GLM 4.6
Z.aiReleased Sep 30, 2025
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
- Context window
- 203K tokens
- Max output
- 131K tokens
- Input
- text
- Output
- text
- Tokenizer
- Other
- Knowledge cutoff
- Mar 31, 2025
- Released
- Sep 30, 2025
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.430 | $0.013 | $0.443 |
| Output | $1.74 | $0.052 | $1.79 |
| Cache read | $0.080 | $0.0024 | $0.082 |
Benchmarks
Artificial Analysis
- Intelligence index
- Coding index
- Agentic index
- 17.7
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| androidnativeagents | 1097 | 52.5% | #20 |
| Full-stackagents | 1098 | 42.3% | #22 |
| godotgamedevagents | 1219 | 53.2% | #7 |
| Mobile appsagents | 1186 | 49.3% | #19 |
| 3Dmodels | 1205 | 54% | #42 |
| Codemodels | 1215 | 54.3% | #47 |
| Data vizmodels | 1208 | 52.8% | #44 |
| Game devmodels | 1215 | 54.6% | #40 |
| SVGmodels | 1167 | 52.1% | #38 |
| UI componentsmodels | 1214 | 54% | #43 |
| Websitesmodels | 1217 | 54.4% | #47 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model z-ai/glm-4.6.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-4.6",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="z-ai/glm-4.6",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "z-ai/glm-4.6",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does GLM 4.6 cost via API?
- Through OpenKey, GLM 4.6 costs $0.443 per 1M input tokens and $1.79 per 1M output tokens. That is the provider price ($0.430 / $1.74) plus a flat 3% fee — nothing else.
- What is GLM 4.6's context window?
- GLM 4.6 accepts up to 203K tokens of context and returns up to 131K tokens per request.
- Is GLM 4.6 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "z-ai/glm-4.6" using any OpenAI SDK — only the base URL and API key change.
- What inputs does GLM 4.6 support?
- GLM 4.6 accepts text input and produces text output. Its knowledge cutoff is Mar 31, 2025.
More from Z.ai
All Z.ai models →GLM 5.2
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
ctx 1.0Min $0.958out $3.09
GLM 5.1
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...
ctx 203Kin $1.00out $4.43
GLM 5V Turbo
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...
ctx 203Kin $1.24out $4.12
GLM 5 Turbo
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
ctx 262Kin $1.24out $4.12