Alex GetmanAI의 초기 신호
KO

GLM-5.2

Z.ai

출시됨 업데이트
컨텍스트 창
1M
1,048,576 토큰
최대 출력
131K
131,072 토큰
입력 / 출력
텍스트 → 텍스트

API 요금

USD / 토큰 100만 개

입력출력캐시 입력
  • $1.40
zai-pricing
  • $4.40
zai-pricing
  • $0.26
zai-pricing
사용량 계산

타임라인

  1. · 가중치 버전 · 근거 링크
입력/출력 가격 · USD / 토큰 100만 개
모델근거 링크입력/출력 가격
glm-5.2
standard · 텍스트
opencode-go$1.40 / $4.40
glm-5.2
standard
zai-pricing
API 경로를 사용할 수 없음
$1.40 / $4.40
  1. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  2. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  3. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  4. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  5. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  6. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  7. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  8. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  9. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  10. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  11. · 근거 링크 · GitHub search · Z.ai · commits · vhaldemar/opencode-plugin-yandex-ai-studio · @vhaldemar
  12. · 근거 링크 · GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]
  13. · 근거 링크 · GitHub search · Z.ai · commits · renj-arch/dimsred · @github-actions[bot]
  14. · 근거 링크 · GitHub search · Z.ai · commits · devlawey/filar · @claude
  15. · 근거 링크 · GitHub search · Z.ai · commits · alexjbarnes/cockpit · @alexjbarnes
  16. · 근거 링크 · GitHub search · Z.ai · commits · ROCm/aiter · @RElbers
  17. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm · @Ma1oneZhang
    발췌
    gain. Models that run top-2048 over every key (GLM-5.2/5.3) should gain more; that is not measured here.
  18. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @pritha90
  27. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @aaronndx
  28. · 근거 링크 · GitHub search · Z.ai · pulls · vllm-project/vllm-torchtpu · @Zhiqun-Zuo
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · octogee-ai/octogee-cloud · @ceckert
    발췌
    - model `z-ai/glm-5.2`;
  30. · 근거 링크 · GitHub search · Z.ai · pulls · metorial/metorial-platform · @herber
    발췌
    | `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. · 근거 링크 · GitHub search · Z.ai · pulls · maximhq/bifrost · @is911
    발췌
    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. · 근거 링크 · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  33. · 근거 링크 · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  34. · 근거 링크 · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  35. · 근거 링크 · GitHub search · Z.ai · pulls · iv-org/invidious · @Fijxu
  36. · 근거 링크 · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
    발췌
    - updated: `/home/runner/_work/models.dev/models.dev/providers/nano-gpt/models/z-ai/glm-5.2:thinking.toml`
  37. · 근거 링크 · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  38. · 근거 링크 · GitHub search · Z.ai · pulls · anomalyco/models.dev · @KevRojo
  39. · 근거 링크 · GitHub search · Z.ai · pulls · AMD-AGI/AKLR · @zhenhuang12
    발췌
    - 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. · 근거 링크 · GitHub search · Z.ai · commits · genji1024/dotfiles · @genji1024
  41. · 근거 링크 · GitHub search · Z.ai · commits · devlawey/filar · @claude
  42. · 근거 링크 · GitHub search · Z.ai · commits · Nulluminati/pi-extensions · @Nulluminati
    발췌
    the 11 ids that /v1/models no longer publishes (GLM-5.2, DeepSeek

시그널 4

사양

GLM-5.2: Z.ai의 AI 모델, 가중치 공개, 출시일 2026-06-16. 컨텍스트 윈도는 1,048,576 토큰입니다. 최대 출력은 131,072 토큰입니다. 토큰 100만 개당 요금은 입력 $1.40, 출력 $4.40입니다.

컨텍스트 창
1,048,576
최대 출력
131,072
입력
텍스트
출력
텍스트
가중치
공개
입력 · USD / 토큰 100만 개
$1.40
출력 · USD / 토큰 100만 개
$4.40
캐시 입력 · USD / 토큰 100만 개
$0.26

자주 묻는 질문

GLM-5.2의 컨텍스트 창 크기는 얼마인가요?

컨텍스트 윈도는 1,048,576 토큰입니다. 최대 출력은 131,072 토큰입니다.

GLM-5.2의 가격은 얼마인가요?

토큰 100만 개당 요금은 입력 $1.40, 출력 $4.40입니다. 캐시 입력은 100만 개당 $0.26입니다.

GLM-5.2의 가중치는 공개되어 있나요?

네. Z.ai에서 가중치를 공개합니다.

GLM-5.2의 출시일은 언제인가요?

2026-06-16.