ivanmlnnn/sentinel/pull/33)
> binding `AI`, shared `functions/api/_ai.js` adapter, and configured model `@cf/zai-org/glm-4.7-flash`.

## Kildelinks

- [vertex-model-garden](https://console.cloud.google.com/vertex-ai/publishers/zai-org/model-garden/glm-4.7-flash)
- [GitHub search · Z.ai · pulls · 1StepMore/Omni_Localizer · @1StepMore](https://github.com/1StepMore/Omni_Localizer/pull/194)
- [GitHub search · Z.ai · pulls · 1bit-MONSTER/llama.cpp · @bong-water-water-bong](https://github.com/1bit-MONSTER/llama.cpp/pull/70)
- [GitHub search · Z.ai · pulls · 1bit-MONSTER/llama.cpp · @bong-water-water-bong](https://github.com/1bit-MONSTER/llama.cpp/pull/72)
- [GitHub search · Z.ai · commits · 1essalion1-sudo/Nexora-exotic · @1essalion1-sudo](https://github.com/1essalion1-sudo/Nexora-exotic/commit/2c785ca7c759604849c408d747eff57326bd8320)
- [GitHub search · Z.ai · pulls · ACROWN-System/AstroCrown-Web · @ASDBradford-HAAN](https://github.com/ACROWN-System/AstroCrown-Web/pull/177)
- [GitHub search · Z.ai · pulls · AlexsJones/llmfit · @jayhemnani9910](https://github.com/AlexsJones/llmfit/pull/1145)
- [GitHub search · Z.ai · commits · AmsyarAmran/Studyhub-stpm · @AmsyarAmran](https://github.com/AmsyarAmran/Studyhub-stpm/commit/595661565192032554995fb908f434bffaf7f2fe)
- [GitHub search · Z.ai · commits · AmsyarAmran/Studyhub-stpm · @AmsyarAmran](https://github.com/AmsyarAmran/Studyhub-stpm/commit/b84a256df9087df2b16f9e2bae07ae25ce881d72)
- [GitHub search · Z.ai · pulls · AndresYepez23/PRISMA · @AndresYepez23](https://github.com/AndresYepez23/PRISMA/pull/105)
- [GitHub search · Z.ai · pulls · B-E-L-I-E-V-E/Personal-AI-Router-Plus · @B-E-L-I-E-V-E](https://github.com/B-E-L-I-E-V-E/Personal-AI-Router-Plus/pull/25)
- [GitHub search · Z.ai · pulls · Cap-go/Capve · @TorichanCapgo](https://github.com/Cap-go/Capve/pull/61)
- [GitHub search · Z.ai · pulls · Danish797035/harness-agent · @Danish797035](https://github.com/Danish797035/harness-agent/pull/13)
- [GitHub search · Z.ai · pulls · GoDanceAi/godance · @SummerTiger](https://github.com/GoDanceAi/godance/pull/34)
- [GitHub search · Z.ai · pulls · HYGON-AI/vllm-plugin-das · @alexanderbin123](https://github.com/HYGON-AI/vllm-plugin-das/pull/409)
- [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/410)
- [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/411)
- [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/412)
- [GitHub search · Z.ai · pulls · HockerAGI/hocker.one · @HockerAGI](https://github.com/HockerAGI/hocker.one/pull/428)
- [GitHub search · Z.ai · pulls · JingbiaoMei/Tokdash · @JingbiaoMei](https://github.com/JingbiaoMei/Tokdash/pull/290)
- [GitHub search · Z.ai · pulls · JoshCLWren/comic-pile · @JoshCLWren](https://github.com/JoshCLWren/comic-pile/pull/5038)
- [GitHub search · Z.ai · pulls · JoshCLWren/comic-pile · @JoshCLWren](https://github.com/JoshCLWren/comic-pile/pull/5138)
- [GitHub search · Z.ai · pulls · LevenST24/galgame2voice · @LevenST24](https://github.com/LevenST24/galgame2voice/pull/518)
- [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/54a1117fb028017bf94a326efe7abe711df01f2c)
- [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/77ee0cdd64b90b5a45d35155e167cadcdc89c125)
- [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/c9c79ddf9760de4789e8c76e5c9e98147d9f057e)
- [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/d5b473e2c542a2ab30983f6c2f520723cb14a6e8)
