AI Observatory / Model Radar
Z Ai / z-ai/glm-4.6
Z.ai: 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...
204,800
Context
204,800
Max output
$0.39 / 1M
Prompt price
2025-09-30
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Z Ai | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.39 / 1M |
| Completion price | $1.90 / 1M | Request price | N/A |
| Context length | 204,800 | Max completion tokens | 204,800 |
| 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 | ||
Best for
z-ai/glm-4.6
Z.ai: 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...
Long context
High-volume usage
Coding workflows
tool-capable
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.