The Orchestrator › Models › Z.ai
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...
Specifications
| Provider | Z.ai |
| Model ID | z-ai/glm-4.6 |
| Context window | 205K tokens (204,800) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2025-09-30 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | z-ai/glm-4.6 | $0.5 | $2.00 | 205K |
| standard | TrustedRouter | zai-org/glm-4.6 | $0.58 | $2.32 | 205K |
| standard | Vercel AI Gateway | z-ai/glm-4.6 | $0.6 | $2.20 | 200K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.6 | $2.20 | 200K |
| 2026-11-14 | $0.58 | $2.32 | 205K |
| 2026-11-14 | $0.454 | $1.85 | 203K |
| 2026-11-14 | $0.5 | $2.00 | 205K |
Capabilities
Agentic tool useStructured outputsControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
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