Z.ai: GLM 5.3
Prime Intellect and llm.buzz tie for the cheapest, and Prime Intellect is the fastest provider of this model. llm.buzz costs the same as a provider on the line, for less speed. Alibaba, Scaleway and Novita cost more for less speed than a provider on the line.
- Live providers
- 5
- Same model, one API
- Cheapest
- $1.50 blended
- llm.buzz
- Fastest output
- 278 tok/s
- Prime Intellect
- Quickest first token
- 0.28 s
- Scaleway
- Best uptime
- 100%
- Prime Intellect
- llm.buzz and Prime Intellect tie for the cheapest Z.ai: GLM 5.3, at $1.50 per million tokens blended.
- Prime Intellect serves Z.ai: GLM 5.3 fastest, at 278 tok/s (median over 24 hours).
- Scaleway starts answering Z.ai: GLM 5.3 quickest, first token in 0.28 s (median over 24 hours).
- Prime Intellect has the best uptime for Z.ai: GLM 5.3, 100% over 72 hours.
Prime Intellect278 tok/s
Scaleway193 tok/s
llm.buzz161 tok/s
Novita93 tok/s
Alibaba65 tok/s
Scaleway0.28 s
Prime Intellect0.58 s
Alibaba1.72 s
Novita1.72 s
llm.buzz2.48 s
llm.buzz$1.50
Prime Intellect$1.50
Alibaba$1.83
Novita$2.15
Scaleway$3.14
5 providers
 llm.buzz | $1.50 | $0.98 | $3.08 | 161 tok/stest | 2.48 stest | 95.8%test |
|---|---|---|---|---|---|---|
 Prime Intellect | $1.50 | $0.98 | $3.08 | 278 tok/stest | 0.58 stest | 100%test |
 Alibaba | $1.83 | $1.19 | $3.74 | 65 tok/stest | 1.72 stest | 100%test |
 ScalewayEU | $3.14 | $2.07 | $6.34 | 193 tok/stest | 0.28 stest | 100%test |
 Novita | $2.15 | $1.40 | $4.40 | 93 tok/stest | 1.72 stest | 100%test |
0150300450$1.00$2.00$3.00$4.00llm.buzz$1.50 blended, 161 tok/sPrime Intellect$1.50 blended, 278 tok/sAlibaba$1.83 blended, 65 tok/sScaleway$3.14 blended, 193 tok/sNovita$2.15 blended, 93 tok/s
Blended price, $ per million tokens (3 input to 1 output)llm.buzz$1.50 blended, 161 tok/sPrime Intellect$1.50 blended, 278 tok/sAlibaba$1.83 blended, 65 tok/sScaleway$3.14 blended, 193 tok/sNovita$2.15 blended, 93 tok/sCustomer traffic on this model is still below the publishing floor, so its figures are from llm.buzz's test requests, tagged "test".
The last 24 hours, by hour
Last 24 hours, from llm.buzz's test requests
- llm.buzz161 tok/s
- Prime Intellect278 tok/s
- Alibaba65 tok/s
- Scaleway193 tok/s
- Novita93 tok/s
Data table
| Provider | From (UTC) | p50 | p90 | p99 |
|---|---|---|---|---|
| llm.buzz | Oct 26, 06:00 | 161 tok/s | 161 tok/s | 161 tok/s |
| llm.buzz | Last 24 hours | 161 tok/s | 161 tok/s | 161 tok/s |
| Prime Intellect | Oct 26, 09:00 | 334 tok/s | 334 tok/s | 334 tok/s |
| Prime Intellect | Oct 26, 14:00 | 278 tok/s | 278 tok/s | 278 tok/s |
| Prime Intellect | Oct 26, 18:00 | 278 tok/s | 278 tok/s | 278 tok/s |
| Prime Intellect | Oct 26, 23:00 | 161 tok/s | 161 tok/s | 161 tok/s |
| Prime Intellect | Oct 27, 03:00 | 278 tok/s | 278 tok/s | 278 tok/s |
| Prime Intellect | Last 24 hours | 278 tok/s | 161 tok/s | 161 tok/s |
| Alibaba | Oct 26, 07:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| Alibaba | Oct 26, 12:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| Alibaba | Oct 26, 16:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| Alibaba | Oct 26, 20:00 | 78 tok/s | 78 tok/s | 78 tok/s |
| Alibaba | Oct 27, 01:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| Alibaba | Last 24 hours | 65 tok/s | 54 tok/s | 54 tok/s |
| Scaleway | Oct 26, 08:00 | 161 tok/s | 161 tok/s | 161 tok/s |
| Scaleway | Oct 26, 12:00 | 193 tok/s | 193 tok/s | 193 tok/s |
