Available now
Zhipu
glm-4.6
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...
TextReasoningToolsOpen Weights204.8KCache
Input$0.36/ 1M
Output$1.32/ 1M
Context204.8K
Endpointsopenai
Capabilities
ReasoningToolsCacheStructured
Modalities
Input
text
Output
text
Quick stats
Context window204.8K
Max output131.1K
Modechat
TokenizerOther
Knowledge cutoff2025
Quantizationfp4
Hugging Facezai-org/GLM-4.6
Performance
Loading performance data...
Supported parameters
| Parameter | Always | Default |
|---|---|---|
| frequency_penalty | - | (do not send) |
| include_reasoning | - | |
| logit_bias | - | - |
| max_tokens | - | |
| min_p | - | - |
| presence_penalty | - | (do not send) |
| reasoning | - | |
| repetition_penalty | - | (do not send) |
| response_format | - | - |
| seed | - | - |
| stop | - | - |
| structured_outputs | - | - |
| temperature | 0.6 | |
| tool_choice | - | |
| tools | - | |
| top_k | (do not send) | |
| top_p | (do not send) |
§ 01
Pricing
| Input price | $0.36 · 1M tokens |
| Output price | $1.32 · 1M tokens |
| Context window | 204.8K tokens |
| Compatible endpoints | openai |
| Vendor | Zhipu |
§ 02
Call glm-4.6 from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
bash
curl https://api.unorouter.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-4.6",
"messages": [{"role": "user", "content": "Hello!"}]
}'§ 03
Frequently asked questions
How much does glm-4.6 cost per 1M tokens?
Input is priced at $0.36 per 1M tokens, output at $1.32 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access glm-4.6 via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=glm-4.6. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
What is the context window of glm-4.6?
glm-4.6 supports a context window of 204.8K tokens, shared between your prompt and the model's response.
§ 04