GLM 4.6 vs GLM-4.5-FP8 API pricing
Updated
GLM 4.6: USD 0.43 input, USD 1.75 output per 1M tokens (Venice). GLM-4.5-FP8: USD 0.60 input, USD 2.20 output per 1M tokens (Z.ai and 1 other). At 3 input tokens per output token, GLM-4.5-FP8 costs 32% more than GLM 4.6 (USD 1 vs USD 0.76 per 1M).
How do GLM 4.6 and GLM-4.5-FP8 differ on price?
- Cheapest input price: GLM 4.6 USD 0.43 against USD 0.60 per 1M tokens, so GLM-4.5-FP8 costs 1.4× as much (40% more).
- Cheapest output price: GLM 4.6 USD 1.75 against USD 2.20 per 1M tokens, so GLM-4.5-FP8 costs 1.26× as much (26% more).
- Among the 201 indexed models, GLM 4.6 ranks 119th cheapest and GLM-4.5-FP8 131st on the 3:1 blend.
- No input:output mix changes the answer: GLM 4.6 is cheaper at every mix before cache discounts.
- Both list cached-input discounts: GLM 4.6 at 5 standard prices of 6, from USD 0.08 (Venice, 81% below that provider's input price); GLM-4.5-FP8 at 1 standard price of 2, from USD 0.11 (Z.ai, 82% below that provider's input price).
- GLM 4.6 states up to 204,800 tokens of context, 1.56× the 131,072 of GLM-4.5-FP8.
- GLM 4.6 has 6 providers with a standard price, 4 more than GLM-4.5-FP8; 2 providers sell both (GMI Cloud and Z.ai).
- On one account, GMI Cloud charges USD 0.95 for GLM 4.6 (1.25× its cheapest price) and USD 1 for GLM-4.5-FP8 (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for GLM 4.6: its dearest standard price is 1.32× its cheapest, against 1× for GLM-4.5-FP8.
- Z.ai's own API charges USD 1 for GLM 4.6 at 3:1, 32% above the cheapest provider (Venice).
- Z.ai's own API is one of 2 providers tied for the lowest standard price we found for GLM-4.5-FP8, USD 1 at 3:1.
- For the one-developer coding agent preset, the gap is USD 1,588 a year in GLM 4.6's favour (GLM 4.6 USD 396.00 a month, GLM-4.5-FP8 USD 528.30).
GLM 4.6 and GLM-4.5-FP8 prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | GLM 4.6 | GLM-4.5-FP8 |
|---|---|---|
| Model page | GLM 4.6 Z.ai · 6 providers | GLM-4.5-FP8 Z.ai · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.76 lower USD 0.43 in / USD 1.75 out at Venice Venice page checked 2026-11-15 | USD 1 USD 0.60 in / USD 2.20 out at Z.ai and 1 other Z.ai page checked 2026-11-14 |
| Cheapest input | USD 0.43 lower Venice source | USD 0.60 Z.ai source |
| Cheapest cached input | USD 0.08 lower Venice source | USD 0.11 Z.ai source |
| Cheapest output | USD 1.75 lower Venice source | USD 2.20 Z.ai source |
| Maker's own API | USD 0.60 / USD 2.20 Z.ai source | USD 0.60 / USD 2.20 Z.ai source |
| Median standard price | USD 0.55 / USD 2.10 input / output, 6 prices | USD 0.60 / USD 2.20 input / output, 2 prices |
| Context window | 204,800 tokens, largest stated; from 198,000 at some providers | 131,072 tokens, largest stated |
| Providers with a standard price | 6 | 2 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do GLM 4.6 and GLM-4.5-FP8 cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | GLM 4.6 | GLM-4.5-FP8 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 51.30 Venice | USD 67.14 Z.ai | USD 15.84 GLM 4.6 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 104.25 Venice | USD 141.72 Z.ai | USD 37.47 GLM 4.6 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 396.00 Venice | USD 528.30 Z.ai | USD 132.30 GLM 4.6 lower |
GLM 4.6 is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 36% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
GLM 4.6 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below GLM-4.5-FP8's, so the input:output ratio never changes the answer.
| Input : output tokens | GLM 4.6 | GLM-4.5-FP8 |
|---|---|---|
| 1 : 3 (long answers) | USD 1.42 lower Venice | USD 1.80 Z.ai |
| 1 : 1 | USD 1.09 lower Venice | USD 1.40 Z.ai |
| 3 : 1 (the site’s blend) | USD 0.76 lower Venice | USD 1 Z.ai |
| 10 : 1 (retrieval, long prompts) | USD 0.55 lower Venice | USD 0.7455 Z.ai |
| 30 : 1 (agents, big contexts) | USD 0.4726 lower Venice | USD 0.6516 Z.ai |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do GLM 4.6 and GLM-4.5-FP8 cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and GLM 4.6 and GLM-4.5-FP8 are not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- GLM 4.6 API pricing: all 6 providers and other tiers.
- GLM-4.5-FP8 API pricing: all 2 providers and other tiers.
- Cost calculator with GLM 4.6 and GLM-4.5-FP8 preloaded
- GLM token counter
- Prompt caching calculator
More comparisons: GLM 4.7 vs GLM 4.6 · GLM 4.5V vs GLM-4.5-FP8 · GLM 4.5 Air vs GLM-4.5-FP8 · every GLM 4.6 comparison · every GLM-4.5-FP8 comparison · all 662 price comparisons
Questions
Is GLM 4.6 cheaper than GLM-4.5-FP8?
Yes. On a blend of 3 input tokens to 1 output token, GLM 4.6 costs USD 0.76 per 1M tokens and GLM-4.5-FP8 USD 1, at each model's cheapest standard price. For input alone, GLM 4.6 is cheaper (USD 0.43 against USD 0.60 per 1M); for output alone, GLM 4.6 is (USD 1.75 against USD 2.20). This compares price only, not quality.
What do GLM 4.6 and GLM-4.5-FP8 cost per 1M tokens?
GLM 4.6: from USD 0.43 input and USD 1.75 output at Venice; Z.ai's own API charges USD 0.60 / USD 2.20; median of 6 standard prices USD 0.55 / USD 2.10. GLM-4.5-FP8: from USD 0.60 input and USD 2.20 output at Z.ai and 1 other; Z.ai's own API charges USD 0.60 / USD 2.20; median of 2 standard prices USD 0.60 / USD 2.20. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both GLM 4.6 and GLM-4.5-FP8?
2 providers have a standard price for both: GMI Cloud (USD 0.95 and USD 1 at 3:1), Z.ai (USD 1 and USD 1 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.76 and USD 1.
Which is cheaper for a coding agent or a chatbot, GLM 4.6 or GLM-4.5-FP8?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 396.00 a month on GLM 4.6 (Venice) against USD 528.30 on GLM-4.5-FP8 (Z.ai), a difference of USD 132.30. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 51.30 a month on GLM 4.6 (Venice) against USD 67.14 on GLM-4.5-FP8 (Z.ai), a difference of USD 15.84. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of GLM 4.6 and GLM-4.5-FP8 change?
GLM 4.6 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below GLM-4.5-FP8's, so the input:output ratio never changes the answer.
Do GLM 4.6 and GLM-4.5-FP8 have cached input pricing?
GLM 4.6 from USD 0.08 per 1M cached input tokens (Venice; 5 of 6 standard prices list a discount). GLM-4.5-FP8 from USD 0.11 per 1M cached input tokens (Z.ai; 1 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, GLM 4.6 or GLM-4.5-FP8?
GLM 4.6: up to 204,800 tokens, against 131,072 for GLM-4.5-FP8, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.