128K context · 9B params · Apache-2.0
zhipu/codegeex
CodeGeeX4 is Zhipu's open-source multilingual code-generation model (20+ languages) with strong agentic coding, repository-level understanding and tool use, built on the GLM-4 backbone.
Reachability & verification
Live reachability
Target (Zhipu AI): https://open.bigmodel.cn/api/paas/v4
Overseas reference latency (est.)
Live reachability probe
Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.
Official Path Verified by ModelHub
Pricing across providers
1Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.
| Provider | Input /1M | Output /1M | Blended | Ctx | p50 latency | API | Verified |
|---|---|---|---|---|---|---|---|
| Zhipu AIcodegeex-4 | ¥0.5 | ¥1.5 | ¥0.8 | 128K | — | OAI | 43d ago |
Works with
Any OpenAI-compatible client works — point the base URL at the provider endpoint.
Capabilities
Languages: en, zh, +20 langs
Code samples
from openai import OpenAI
client = OpenAI(
base_url="https://open.bigmodel.cn/api/paas/v4",
api_key="YOUR_API_KEY",
)
resp = client.chat.completions.create(
model="codegeex-4",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)curl https://open.bigmodel.cn/api/paas/v4/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "codegeex-4",
"messages": [{"role": "user", "content": "Hello!"}]
}'import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://open.bigmodel.cn/api/paas/v4",
apiKey: "YOUR_API_KEY",
});
const resp = await client.chat.completions.create({
model: "codegeex-4",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Technical specs
Context
128K
Max output
—
Parameters
9B
Release
2025
Training cutoff
—
License
Apache-2.0
Similar models
Frequently asked questions
How much does CodeGeeX4 cost?
The cheapest tracked blended price is ¥0.8 per 1M tokens on Zhipu AI. See the pricing matrix above for input/output splits per provider.
Can I use CodeGeeX4 from outside China?
Availability depends on the hosting provider. Use our Path Planner on the Zhipu AI page to map a verified official-vs-brokered access path, including payment and KYC constraints.
Is CodeGeeX4 open source?
Yes — CodeGeeX4 is open-weight under the Apache-2.0 license. You can self-host it or use any listed inference provider.
Is CodeGeeX4 OpenAI-compatible?
Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.
What is the maximum context window?
CodeGeeX4 supports up to 128K tokens of context with a maximum output of — tokens.
Need verified access to CodeGeeX4?
We broker vetted intros to Zhipu AI — payment, KYC and endpoint verification handled.