- [GitHub search · Z.ai · commits · Nitjsefnie/ai-researcher · @github-actions[bot]](https://github.com/Nitjsefnie/ai-researcher/commit/f90ccb022763e0192eb32cf610f6c8ce72e5080b)
- [GitHub search · Z.ai · commits · Nitjsefnie/claudit · @github-actions[bot]](https://github.com/Nitjsefnie/claudit/commit/7d6ca9692df859c0172871ef80de2aaa9462c08c)
- [GitHub search · Z.ai · pulls · NousResearch/hermes-agent · @DevvGwardo](https://github.com/NousResearch/hermes-agent/pull/153629)
- [GitHub search · Z.ai · pulls · NovaSky-AI/SkyRL · @ArturNiederfahrenhorst](https://github.com/NovaSky-AI/SkyRL/pull/2734)
- [GitHub search · Z.ai · commits · Ogires/horoscopo-de-bardo · @Ogires](https://github.com/Ogires/horoscopo-de-bardo/commit/3b4094bbb4fe7bde3e62bdfdfdddd02b1713e799)
- [GitHub search · Z.ai · commits · PowerTokens/video-studio · @PowerTokens](https://github.com/PowerTokens/video-studio/commit/a555fb44c18ad951ac60a96e1de8aea33952e2cf)
- [GitHub search · Z.ai · pulls · Prool-bot/ngo-grants-facebook · @Prool-bot](https://github.com/Prool-bot/ngo-grants-facebook/pull/94)
- [GitHub search · Z.ai · pulls · ROCm/aiter · @hyjuunn](https://github.com/ROCm/aiter/pull/7476)
- [GitHub search · Z.ai · pulls · SonicStar-Solutions/agentic-inbox · @cvbutani](https://github.com/SonicStar-Solutions/agentic-inbox/pull/1)
- [GitHub search · Z.ai · pulls · Sys64k/ai-swarm-orchestrator · @Sys64k](https://github.com/Sys64k/ai-swarm-orchestrator/pull/178)
- [GitHub search · Z.ai · pulls · Sys64k/ai-swarm-orchestrator · @Sys64k](https://github.com/Sys64k/ai-swarm-orchestrator/pull/179)
- [GitHub search · Z.ai · pulls · Sys64k/hardwarestack · @Sys64k](https://github.com/Sys64k/hardwarestack/pull/15)
- [GitHub search · Z.ai · commits · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/commit/f5e9aebda2acdaab729401d4c4391656f93399a6)
- [GitHub search · Z.ai · pulls · Trollz1004/ANTIGRAVITY · @Trollz1004](https://github.com/Trollz1004/ANTIGRAVITY/pull/402)
- [GitHub search · Z.ai · pulls · afjcjsbx/picoclaw · @trufae](https://github.com/afjcjsbx/picoclaw/pull/615)
- [GitHub search · Z.ai · pulls · ai-advokat/ai-advokat.github.io · @ai-advokat](https://github.com/ai-advokat/ai-advokat.github.io/pull/681)
- [GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @ishandhanani](https://github.com/ai-dynamo/dynamo/pull/18443)
- [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 · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13561)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13603)
- [GitHub search · Z.ai · pulls · antonellof/frink · @antonellof](https://github.com/antonellof/frink/pull/516)
- [GitHub search · Z.ai · commits · aphrody-labs/aphrody · @aphrody-dev](https://github.com/aphrody-labs/aphrody/commit/375b3ff3cdb5765c0bc814b5e71b8d336a237f36)
- [GitHub search · Z.ai · pulls · brokespace/seal · @brokespace](https://github.com/brokespace/seal/pull/23)
- [GitHub search · Z.ai · pulls · brokespace/seal · @brokespace](https://github.com/brokespace/seal/pull/32)
- [GitHub search · Z.ai · pulls · can1357/oh-my-pi · @andrebrait](https://github.com/can1357/oh-my-pi/pull/14458)
- [GitHub search · Z.ai · pulls · chadkhalil21-svg/Plenum-Scientific-Intelligence · @chadkhalil21-svg](https://github.com/chadkhalil21-svg/Plenum-Scientific-Intelligence/pull/711)
