Z.aiopen weightsGLM 4.5 Air pricing
$0.13 per 1M input tokens and $0.85 per 1M output tokens. In real work that is 0.15¢ per chat answer and 0.32¢ to summarize a 20-page PDF.
What GLM 4.5 Air costs per task
Token counts estimated from a measured model of the same lab (GLM 5.3 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.15¢$1.52 / 1,000 | 48 in · 391 out · 1,391 reasoning | 136 of 336 | estimated |
| Reply to a customer email | 0.03¢$0.25 / 1,000 | 265 in · 234 out · 24 reasoning | 71 of 336 | estimated |
| Write a 1,500-word blog post | 0.59¢$5.89 / 1,000 | 62 in · 2,174 out · 4,749 reasoning | 148 of 336 | estimated |
| Write 10 product descriptions | 0.60¢$6.02 / 1,000 | 289 in · 1,101 out · 5,940 reasoning | 170 of 336 | estimated |
| Translate 1,000 words | 0.88¢$8.80 / 1,000 | 1,330 in · 1,394 out · 8,761 reasoning | 179 of 336 | estimated |
| Proofread one page (500 words) | 0.08¢$0.77 / 1,000 | 730 in · 642 out · 155 reasoning | 81 of 336 | estimated |
| Summarize a 20-page PDF | 0.32¢$3.23 / 1,000 | 12,995 in · 544 out · 1,270 reasoning | 93 of 336 | estimated |
| Extract data from an invoice | 0.09¢$0.93 / 1,000 | 391 in · 455 out · 576 reasoning | 94 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.4¢$14.24 / 1,000 | 4,900 in · 0 out · 16,000 reasoning | 128 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.22¢$2.16 / 1,000 | 3,714 in · 274 out · 1,697 reasoning | 101 of 336 | estimated |
| Classify 100 support tickets | 0.68¢$6.84 / 1,000 | 1,281 in · 441 out · 7,411 reasoning | 170 of 336 | estimated |
| Review 500 lines of code | ≥1.4¢$14.19 / 1,000 | 4,532 in · 2 out · 15,998 reasoning | 179 of 336 | estimated |
| Write a SQL query | 0.14¢$1.37 / 1,000 | 128 in · 473 out · 1,123 reasoning | 129 of 336 | estimated |
| Run a 50-step coding agent | 10¢$102 / 1,000 | 2,239,737 in · 15,014 out · 28,800 reasoning | 56 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GLM 4.5 Air through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Novitabf16 | $0.13 / $0.85 | $0.025 | 131K | 100% |
 SiliconFlowfp8 | $0.14 / $0.86 | - | 131K | |
Z.AIfp8 | $0.20 / $1.10 | $0.03 | 131K | 100% |
Price history
First seen in our price history on Jul 29, 2025 at $0.20 input / $1.10 output. Since then the output price moved from $1.10 to $0.85 per 1M tokens (7 changes).
FAQ
How much does GLM 4.5 Air cost?
GLM 4.5 Air costs $0.13 per 1 million input tokens and $0.85 per 1 million output tokens, with cached input at $0.025 (list price on Oct 18, 2026). In practice one chat answer costs about 0.15¢ and summarizing a 20-page PDF about 0.32¢.
Where is GLM 4.5 Air cheapest?
Among 3 providers we track, the lowest list price today is at Novita: $0.13 input and $0.85 output per 1M tokens.
Is the GLM 4.5 Air cost per task measured or estimated?
Estimated: GLM 4.5 Air was not run directly. Tokens come from GLM 5.3 Flash and are rescaled by the tokenizer of Z.ai. Real usage can differ.