Z.aiopen weightsGLM 4.6 pricing
$0.50 per 1M input tokens and $2.00 per 1M output tokens. In real work that is 0.36¢ per chat answer and 1.0¢ to summarize a 20-page PDF.
What GLM 4.6 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 | 0.36¢$3.59 / 1,000 | 48 in · 391 out · 1,391 reasoning | 208 of 336 | estimated |
| Reply to a customer email | 0.06¢$0.65 / 1,000 | 265 in · 234 out · 24 reasoning | 127 of 336 | estimated |
| Write a 1,500-word blog post | 1.4¢$13.88 / 1,000 | 62 in · 2,174 out · 4,749 reasoning | 208 of 336 | estimated |
| Write 10 product descriptions | 1.4¢$14.23 / 1,000 | 289 in · 1,101 out · 5,940 reasoning | 245 of 336 | estimated |
| Translate 1,000 words | 2.1¢$20.98 / 1,000 | 1,330 in · 1,394 out · 8,761 reasoning | 248 of 336 | estimated |
| Proofread one page (500 words) | 0.20¢$1.96 / 1,000 | 730 in · 642 out · 155 reasoning | 151 of 336 | estimated |
| Summarize a 20-page PDF | 1.0¢$10.13 / 1,000 | 12,995 in · 544 out · 1,270 reasoning | 187 of 336 | estimated |
| Extract data from an invoice | 0.23¢$2.26 / 1,000 | 391 in · 455 out · 576 reasoning | 161 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥3.4¢$34.45 / 1,000 | 4,900 in · 0 out · 16,000 reasoning | 202 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.58¢$5.80 / 1,000 | 3,714 in · 274 out · 1,697 reasoning | 185 of 336 | estimated |
| Classify 100 support tickets | 1.6¢$16.34 / 1,000 | 1,281 in · 441 out · 7,411 reasoning | 241 of 336 | estimated |
| Review 500 lines of code | ≥3.4¢$34.27 / 1,000 | 4,532 in · 2 out · 15,998 reasoning | 231 of 336 | estimated |
| Write a SQL query | 0.33¢$3.26 / 1,000 | 128 in · 473 out · 1,123 reasoning | 196 of 336 | estimated |
| Run a 50-step coding agent | 34¢$344 / 1,000 | 2,239,737 in · 15,014 out · 28,800 reasoning | 137 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GLM 4.6 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp4 | $0.40 / $1.60 | $0.08 | 202K | |
| V Venicefp4 | $0.43 / $1.75 | $0.08 | 198K | 100% |
DeepInfrafp4 | $0.50 / $2.00 | $0.10 | 202K | 100% |
 Novitabf16 | $0.55 / $2.20 | $0.11 | 204K | 100% |
Z.AIfp4 | $0.60 / $2.20 | $0.11 | 202K | 100% |
Price history
First seen in our price history on Oct 1, 2025 at $0.60 input / $2.00 output. Since then the output price moved from $2.00 to $2.00 per 1M tokens (10 changes).
FAQ
How much does GLM 4.6 cost?
GLM 4.6 costs $0.50 per 1 million input tokens and $2.00 per 1 million output tokens, with cached input at $0.10 (list price on Oct 18, 2026). In practice one chat answer costs about 0.36¢ and summarizing a 20-page PDF about 1.0¢.
Where is GLM 4.6 cheapest?
Among 5 providers we track, the lowest list price today is at DeepInfra: $0.40 input and $1.60 output per 1M tokens.
Is the GLM 4.6 cost per task measured or estimated?
Estimated: GLM 4.6 was not run directly. Tokens come from GLM 5.3 Flash and are rescaled by the tokenizer of Z.ai. Real usage can differ.