Alex Getmantidlige AI-signaler
DA

GLM-5.2

Z.ai

Lanceret Opdateret
Kontekstvindue
1M
1.048.576 tokens
Maksimal outputlængde
131K
131.072 tokens
Input / Output
tekst → tekst

API-priser

USD / 1 mio. tokens

InputOutputCachelagret input
  • $1,40
zai-pricing
  • $4,40
zai-pricing
  • $0,26
zai-pricing
Beregn din brugsomkostning

Tidslinje

  1. · Vægtversion · kildelink
Pris for input / output · USD / 1 mio. tokens
ModelKildelinksPris for input / output
glm-5.2
standard · tekst
opencode-go$1,40 / $4,40
glm-5.2
standard
zai-pricing
API-rute er ikke tilgængelig
$1,40 / $4,40
  1. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  2. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  3. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  4. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  5. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  6. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  7. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  8. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  9. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  10. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  11. · Kildelinks · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  12. · Kildelinks · GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]
  13. · Kildelinks · GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]
  14. · Kildelinks · GitHub search · Z.ai · commits · devlawey/filar · @claude
  15. · Kildelinks · GitHub search · Z.ai · commits · alexjbarnes/cockpit · @alexjbarnes
  16. · Kildelinks · GitHub search · Z.ai · commits · ROCm/aiter · @RElbers
  17. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm · @Ma1oneZhang
    Uddrag
    gain. Models that run top-2048 over every key (GLM-5.2/5.3) should gain more; that is not measured here.
  18. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @pritha90
  27. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @aaronndx
  28. · Kildelinks · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · octogee-ai/octogee-cloud · @ceckert
    Uddrag
    - model `z-ai/glm-5.2`;
  30. · Kildelinks · GitHub search · Z.ai · pulls · metorial/metorial-platform · @herber
    Uddrag
    | `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. · Kildelinks · GitHub search · Z.ai · pulls · maximhq/bifrost · @is911
    Uddrag
    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. · Kildelinks · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  33. · Kildelinks · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  34. · Kildelinks · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  35. · Kildelinks · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  36. · Kildelinks · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
    Uddrag
    - updated: `/home/runner/_work/models.dev/models.dev/providers/nano-gpt/models/z-ai/glm-5.2:thinking.toml`
  37. · Kildelinks · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  38. · Kildelinks · GitHub search · Z.ai · pulls · anomalyco/models.dev · @KevRojo
  39. · Kildelinks · GitHub search · Z.ai · pulls · AMD-AGI/AKLR · @zhenhuang12
    Uddrag
    - 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. · Kildelinks · GitHub search · Z.ai · commits · genji1024/dotfiles · @genji1024
  41. · Kildelinks · GitHub search · Z.ai · commits · devlawey/filar · @claude
  42. · Kildelinks · GitHub search · Z.ai · commits · Nulluminati/pi-extensions · @Nulluminati
    Uddrag
    the 11 ids that /v1/models no longer publishes (GLM-5.2, DeepSeek

Signaler 4

Specifikationer

GLM-5.2 er en model fra Z.ai med åbne vægte, lanceret den 2026-06-16. Kontekstvinduet er 1.048.576 tokens. Den maksimale outputlængde er 131.072 tokens. Prisen er $1,40 pr. million inputtokens og $4,40 pr. million outputtokens.

Kontekstvindue
1.048.576
Maksimal outputlængde
131.072
Input
tekst
Output
tekst
Vægte
Åbne
Input · USD / 1 mio. tokens
$1,40
Output · USD / 1 mio. tokens
$4,40
Cachelagret input · USD / 1 mio. tokens
$0,26

Spørgsmål

Hvor stort er kontekstvinduet for GLM-5.2?

Kontekstvinduet er 1.048.576 tokens. Den maksimale outputlængde er 131.072 tokens.

Hvad koster GLM-5.2?

Prisen er $1,40 pr. million inputtokens og $4,40 pr. million outputtokens. Cachelagret input koster $0,26 pr. million tokens.

Er vægtene for GLM-5.2 offentligt tilgængelige?

Ja. Z.ai offentliggør vægtene.

Hvornår blev GLM-5.2 lanceret?

Den 2026-06-16.