Alex Getmanerken yapay zeka sinyalleri

GLM-5

Z.ai

Yayımlandı Güncellendi
Bağlam penceresi
203K
202.752 token
Maksimum çıktı
131K
131.072 token
Girdi / Çıktı
metin → metin

API fiyatları

USD / 1 milyon token

GirdiÇıktıÖnbellekten girdi
  • $1,00
zai-pricing
  • $3,20
zai-pricing
  • $0,20
zai-pricing

Zaman çizelgesi

  1. · Ağırlık sürümü · kanıt bağlantısı
Girdi / çıktı fiyatı · USD / 1 milyon token
ModelKanıt bağlantılarıGirdi / çıktı fiyatı
glm-5
standard
zai-pricing
API yolu kullanılamıyor
$1,00 / $3,20
  1. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc
    Alıntı
    Atria-Dawn, `glm`, beside Atria-Dawn-Preview: the template writes the GLM-5 shape (`[gMASK]<sop>`, a reasoning-effort system turn, `<|system|>` / `<|user|>` / `<|assistant|>` / `<|observation|>` turns), the tools
  2. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · milabench/milabench · @bouthilx
    Alıntı
    - GLM-5: layout check before launch, loss from the last stage, checkpoint timing and checksums, crash cleanup; `benchmarks/megatron/dev.yaml`, `scripts/trillium/glm/`.
  3. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · maximhq/bifrost · @mickgvirtu
    Alıntı
    is not `schemas.Anthropic`, and the served model -- `glm-5`, `Kimi-K2`, ... -- is neither opus-4.8 nor Fable), so Claude Code's per-turn reminders were hoisted every
  4. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  5. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · ai-dynamo/frontend-crates · @dundysm
  6. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @indrajit96
    Alıntı
    for any DSA model (including DeepSeek V3.2 and GLM-5), or matching `flashmla_kv`/`trtllm` kernels on K3.1's sharded DCP path. Kernels SGLang has not resolved at CLI
  7. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · ROCm/ATOM · @whx-sjtu
  8. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @moraxu
    Alıntı
    class is registered for both `DeepseekV3ForCausalLM` and `DeepseekV32ForCausalLM`; GLM-5 (`GlmMoeDsaForCausalLM`) and Mistral Large 3 subclass it, so exact-class matching excludes them. Kimi K2 declares `DeepseekV3ForCausalLM`
  9. · Kanıt bağlantıları · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux
    Alıntı
    - `modeling_glm5_next_vision.py`: the GLM-5 input processor takes the prefix tokenization cache (the fourth commit). Before, it tokenized every text prompt in full and ignored `enable_tokenization_cache`.
Özellikler

GLM-5, Z.ai tarafından geliştirilen bir yapay zekâ modelidir. Modelin ağırlıkları kamuya açıktır. Yayın tarihi: 2026-02-12. Bağlam penceresi 202.752 token uzunluğundadır. Model en fazla 131.072 token üretebilir. Bir milyon token başına giriş ücreti $1,00, çıkış ücreti $3,20 tutarındadır.

Bağlam penceresi
202.752
Maksimum çıktı
131.072
Girdi
metin
Çıktı
metin
Ağırlıklar
Açık
Girdi · USD / 1 milyon token
$1,00
Çıktı · USD / 1 milyon token
$3,20
Önbellekten girdi · USD / 1 milyon token
$0,20

Sorular

GLM-5 modelinin bağlam penceresi ne kadar?

Bağlam penceresi 202.752 token uzunluğundadır. Model en fazla 131.072 token üretebilir.

GLM-5 modelinin fiyatı nedir?

Bir milyon token başına giriş ücreti $1,00, çıkış ücreti $3,20 tutarındadır. Önbellekten girdi fiyatı milyon token başına $0,20.

GLM-5 modelinin ağırlıkları kamuya açık mı?

Evet. Z.ai model ağırlıklarını yayınlar.

GLM-5 ne zaman piyasaya sürüldü?

2026-02-12.