Alex Getmanสัญญาณ AI ก่อนใคร

GLM-5

Z.ai

เปิดตัวแล้ว อัปเดต
หน้าต่างบริบท
203K
202,752 โทเค็น
เอาต์พุตสูงสุด
131K
131,072 โทเค็น
อินพุต / เอาต์พุต
ข้อความ → ข้อความ

ราคา API

USD / หนึ่งล้านโทเค็น

อินพุตเอาต์พุตอินพุตที่แคชไว้
  • $1.00
zai-pricing
  • $3.20
zai-pricing
  • $0.20
zai-pricing

ลำดับเวลา

  1. · เวอร์ชันน้ำหนัก · ลิงก์หลักฐาน
ราคาอินพุต / เอาต์พุต · USD / หนึ่งล้านโทเค็น
โมเดลลิงก์หลักฐานราคาอินพุต / เอาต์พุต
glm-5
standard
zai-pricing
เส้นทาง API ไม่พร้อมใช้งาน
$1.00 / $3.20
  1. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc
    ข้อความที่คัดมา
    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. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · milabench/milabench · @bouthilx
    ข้อความที่คัดมา
    - 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. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · maximhq/bifrost · @mickgvirtu
    ข้อความที่คัดมา
    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. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  5. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · ai-dynamo/frontend-crates · @dundysm
  6. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @indrajit96
    ข้อความที่คัดมา
    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. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · ROCm/ATOM · @whx-sjtu
  8. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @moraxu
    ข้อความที่คัดมา
    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. · ลิงก์หลักฐาน · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux
    ข้อความที่คัดมา
    - `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`.
ข้อมูลจำเพาะ

GLM-5 เป็นโมเดลจาก Z.ai ที่เปิดให้เข้าถึงน้ำหนักโมเดล เปิดตัวเมื่อ 2026-02-12 หน้าต่างบริบทมีขนาด 202,752 โทเค็น เอาต์พุตสูงสุดคือ 131,072 โทเค็น ราคาอยู่ที่ $1.00 ต่อหนึ่งล้านโทเค็นอินพุต และ $3.20 ต่อหนึ่งล้านโทเค็นเอาต์พุต

หน้าต่างบริบท
202,752
เอาต์พุตสูงสุด
131,072
อินพุต
ข้อความ
เอาต์พุต
ข้อความ
น้ำหนักโมเดล
เปิด
อินพุต · USD / หนึ่งล้านโทเค็น
$1.00
เอาต์พุต · USD / หนึ่งล้านโทเค็น
$3.20
อินพุตที่แคชไว้ · USD / หนึ่งล้านโทเค็น
$0.20

คำถาม

หน้าต่างบริบทของ GLM-5 มีขนาดเท่าไร?

หน้าต่างบริบทมีขนาด 202,752 โทเค็น เอาต์พุตสูงสุดคือ 131,072 โทเค็น

GLM-5 ราคาเท่าไร?

ราคาอยู่ที่ $1.00 ต่อหนึ่งล้านโทเค็นอินพุต และ $3.20 ต่อหนึ่งล้านโทเค็นเอาต์พุต อินพุตที่แคชไว้มีราคา $0.20 ต่อหนึ่งล้านโทเค็น

น้ำหนักโมเดลของ GLM-5 เปิดให้สาธารณะเข้าถึงหรือไม่?

ใช่ Z.ai เผยแพร่น้ำหนักโมเดล

GLM-5 เปิดตัวเมื่อไร?

เมื่อ 2026-02-12