{
"companyAnalysis": "上海盈通电气有限公司是一家专业从事电力质量解决方案的公司，专注于积极谐波滤波器、静态无功发生器、能源存储系统等产品的研发、生产和销售。他们在新能量和电力质量管理方面处于领先地位，且有良好的行业声誉，涉及的领域包括能源效率管理等。",
"type": "1",
"JudgmentResult": "1",
"JudgmentReason": "公司主营产品中包括积极谐波滤波器，与搜索目标Active Harmonic filter直接相关。",
"HumanReason": "我们公司做的就是积极谐波滤波器的相关业务，自然与这个搜索目标相关，满足客户需求。"
}
GLM-5 uses a Mixture of Experts (MoE) architecture with ~745B total parameters and 8 active experts per token (~44B active), enabling efficient large-scale reasoning and agentic workflows compared to previous GLM series.
GLM-5 supports a 200K token context window with up to 128K output tokens, making it suitable for extended reasoning and document tasks.
Yes — GLM-5 is explicitly optimized for long-horizon agent tasks and complex systems engineering workflows, with deep reasoning and planning capabilities beyond standard chat models.
Yes — GLM-5 supports function calling, structured JSON outputs, context caching, and real-time streaming to integrate with external tools and systems.
GLM-5 is competitive with top proprietary models in benchmarks, performing close to Claude Opus 4.5 and offering significantly lower per-token costs and open-weight availability, though closed-source models may still lead in some fine-grained benchmarks.
Yes — GLM-5 is released under a permissive MIT license, enabling open-weight access and community development.
GLM-5 is well suited for long-sequence reasoning, agentic automation, coding assistance, creative writing at scale, and backend system design tasks that demand coherent multi-step outputs.
While powerful, GLM-5 is primarily text-only (no native multimodal support) and may be slower or more resource-intensive than smaller models, especially for shorter tasks.
| Comet 价格 (USD / M Tokens) | 官方定价 (USD / M Tokens) | 折扣 |
|---|---|---|
輸入:$0.672/M 輸出:$2.688/M | 輸入:$0.84/M 輸出:$3.36/M | -20% |
from openai import OpenAI
import os
# Get your CometAPI key from https://api.cometapi.com/console/token
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com/v1"
client = OpenAI(base_url=BASE_URL, api_key=COMETAPI_KEY)
# glm-5: Zhipu GLM-5 model via chat/completions
completion = client.chat.completions.create(
model="glm-5",
messages=[{"role": "user", "content": "Hello! Tell me a short joke."}],
)
print(completion.choices[0].message.content)