- [GitHub search · Z.ai · pulls · chadkhalil21-svg/Plenum-Scientific-Intelligence · @chadkhalil21-svg](https://github.com/chadkhalil21-svg/Plenum-Scientific-Intelligence/pull/731)
- [GitHub search · Z.ai · pulls · cheaper-inference/OmniRoute · @kainatquaderee](https://github.com/cheaper-inference/OmniRoute/pull/18313)
- [GitHub search · Z.ai · pulls · dannywise093-crypto/ATLAS · @dannywise093-crypto](https://github.com/dannywise093-crypto/ATLAS/pull/4)
- [GitHub search · Z.ai · pulls · diazMelgarejo/Perpetua-Tools · @diazMelgarejo](https://github.com/diazMelgarejo/Perpetua-Tools/pull/506)
- [GitHub search · Z.ai · pulls · diazMelgarejo/Perpetua-Tools · @diazMelgarejo](https://github.com/diazMelgarejo/Perpetua-Tools/pull/514)
- [GitHub search · Z.ai · pulls · diazMelgarejo/orama-system · @diazMelgarejo](https://github.com/diazMelgarejo/orama-system/pull/506)
- [GitHub search · Z.ai · pulls · diazMelgarejo/orama-system · @diazMelgarejo](https://github.com/diazMelgarejo/orama-system/pull/507)
- [GitHub search · Z.ai · pulls · eaitbrahim/NarratoFlow · @eaitbrahim](https://github.com/eaitbrahim/NarratoFlow/pull/187)
- [GitHub search · Z.ai · pulls · eltmon/overdeck · @eltmon](https://github.com/eltmon/overdeck/pull/5216)
- [GitHub search · Z.ai · pulls · fumitakaojima/ai-frontier-news · @fumitakaojima](https://github.com/fumitakaojima/ai-frontier-news/pull/8)
- [GitHub search · Z.ai · pulls · gorfreee/clasica_madrid · @gorfreee](https://github.com/gorfreee/clasica_madrid/pull/419)
- [GitHub search · Z.ai · pulls · hale-lang/voice · @rileyr](https://github.com/hale-lang/voice/pull/221)
- [GitHub search · Z.ai · pulls · hireymage/voice-agent-mcp · @hireymage](https://github.com/hireymage/voice-agent-mcp/pull/5)
- [GitHub search · Z.ai · pulls · ivanmlnnn/sentinel · @ivanmlnnn](https://github.com/ivanmlnnn/sentinel/pull/33)
- [GitHub search · Z.ai · pulls · judecutler/wugs · @judecutler](https://github.com/judecutler/wugs/pull/64)
- [GitHub search · Z.ai · pulls · kahnwong/self-hosted · @renovate[bot]](https://github.com/kahnwong/self-hosted/pull/800)
- [GitHub search · Z.ai · pulls · kennedy-blip/Julesown · @kennedy-blip](https://github.com/kennedy-blip/Julesown/pull/6)
- [GitHub search · Z.ai · pulls · laurofiorenzani/jarvis · @laurofiorenzani](https://github.com/laurofiorenzani/jarvis/pull/48)
- [GitHub search · Z.ai · pulls · leehack/llamadart · @leehack](https://github.com/leehack/llamadart/pull/1976)
- [GitHub search · Z.ai · commits · lettroi/safeshell-pro · @lettroi](https://github.com/lettroi/safeshell-pro/commit/051be91c8ab11836df7f3dad589589aa4c5339d8)
- [GitHub search · Z.ai · commits · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/commit/190b909579892ed841dbcb52fda2110e767a6d0e)
- [GitHub search · Z.ai · pulls · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/pull/962)
- [GitHub search · Z.ai · pulls · logicplanes/kaeso · @dvnold](https://github.com/logicplanes/kaeso/pull/974)
- [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/713)
- [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/717)
- [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/724)
- [GitHub search · Z.ai · pulls · luongnv89/freetokens · @luongnv89](https://github.com/luongnv89/freetokens/pull/731)
- [GitHub search · Z.ai · pulls · marromugi/iris · @marromugi](https://github.com/marromugi/iris/pull/37)