| Scaleway | Oct 26, 17:00 | 193 tok/s | 193 tok/s | 193 tok/s |
| Scaleway | Oct 26, 21:00 | 134 tok/s | 134 tok/s | 134 tok/s |
| Scaleway | Oct 27, 02:00 | 334 tok/s | 334 tok/s | 334 tok/s |
| Scaleway | Last 24 hours | 193 tok/s | 134 tok/s | 134 tok/s |
| Novita | Oct 26, 06:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| Novita | Oct 26, 10:00 | 112 tok/s | 112 tok/s | 112 tok/s |
| Novita | Oct 26, 14:00 | 112 tok/s | 112 tok/s | 112 tok/s |
| Novita | Oct 26, 19:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| Novita | Oct 26, 23:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| Novita | Oct 27, 04:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| Novita | Last 24 hours | 93 tok/s | 93 tok/s | 93 tok/s |
- llm.buzz2.48 s
- Prime Intellect0.58 s
- Alibaba1.72 s
- Scaleway0.28 s
- Novita1.72 s
Data table
| Provider | From (UTC) | p50 | p90 | p99 |
|---|---|---|---|---|
| llm.buzz | Oct 26, 06:00 | 2.48 s | 2.48 s | 2.48 s |
| llm.buzz | Last 24 hours | 2.48 s | 2.48 s | 2.48 s |
| Prime Intellect | Oct 26, 09:00 | 0.58 s | 0.58 s | 0.58 s |
| Prime Intellect | Oct 26, 14:00 | 0.58 s | 0.58 s | 0.58 s |
| Prime Intellect | Oct 26, 18:00 | 1.44 s | 1.44 s | 1.44 s |
| Prime Intellect | Oct 26, 23:00 | 0.58 s | 0.58 s | 0.58 s |
| Prime Intellect | Oct 27, 03:00 | 0.69 s | 0.69 s | 0.69 s |
| Prime Intellect | Last 24 hours | 0.58 s | 1.44 s | 1.44 s |
| Alibaba | Oct 26, 07:00 | 1.44 s | 1.44 s | 1.44 s |
| Alibaba | Oct 26, 12:00 | 1.72 s | 1.72 s | 1.72 s |
| Alibaba | Oct 26, 16:00 | 2.07 s | 2.07 s | 2.07 s |
| Alibaba | Oct 26, 20:00 | 1.72 s | 1.72 s | 1.72 s |
| Alibaba | Oct 27, 01:00 | 10.7 s | 10.7 s | 10.7 s |
| Alibaba | Last 24 hours | 1.72 s | 10.7 s | 10.7 s |
| Scaleway | Oct 26, 08:00 | 0.28 s | 0.28 s | 0.28 s |
| Scaleway | Oct 26, 12:00 | 0.40 s | 0.40 s | 0.40 s |
| Scaleway | Oct 26, 17:00 | 0.33 s | 0.33 s | 0.33 s |
| Scaleway | Oct 26, 21:00 | 0.28 s | 0.28 s | 0.28 s |
| Scaleway | Oct 27, 02:00 | 0.23 s | 0.23 s | 0.23 s |
| Scaleway | Last 24 hours | 0.28 s | 0.40 s | 0.40 s |
| Novita | Oct 26, 06:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Oct 26, 10:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Oct 26, 14:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Oct 26, 19:00 | 1.00 s | 1.00 s | 1.00 s |
| Novita | Oct 26, 23:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Oct 27, 04:00 | 1.72 s | 1.72 s | 1.72 s |
| Novita | Last 24 hours | 1.72 s | 1.72 s | 1.72 s |
Uptime
Last 72 hours, by hourThis model
llm.buzz
Prime Intellect
Alibaba
Scaleway
Novita
- Up: 95% or more served
- Degraded: 85% to 95%
- Down: below 85%
- No data
- From llm.buzz's test requests
How we measure
- Speed and first tokenOutput speed and time to first token are medians over the last 24 hours, per provider, from text requests.
- UptimeThe share of attempts the provider served over the 72 hours before the figures' end, provider failures counted against it.
- Two sourcesCustomer traffic once enough organizations count toward a figure; below that, llm.buzz's test requests, short streamed requests sent to every live provider. The tables tag those "test".
- PriceEach provider's price per million tokens, with a running discount applied. The blended price weighs input and output 3 to 1, a chat request's usual mix.
Let the router pickName the model; llm.buzz sends each request to a provider and moves to the next when one fails.