The Orchestrator › Models › Z.ai
Z.ai: GLM 4.5 Air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
Specifications
| Provider | Z.ai |
| Model ID | z-ai/glm-4.5-air |
| Context window | 131K tokens (131,072) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2025-07-25 |
| 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-4.5-air | $0.2 | $1.10 | 131K |
| standard | TrustedRouter | zai-org/glm-4.5-air | $0.137 | $0.897 | 131K |
| standard | Vercel AI Gateway | z-ai/glm-4.5-air | $0.2 | $1.10 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.2 | $1.10 | 128K |
| 2026-11-14 | $0.137 | $0.897 | 131K |
| 2026-11-14 | $0.165 | $0.988 | 131K |
| 2026-11-14 | $0.2 | $1.10 | 131K |
Capabilities
Agentic tool useControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, tool_choice, tools, top_k, top_p