Our agents fan out thousands of cheap classification and tagging calls to the GLM 4.5 Air API through RouterBase — the cost per token keeps the whole pipeline economical.
The GLM 4.5 Air API is Z.ai's lightweight, low-cost GLM model — a frontier LLM for advanced reasoning, coding, and agentic workflows, with native tool calling, structured outputs, and a long context window. The GLM 4.5 Air API is OpenAI-compatible: point any existing SDK at RouterBase and set the model to glm-4-5-air. Input at $0.19 / 1M tokens, output at $1.045 / 1M tokens, cached-input reads at $0.0285 / 1M — 5% below the official rate, all through one REST endpoint.
Input
GLM-4.5-Air
Hi! I'm a helpful AI assistant. What can I do for you?
GLM 4.5 Air API: Chat
Use the GLM 4.5 Air API to run Z.ai's lightweight, low-cost GLM model — advanced reasoning, coding, and agentic workflows with native tool calling.
The GLM 4.5 Air API is Z.ai's lightweight, low-cost GLM model — a frontier large language model built for advanced reasoning, coding, and agentic workflows, with native tool calling, structured outputs, and a long context window. Routed through RouterBase, the GLM 4.5 Air API is fully OpenAI-compatible: point any existing SDK at RouterBase's base URL, set the model to glm-4-5-air, and your first GLM 4.5 Air API call goes through immediately.
Pricing for the GLM 4.5 Air API is $0.19 / 1M input tokens, $1.045 / 1M output tokens, and $0.0285 / 1M cached-input reads — 5% below the official published rate. One RouterBase key reaches the GLM 4.5 Air API and 200+ other models — no Z.ai account required.
Six reasons teams ship on the GLM 4.5 Air API
From lightweight reasoning to 5%-off pricing — what makes the GLM 4.5 Air API stand out.
Lightweight & low-cost
The GLM 4.5 Air API is Z.ai's lightweight, low-cost GLM model — strong reasoning, math, and analysis for the hardest problems your product can throw at it.
Built for code
The GLM 4.5 Air API handles multi-file code generation, refactoring, and debugging — a strong choice for coding agents and developer tools.
Native tool calling
The GLM 4.5 Air API supports function / tool calling out of the box — wire it into agents and let it call your tools in the OpenAI format.
Long context window
The GLM 4.5 Air API accepts long inputs — fit long documents, multi-file codebases, or full conversation history into a single call.
OpenAI-compatible, one key
The GLM 4.5 Air API speaks the OpenAI chat-completions format; the same RouterBase key also routes to GPT-5.5, Claude, Gemini, and 200+ other models.
5% below official
The GLM 4.5 Air API is priced 5% under Z.ai's published rate — $0.19 / 1M input, $1.045 / 1M output. Pay only for the tokens you use.
Quickstart
Get started with the GLM 4.5 Air API in 3 steps
From sign-up to your first response in under 5 minutes.
Create a RouterBase API key
Sign up and generate an API key — one key reaches the GLM 4.5 Air API and every other model in the catalog.
Send your first message
Point any OpenAI-compatible SDK at routerbase.com/v1 and set the model to glm-4-5-air. The GLM 4.5 Air API response follows the standard chat-completions schema — streaming and tool use supported.
Inspect usage
Every GLM 4.5 Air API response includes a detailed token breakdown — input, output, and cached-input tokens — so cost and cache-hit rate are visible on every call.
Pay only for what you use
RouterBase passes through partner-tier pricing. Compared against the model's official published API rate.
What teams build with the GLM 4.5 Air API
Real production loads running on the RouterBase model catalog across 200+ models.
We swapped our pricey extraction model for the GLM 4.5 Air API in one line through RouterBase — same prompts, a fraction of the bill, no users noticed.
Tool calling on the GLM 4.5 Air API dropped straight into our existing routing agent — no custom adapter, and at this price we can let it run all day.
RouterBase puts 200+ models behind one key. We A/B the GLM 4.5 Air API against bigger models on our summarization-at-scale jobs — it holds up at a fraction of the cost.
At $0.19 per 1M input the GLM 4.5 Air API made high-volume RAG affordable — we run far more queries for the same budget than we ever could before.
We pointed our OpenAI SDK at RouterBase with one base-URL swap and the GLM 4.5 Air API became our cheap, fast drop-in for high-throughput batch work.
Frequently Asked Questions
Common questions about the GLM 4.5 Air API.
The GLM 4.5 Air API is RouterBase's pass-through to Z.ai's GLM-4.5-Air — Z.ai's lightweight, low-cost GLM model for reasoning, coding, and agentic work, served via an OpenAI-compatible REST interface with native tool calling and structured outputs.