Z-ai model
GLM 5 API cost calculator
GLM 5 costs $1 per 1M input tokens and $3.20 per 1M output tokens on the Z-ai API, with a 205K-token context window. A typical request (2K input, 500 output tokens) costs $0.0036 — about $108/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on GLM 5
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0015 | $1.46 |
| RAG query with context | 4,000 / 500 | $0.0056 | $5.60 |
| Document summarization | 20,000 / 1,000 | $0.02 | $23.20 |
| Agent coding session | 100,000 / 5,000 | $0.12 | $116 |
GLM 5 vs other Z-ai models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| GLM 5 | $1 | $3.20 | 205K |
| GLM 5.3 Prime | $2.80 | $8.80 | 1M |
| GLM 5.3 FlashX | $0.37 | $1.25 | 1.0M |
| GLM 5.3 Flash | $0.15 | $0.50 | 1.0M |
| GLM 5.3 | $0.07 | $1.40 | 1.0M |
Frequently asked questions
How much does GLM 5 cost per 1M tokens?
According to current pricing data, GLM 5 costs $1 per 1M input tokens and $3.20 per 1M output tokens. Processing 1M tokens each way costs $4.20.
What does a typical API request to GLM 5 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0036. At 1,000 requests per day that is $3.60 daily, or about $108 per month.
What is GLM 5's context window?
GLM 5 supports a 205K-token context window (204,800 tokens).
Does GLM 5 support prompt caching?
Yes. Cached input tokens cost $0.20 per 1M — a 80% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to GLM 5?
gpt-oss-20b from OpenAI is currently the cheapest comparable option at $0.02 per 1M input tokens versus $1 for GLM 5 — roughly 56x cheaper on input.
Compare all current prices on the live model pricing dashboard, see GLM 5 vs gpt-oss-20b pricing, or run GLM 5 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.