glm-5.2 API

GLM-5.2 is the flagship foundation model from Zhipu AI (published internationally under the Z.ai brand), built specifically for long-horizon software-engineering tasks. Z.ai documents a 1M-token context window with up to 128K output tokens, and positions GLM-5.2 as the strongest open-source model on agentic coding benchmarks — scoring 81.0 on Terminal-Bench 2.1 and trailing the top proprietary model by roughly one point on FrontierSWE, according to the provider's own published results. What sets GLM-5.2 apart from earlier GLM generations is stability over long tasks rather than raw single-turn cleverness. Z.ai highlights project-level codebase understanding, multi-file refactoring, reliable adherence to engineering conventions, and higher end-to-end success rates in development scenarios. The genuinely usable 1M-token context means an entire mid-sized repository, a week of build logs, or a full documentation set fits into a single request instead of being chopped into lossy retrieval fragments. The model also ships with multiple thinking modes, so it can spend more deliberation on hard problems and answer quickly on easy ones. On CaMeL Hub, glm-5.2 is exposed through both the OpenAI-compatible /v1/chat/completions endpoint and the Anthropic-compatible /v1/messages endpoint — existing OpenAI SDK or Claude SDK code works after changing only the base URL and API key. Responses stream token by token, which matters for a model that can emit up to 128K tokens in one completion. Billing is strictly pay-as-you-go with separately metered input ($8 per 1M tokens) and output ($28 per 1M tokens); you can top up with Alipay, WeChat Pay, or international cards and switch between GLM-5.2 and any other hosted model by changing one string.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="glm-5.2",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "glm-5.2",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);