GLM-4.5-FP8 vs Kimi K2 0905 API pricing
Updated
GLM-4.5-FP8: USD 0.60 input, USD 2.20 output per 1M tokens (Z.ai and 1 other). Kimi K2 0905: USD 0.60 input, USD 2.50 output per 1M tokens (Featherless and 1 other). At 3 input tokens per output token, Kimi K2 0905 costs 7.5% more than GLM-4.5-FP8 (USD 1.075 vs USD 1 per 1M).
How do GLM-4.5-FP8 and Kimi K2 0905 differ on price?
- Cheapest input price: both USD 0.60 per 1M tokens.
- Cheapest output price: GLM-4.5-FP8 USD 2.20 against USD 2.50 per 1M tokens, so Kimi K2 0905 costs 1.14× as much (14% more).
- Among the 201 indexed models, GLM-4.5-FP8 ranks 131st cheapest and Kimi K2 0905 134th on the 3:1 blend.
- No input:output mix changes the answer: GLM-4.5-FP8 is cheaper at every mix before cache discounts.
- Only GLM-4.5-FP8 lists a cached-input discount: GLM-4.5-FP8 at 1 standard price of 2, from USD 0.11 (Z.ai, 82% below that provider's input price). Kimi K2 0905's cached tokens bill at the input price.
- Kimi K2 0905 states up to 262,144 tokens of context, 2× the 131,072 of GLM-4.5-FP8.
- Both have 2 providers with a standard price; no provider sells both, so using both means two accounts.
- Shopping around matters equally: on both, the dearest standard price is 1× the cheapest.
- 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 9,320 a year in GLM-4.5-FP8's favour (GLM-4.5-FP8 USD 528.30 a month, Kimi K2 0905 USD 1,305).
GLM-4.5-FP8 and Kimi K2 0905 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-4.5-FP8 | Kimi K2 0905 |
|---|---|---|
| Model page | GLM-4.5-FP8 Z.ai · 2 providers | Kimi K2 Instruct 0905 Moonshot AI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 1 lower USD 0.60 in / USD 2.20 out at Z.ai and 1 other Z.ai page checked 2026-11-14 | USD 1.075 USD 0.60 in / USD 2.50 out at Featherless and 1 other Featherless page checked 2026-11-15 |
| Cheapest input | USD 0.60 tie Z.ai source | USD 0.60 tie Featherless source |
| Cheapest cached input | USD 0.11 Z.ai source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 2.20 lower Z.ai source | USD 2.50 Featherless source |
| Maker's own API | USD 0.60 / USD 2.20 Z.ai source | Moonshot AI publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.60 / USD 2.20 input / output, 2 prices | USD 0.60 / USD 2.50 input / output, 2 prices |
| Context window | 131,072 tokens, largest stated | 262,144 tokens, largest stated; from 32,768 at some providers |
| Providers with a standard price | 2 | 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-4.5-FP8 and Kimi K2 0905 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-4.5-FP8 | Kimi K2 0905 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 67.14 Z.ai | USD 99.00 Featherless | USD 31.86 GLM-4.5-FP8 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 141.72 Z.ai | USD 181.50 Featherless | USD 39.78 GLM-4.5-FP8 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 528.30 Z.ai | USD 1,305 Novita AI | USD 776.70 GLM-4.5-FP8 lower |
GLM-4.5-FP8 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.47× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
GLM-4.5-FP8 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 Kimi K2 0905's, so the input:output ratio never changes the answer. On input price alone they tie.
| Input : output tokens | GLM-4.5-FP8 | Kimi K2 0905 |
|---|---|---|
| 1 : 3 (long answers) | USD 1.80 lower Z.ai | USD 2.025 Featherless |
| 1 : 1 | USD 1.40 lower Z.ai | USD 1.55 Featherless |
| 3 : 1 (the site’s blend) | USD 1 lower Z.ai | USD 1.075 Featherless |
| 10 : 1 (retrieval, long prompts) | USD 0.7455 lower Z.ai | USD 0.7727 Featherless |
| 30 : 1 (agents, big contexts) | USD 0.6516 lower Z.ai | USD 0.6613 Featherless |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do GLM-4.5-FP8 and Kimi K2 0905 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-4.5-FP8 is not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- GLM-4.5-FP8 API pricing: all 2 providers and other tiers.
- Kimi K2 Instruct 0905 API pricing: all 2 providers and other tiers.
- Cost calculator with GLM-4.5-FP8 and Kimi K2 0905 preloaded
- GLM token counter
- Kimi token counter
- Prompt caching calculator
More comparisons: GLM 4.6 vs GLM-4.5-FP8 · GLM 4.5V vs GLM-4.5-FP8 · GLM 4.5 Air vs GLM-4.5-FP8 · GLM 5.3 vs Kimi K2 0905 · Kimi K2 0905 vs Kimi K2 · every GLM-4.5-FP8 comparison · every Kimi K2 0905 comparison · all 662 price comparisons
Questions
Is GLM-4.5-FP8 cheaper than Kimi K2 0905?
Yes. On a blend of 3 input tokens to 1 output token, GLM-4.5-FP8 costs USD 1 per 1M tokens and Kimi K2 0905 USD 1.075, at each model's cheapest standard price. For input alone, both start at USD 0.60 per 1M; for output alone, GLM-4.5-FP8 is (USD 2.20 against USD 2.50). This compares price only, not quality.
What do GLM-4.5-FP8 and Kimi K2 0905 cost per 1M tokens?
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. Kimi K2 0905: from USD 0.60 input and USD 2.50 output at Featherless and 1 other; median of 2 standard prices USD 0.60 / USD 2.50. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both GLM-4.5-FP8 and Kimi K2 0905?
None of the providers we track sells both at a standard price. GLM-4.5-FP8 is cheapest at Z.ai and 1 other and Kimi K2 0905 at Featherless and 1 other, so running both means two accounts.
Which is cheaper for a coding agent or a chatbot, GLM-4.5-FP8 or Kimi K2 0905?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 528.30 a month on GLM-4.5-FP8 (Z.ai) against USD 1,305 on Kimi K2 0905 (Novita AI), a difference of USD 776.70. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 67.14 a month on GLM-4.5-FP8 (Z.ai) against USD 99.00 on Kimi K2 0905 (Featherless), a difference of USD 31.86. 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-4.5-FP8 and Kimi K2 0905 change?
GLM-4.5-FP8 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 Kimi K2 0905's, so the input:output ratio never changes the answer. On input price alone they tie.
Do GLM-4.5-FP8 and Kimi K2 0905 have cached input pricing?
GLM-4.5-FP8 from USD 0.11 per 1M cached input tokens (Z.ai; 1 of 2 standard prices list a discount). Kimi K2 0905: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, GLM-4.5-FP8 or Kimi K2 0905?
Kimi K2 0905: up to 262,144 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.