1 million GLM-4.5-AirX (Z.ai) tokens cost $1.10 as input or $4.50 as output. Most workloads land in between — a 70/30 input/output split costs about $2.12. Verified Aug 26, 2026
Quick answer
For GLM-4.5-AirX (Z.ai), 1 million tokens cost $1.10 as input or $4.50 as output. A representative 70/30 workload is about $2.12.
Method & trust
The page prices the selected token volume using the model's listed input and output rates, then applies a 70/30 input/output split for the representative workload. Cached input, batch discounts, retries, and provider fees can change the final invoice.
Interactive calculator
1,000,000 in · 0 out
Input price
$1.10 / 1M tokens
Output price
$4.50 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 1 million tokens buys in practice
$1.78
80% input / 20% output — short replies over conversation history.
$1.44
90% input / 10% output — long retrieved context, grounded answers.
$1.27
95% input / 5% output — full documents in, structured extraction out.
Same 1 million tokens on other models
Related calculations
FAQ
1 million input tokens cost $1.10; 1 million output tokens cost $4.50. A typical 70/30 input/output mix costs about $2.12. Rates: $1.10/M input, $4.50/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 1 million tokens is roughly 208 requests. For a RAG workload with ~8,500 tokens per request, about 118 requests.
Yes — cached input costs $0.22/M instead of $1.10/M, a 80% discount on repeated context.