Alex Getmansinyal AI awal
ID

GLM-5.2

Z.ai

Dirilis Diperbarui
Jendela konteks
1M
1.048.576 token
Keluaran maksimal
131K
131.072 token
Masukan / Keluaran
teks → teks

Harga API

USD / 1 juta token

MasukanKeluaranMasukan dalam cache
  • $1,40
zai-pricing
  • $4,40
zai-pricing
  • $0,26
zai-pricing
Hitung biaya penggunaan Anda

Linimasa

  1. · Versi bobot · tautan bukti
Harga masukan / keluaran · USD / 1 juta token
ModelTautan buktiHarga masukan / keluaran
glm-5.2
standard · teks
opencode-go$1,40 / $4,40
glm-5.2
standard
zai-pricing
Rute API tidak tersedia
$1,40 / $4,40
  1. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  2. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  3. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  4. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  5. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  6. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  7. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  8. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  9. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  10. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  11. · Tautan bukti · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  12. · Tautan bukti · GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]
  13. · Tautan bukti · GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]
  14. · Tautan bukti · GitHub search · Z.ai · commits · devlawey/filar · @claude
  15. · Tautan bukti · GitHub search · Z.ai · commits · alexjbarnes/cockpit · @alexjbarnes
  16. · Tautan bukti · GitHub search · Z.ai · commits · ROCm/aiter · @RElbers
  17. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm · @Ma1oneZhang
    Kutipan
    gain. Models that run top-2048 over every key (GLM-5.2/5.3) should gain more; that is not measured here.
  18. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  19. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  20. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  21. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  22. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  23. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  24. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  25. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    glm-agentx branch (#1809, #2107, #2201), that brings the GLM-5.2 decode optimizations to main. Each kernel comes first in its own PR, and a separate PR
  26. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @pritha90
  27. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @aaronndx
  28. · Tautan bukti · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Kutipan
    At decode, every decoder layer of GLM-5.2 ends with a TP all-reduce, which sums the layer's output across the 16 cores. This tensor is small.
  29. · Tautan bukti · GitHub search · Z.ai · pulls · octogee-ai/octogee-cloud · @ceckert
    Kutipan
    - model `z-ai/glm-5.2`;
  30. · Tautan bukti · GitHub search · Z.ai · pulls · metorial/metorial-platform · @herber
    Kutipan
    | `nano-gpt/z-ai/glm-5.2` | link → `zhipu/glm-5.2` | NanoGPT's GLM 5.2 is Z.ai's flagship 1M-context coding model released June 2026 (NVIDIA NIM, Vercel), matching zhipu/glm-5.2 (2026-06-13,
  31. · Tautan bukti · GitHub search · Z.ai · pulls · maximhq/bifrost · @is911
    Kutipan
    only for models that accept it (qwen3.8-max, kimi-k3, glm-5.2) and stripped elsewhere to avoid vendor 400s; `max` preserved on kimi-k3. Since opening, live dogfooding corrected
  32. · Tautan bukti · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  33. · Tautan bukti · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  34. · Tautan bukti · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  35. · Tautan bukti · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  36. · Tautan bukti · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
    Kutipan
    - updated: `/home/runner/_work/models.dev/models.dev/providers/nano-gpt/models/z-ai/glm-5.2:thinking.toml`
  37. · Tautan bukti · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  38. · Tautan bukti · GitHub search · Z.ai · pulls · anomalyco/models.dev · @KevRojo
  39. · Tautan bukti · GitHub search · Z.ai · pulls · AMD-AGI/AKLR · @zhenhuang12
    Kutipan
    - Files per model: qwen3.5 160, glm-5.2 147, kimi-k3 119, qwen3-next 80, deepseek-v4-pro 53, glm-5.3 53, deepseek-v4-flash 45, deepseek-r1 40, deepseek-v3 40, minimax-m2.5 32, muse-spark
  40. · Tautan bukti · GitHub search · Z.ai · commits · genji1024/dotfiles · @genji1024
  41. · Tautan bukti · GitHub search · Z.ai · commits · devlawey/filar · @claude
  42. · Tautan bukti · GitHub search · Z.ai · commits · Nulluminati/pi-extensions · @Nulluminati
    Kutipan
    the 11 ids that /v1/models no longer publishes (GLM-5.2, DeepSeek

Sinyal 4

Spesifikasi

GLM-5.2 adalah model AI dari Z.ai dengan bobot terbuka, dirilis pada 2026-06-16. Jendela konteksnya sebesar 1.048.576 token. Keluaran maksimalnya 131.072 token. Harga per satu juta token adalah $1,40 untuk input dan $4,40 untuk output.

Jendela konteks
1.048.576
Keluaran maksimal
131.072
Masukan
teks
Keluaran
teks
Bobot
Terbuka
Masukan · USD / 1 juta token
$1,40
Keluaran · USD / 1 juta token
$4,40
Masukan dalam cache · USD / 1 juta token
$0,26

Pertanyaan

Seberapa besar jendela konteks GLM-5.2?

Jendela konteksnya sebesar 1.048.576 token. Keluaran maksimalnya 131.072 token.

Berapa biaya GLM-5.2?

Harga per satu juta token adalah $1,40 untuk input dan $4,40 untuk output. Masukan dari cache berharga $0,26 per juta token.

Apakah bobot model GLM-5.2 tersedia untuk umum?

Ya. Z.ai menerbitkan bobot model.

Kapan GLM-5.2 dirilis?

2026-06-16.