- [GitHub search · Z.ai · pulls · methaneex-oss/AURIONS · @methaneex-oss](https://github.com/methaneex-oss/AURIONS/pull/7)
- [GitHub search · Z.ai · pulls · paracha34/zara · @paracha34](https://github.com/paracha34/zara/pull/2)
- [GitHub search · Z.ai · pulls · praveens6050-afk/Fashion_Fussion · @praveens6050-afk](https://github.com/praveens6050-afk/Fashion_Fussion/pull/449)
- [GitHub search · Z.ai · pulls · quiquandon-oss/PulseWorkerV2 · @quiquandon-oss](https://github.com/quiquandon-oss/PulseWorkerV2/pull/135)
- [GitHub search · Z.ai · pulls · rasikur077-arch/lili-bilingual-companion · @rasikur077-arch](https://github.com/rasikur077-arch/lili-bilingual-companion/pull/3)
- [GitHub search · Z.ai · commits · rodrigueztaylor87/rod · @rodrigueztaylor87](https://github.com/rodrigueztaylor87/rod/commit/88a4dbdbf70aeeb1ade2f2fa9112403a1a007942)
- [GitHub search · Z.ai · pulls · rolexdkscreation-max/DK2.0 · @rolexdkscreation-max](https://github.com/rolexdkscreation-max/DK2.0/pull/236)
- [GitHub search · Z.ai · pulls · salamou1944/Salamou-31 · @salamou1944](https://github.com/salamou1944/Salamou-31/pull/72)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @1195343015](https://github.com/sgl-project/sglang/pull/46766)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @bvolpato](https://github.com/sgl-project/sglang/pull/48181)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @HollowMan6](https://github.com/sgl-project/sglang/pull/48716)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @divakantpandey](https://github.com/sgl-project/sglang/pull/50292)
- [GitHub search · Z.ai · pulls · sgl-project/sglang · @ami-GS](https://github.com/sgl-project/sglang/pull/50557)
- [GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6025)
- [GitHub search · Z.ai · pulls · sourceplane/pdf-quiz-generator · @pullely](https://github.com/sourceplane/pdf-quiz-generator/pull/1)
- [GitHub search · Z.ai · pulls · sourceplane/pdf-quiz-generator · @pullely](https://github.com/sourceplane/pdf-quiz-generator/pull/2)
- [GitHub search · Z.ai · pulls · spiceai/cookbook · @spiceemma](https://github.com/spiceai/cookbook/pull/771)
- [GitHub search · Z.ai · pulls · szl-holdings/a11oy · @stephenlutar2-hash](https://github.com/szl-holdings/a11oy/pull/3405)
- [GitHub search · Z.ai · pulls · thisishaidee/kivora · @thisishaidee](https://github.com/thisishaidee/kivora/pull/21)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @lihzamd](https://github.com/vllm-project/vllm/pull/60822)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @umarkovi-amd](https://github.com/vllm-project/vllm/pull/61872)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @Pb314314](https://github.com/vllm-project/vllm/pull/66799)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @mgoin](https://github.com/vllm-project/vllm/pull/67267)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @mgoin](https://github.com/vllm-project/vllm/pull/67281)
- [GitHub search · Z.ai · pulls · vllm-project/vllm · @hyjuunn](https://github.com/vllm-project/vllm/pull/67541)
- [GitHub search · Z.ai · pulls · wwoosshh/GeulPUv2 · @wwoosshh](https://github.com/wwoosshh/GeulPUv2/pull/355)
- [hf-author-artifacts:zai-org](https://huggingface.co/api/models/zai-org/GLM-4.7-Flash/paths-info/7dd20894a642a0aa287e9827cb1a1f7f91386b67)
- [huggingface-router](https://huggingface.co/zai-org/GLM-4.7-Flash)

## Signaler