Z.aiopen weightsGLM 5.1 pricing
$0.97 per 1M input tokens and $3.04 per 1M output tokens. In real work that is 0.55¢ per chat answer and 1.8¢ to summarize a 20-page PDF.
What GLM 5.1 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 | 0.55¢$5.46 / 1,000 | 48 in · 391 out · 1,391 reasoning | 229 of 336 | estimated |
| Reply to a customer email | 0.10¢$1.04 / 1,000 | 265 in · 234 out · 24 reasoning | 172 of 336 | estimated |
| Write a 1,500-word blog post | 2.1¢$21.08 / 1,000 | 62 in · 2,174 out · 4,749 reasoning | 239 of 336 | estimated |
| Write 10 product descriptions | 2.2¢$21.66 / 1,000 | 289 in · 1,101 out · 5,940 reasoning | 274 of 336 | estimated |
| Translate 1,000 words | 3.2¢$32.12 / 1,000 | 1,330 in · 1,394 out · 8,761 reasoning | 278 of 336 | estimated |
| Proofread one page (500 words) | 0.31¢$3.12 / 1,000 | 730 in · 642 out · 155 reasoning | 187 of 336 | estimated |
| Summarize a 20-page PDF | 1.8¢$18.06 / 1,000 | 12,995 in · 544 out · 1,270 reasoning | 236 of 336 | estimated |
| Extract data from an invoice | 0.35¢$3.51 / 1,000 | 391 in · 455 out · 576 reasoning | 202 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥5.3¢$53.31 / 1,000 | 4,900 in · 0 out · 16,000 reasoning | 243 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.96¢$9.57 / 1,000 | 3,714 in · 274 out · 1,697 reasoning | 229 of 336 | estimated |
| Classify 100 support tickets | 2.5¢$25.08 / 1,000 | 1,281 in · 441 out · 7,411 reasoning | 276 of 336 | estimated |
| Review 500 lines of code | ≥5.3¢$52.95 / 1,000 | 4,532 in · 2 out · 15,998 reasoning | 257 of 336 | estimated |
| Write a SQL query | 0.50¢$4.97 / 1,000 | 128 in · 473 out · 1,123 reasoning | 227 of 336 | estimated |
| Run a 50-step coding agent | 60¢$599 / 1,000 | 2,239,737 in · 15,014 out · 28,800 reasoning | 187 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GLM 5.1 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| B Baidufp8 | $0.96 / $3.03 | $0.18 | 202K | 100% |
| S StreamLakefp8 | $0.97 / $3.04 | $0.18 | 200K | 100% |
 Chutesfp8 | $0.98 / $3.08 | $0.098 | 202K | 75% |
 SiliconFlowfp8 | $1.19 / $3.74 | $0.60 | 204K | 100% |
| A AtlasCloudfp8 | $1.26 / $3.96 | $0.23 | 202K | 100% |
| P Phalaunknown | $1.21 / $4.20 | $0.60 | 202K | |
 Alibabafp8 | $1.33 / $4.18 | $0.25 | 202K | 100% |
 Novitafp8 | $1.38 / $4.40 | $0.26 | 204K | 100% |
 Nebiusfp8 | $1.40 / $4.40 | - | 202K | 100% |
| G GMICloudfp8 | $1.40 / $4.40 | $0.26 | 202K | 100% |
| F Friendliunknown | $1.40 / $4.40 | $0.26 | 202K | 100% |
Z.AIfp8 | $1.40 / $4.40 | $0.26 | 202K | 100% |
| V Venicefp8 | $1.40 / $4.40 | $0.26 | 200K |
Price history
First seen in our price history on Apr 7, 2026 at $1.00 input / $3.20 output. Since then the output price moved from $3.20 to $3.04 per 1M tokens (7 changes).
FAQ
How much does GLM 5.1 cost?
GLM 5.1 costs $0.97 per 1 million input tokens and $3.04 per 1 million output tokens, with cached input at $0.18 (list price on Oct 18, 2026). In practice one chat answer costs about 0.55¢ and summarizing a 20-page PDF about 1.8¢.
Where is GLM 5.1 cheapest?
Among 13 providers we track, the lowest list price today is at Baidu: $0.96 input and $3.03 output per 1M tokens.
Is the GLM 5.1 cost per task measured or estimated?
Estimated: GLM 5.1 was not run directly. Tokens come from GLM 5.3 Flash and are rescaled by the tokenizer of Z.ai. Real usage can differ.