Alex Getmansinais antecipados de IA
PT

GLM-5.2

Z.ai

Lançado Atualizado
Janela de contexto
1M
1.048.576 tokens
Saída máxima
131K
131.072 tokens
Entrada / Saída
texto → texto

Preços da API

USD / 1 milhão de tokens

EntradaSaídaEntrada em cache
  • $1,40
zai-pricing
  • $4,40
zai-pricing
  • $0,26
zai-pricing
Calcular seu volume de uso

Cronologia

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

Sinais 4

Especificações

GLM-5.2 é um modelo de Z.ai com pesos abertos, lançado em 2026-06-16. A janela de contexto é de 1.048.576 tokens. A saída máxima é de 131.072 tokens. O preço por milhão de tokens é de $1,40 na entrada e $4,40 na saída.

Janela de contexto
1.048.576
Saída máxima
131.072
Entrada
texto
Saída
texto
Pesos
Abertos
Entrada · USD / 1 milhão de tokens
$1,40
Saída · USD / 1 milhão de tokens
$4,40
Entrada em cache · USD / 1 milhão de tokens
$0,26

Perguntas

Qual é a janela de contexto do GLM-5.2?

A janela de contexto é de 1.048.576 tokens. A saída máxima é de 131.072 tokens.

Quanto custa o GLM-5.2?

O preço por milhão de tokens é de $1,40 na entrada e $4,40 na saída. A entrada em cache custa $0,26 por milhão.

O GLM-5.2 tem pesos abertos?

Sim. Z.ai disponibiliza os pesos.

Quando o GLM-5.2 foi lançado?

Em 2026-06-16.