
GLM-5
Z.ai
- കോൺടെക്സ്റ്റ് വിൻഡോ
- 203K 2,02,752 ടോക്കണുകൾ
- പരമാവധി ഔട്ട്പുട്ട്
- 131K 1,31,072 ടോക്കണുകൾ
- ഇൻപുട്ട് / ഔട്ട്പുട്ട്
- ടെക്സ്റ്റ് → ടെക്സ്റ്റ്
API നിരക്കുകൾ
USD / 10 ലക്ഷം ടോക്കണുകൾ
| ഇൻപുട്ട് | ഔട്ട്പുട്ട് | കാഷിൽ സൂക്ഷിച്ച ഇൻപുട്ട് |
|---|---|---|
|
|
|
കാലക്രമം
- · വെയ്റ്റുകളുടെ പതിപ്പ് · തെളിവിന്റെ ലിങ്ക്
ഇൻപുട്ട് / ഔട്ട്പുട്ട് വില · USD / 10 ലക്ഷം ടോക്കണുകൾ
| മോഡൽ | തെളിവുകളുടെ ലിങ്കുകൾ | ഇൻപുട്ട് / ഔട്ട്പുട്ട് വില |
|---|---|---|
glm-5standard | zai-pricing API റൂട്ട് ലഭ്യമല്ല | $1.00 / $3.20 |
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc
ഉദ്ധരണി
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
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · milabench/milabench · @bouthilx
ഉദ്ധരണി
- GLM-5: layout check before launch, loss from the last stage, checkpoint timing and checksums, crash cleanup; `benchmarks/megatron/dev.yaml`, `scripts/trillium/glm/`.
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · maximhq/bifrost · @mickgvirtu
ഉദ്ധരണി
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
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · ai-dynamo/frontend-crates · @dundysm
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @indrajit96
ഉദ്ധരണി
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
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · ROCm/ATOM · @whx-sjtu
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @moraxu
ഉദ്ധരണി
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`
- · തെളിവുകളുടെ ലിങ്കുകൾ · GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux
ഉദ്ധരണി
- `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`.
സാങ്കേതിക വിവരങ്ങൾ
Z.ai വികസിപ്പിച്ച മോഡലാണ് GLM-5; ഇതിന്റെ വെയിറ്റുകൾ പൊതുവായി ലഭ്യമാണ്; റിലീസ് ചെയ്ത തീയതി 2026-02-12. കോൺടെക്സ്റ്റ് വിൻഡോയുടെ വലുപ്പം 2,02,752 ടോക്കണുകൾ ആണ്. പരമാവധി ഔട്ട്പുട്ട് 1,31,072 ടോക്കണുകൾ ആണ്. പത്ത് ലക്ഷം ഇൻപുട്ട് ടോക്കണുകൾക്ക് $1.00, പത്ത് ലക്ഷം ഔട്ട്പുട്ട് ടോക്കണുകൾക്ക് $3.20 എന്നതാണ് വില.
- കോൺടെക്സ്റ്റ് വിൻഡോ
- 2,02,752
- പരമാവധി ഔട്ട്പുട്ട്
- 1,31,072
- ഇൻപുട്ട്
- ടെക്സ്റ്റ്
- ഔട്ട്പുട്ട്
- ടെക്സ്റ്റ്
- വെയിറ്റുകൾ
- തുറന്നത്
- ഇൻപുട്ട് · USD / 10 ലക്ഷം ടോക്കണുകൾ
- $1.00
- ഔട്ട്പുട്ട് · USD / 10 ലക്ഷം ടോക്കണുകൾ
- $3.20
- കാഷിൽ സൂക്ഷിച്ച ഇൻപുട്ട് · USD / 10 ലക്ഷം ടോക്കണുകൾ
- $0.20
ചോദ്യങ്ങൾ
GLM-5-ന്റെ കോൺടെക്സ്റ്റ് വിൻഡോയുടെ വലുപ്പം എത്രയാണ്?
കോൺടെക്സ്റ്റ് വിൻഡോയുടെ വലുപ്പം 2,02,752 ടോക്കണുകൾ ആണ്. പരമാവധി ഔട്ട്പുട്ട് 1,31,072 ടോക്കണുകൾ ആണ്.
GLM-5-ന്റെ വില എത്രയാണ്?
പത്ത് ലക്ഷം ഇൻപുട്ട് ടോക്കണുകൾക്ക് $1.00, പത്ത് ലക്ഷം ഔട്ട്പുട്ട് ടോക്കണുകൾക്ക് $3.20 എന്നതാണ് വില. കാഷിൽ സൂക്ഷിച്ച ഇൻപുട്ടിന് പത്ത് ലക്ഷം ടോക്കണുകൾക്ക് $0.20 ആണ് വില.
GLM-5-ന്റെ വെയിറ്റുകൾ പൊതുവായി ലഭ്യമാണോ?
അതെ. Z.ai വെയിറ്റുകൾ പ്രസിദ്ധീകരിക്കുന്നു.
GLM-5 എപ്പോഴാണ് റിലീസ് ചെയ്തത്?
2026-02-12 ന്.