Qwen: Qwen3.8 27B
DeepInfra is the cheapest and Scaleway the fastest. Prime Intellect and Novita cost more for less speed than a provider on the line.
- Live providers
- 4
- Same model, one API
- Cheapest
- $0.775 blended
- DeepInfra
- Fastest output
- 161 tok/s
- Scaleway
- Quickest first token
- 0.23 s
- Scaleway
- Best uptime
- 100%
- Scaleway
- DeepInfra serves Qwen: Qwen3.8 27B cheapest, at $0.775 per million tokens blended.
- Scaleway serves Qwen: Qwen3.8 27B fastest, at 161 tok/s (median over 24 hours).
- Scaleway starts answering Qwen: Qwen3.8 27B quickest, first token in 0.23 s (median over 24 hours).
- Scaleway has the best uptime for Qwen: Qwen3.8 27B, 100% over 72 hours.
Scaleway161 tok/s
Prime Intellect112 tok/s
DeepInfra54 tok/s
Novita54 tok/s
Scaleway0.23 s
DeepInfra0.69 s
Prime Intellect0.83 s
Novita2.07 s
DeepInfra$0.775
Novita$1.06
Scaleway$1.47
Prime Intellect$1.54
4 providers
 DeepInfra | $0.775 | $0.20 | $2.50 | 54 tok/stest | 0.69 stest | 93%test |
|---|---|---|---|---|---|---|
 ScalewayEU | $1.47 | $0.6915 | $3.80 | 161 tok/stest | 0.23 stest | 100%test |
 Prime Intellect | $1.54 | $0.99 | $3.20 | 112 tok/stest | 0.83 stest | 97.2%test |
 Novita | $1.06 | $0.42 | $3.00 | 54 tok/stest | 2.07 stest | 90.3%test |
060120180$0.50$1.00$1.50$2.00DeepInfra$0.775 blended, 54 tok/sScaleway$1.47 blended, 161 tok/sPrime Intellect$1.54 blended, 112 tok/sNovita$1.06 blended, 54 tok/s
Blended price, $ per million tokens (3 input to 1 output)DeepInfra$0.775 blended, 54 tok/sScaleway$1.47 blended, 161 tok/sPrime Intellect$1.54 blended, 112 tok/sNovita$1.06 blended, 54 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
- DeepInfra54 tok/s
- Scaleway161 tok/s
- Prime Intellect112 tok/s
- Novita54 tok/s
Data table
| Provider | From (UTC) | p50 | p90 | p99 |
|---|---|---|---|---|
| DeepInfra | Oct 26, 06:00 | 31 tok/s | 31 tok/s | 31 tok/s |
| DeepInfra | Oct 26, 11:00 | 37 tok/s | 37 tok/s | 37 tok/s |
| DeepInfra | Oct 26, 15:00 | 22 tok/s | 22 tok/s | 22 tok/s |
| DeepInfra | Oct 26, 19:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| DeepInfra | Oct 26, 23:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| DeepInfra | Oct 27, 04:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| DeepInfra | Last 24 hours | 54 tok/s | 22 tok/s | 22 tok/s |
| Scaleway | Oct 26, 07:00 | 134 tok/s | 134 tok/s | 134 tok/s |
| Scaleway | Oct 26, 12:00 | 161 tok/s | 161 tok/s | 161 tok/s |
| Scaleway | Oct 26, 17:00 | 134 tok/s | 134 tok/s | 134 tok/s |
| Scaleway | Oct 26, 21:00 | 161 tok/s | 161 tok/s | 161 tok/s |
| Scaleway | Oct 27, 02:00 | 161 tok/s | 161 tok/s | 161 tok/s |
| Scaleway | Last 24 hours | 161 tok/s | 134 tok/s | 134 tok/s |
| Prime Intellect | Oct 26, 07:00 | 45 tok/s | 45 tok/s | 45 tok/s |
| Prime Intellect | Oct 26, 11:00 | 93 tok/s | 93 tok/s | 93 tok/s |
| Prime Intellect | Oct 26, 16:00 | 112 tok/s | 112 tok/s | 112 tok/s |
| Prime Intellect | Oct 27, 01:00 | 193 tok/s | 193 tok/s | 193 tok/s |
| Prime Intellect | Last 24 hours | 112 tok/s | 45 tok/s | 45 tok/s |
| Novita | Oct 26, 05:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| Novita | Oct 26, 10:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| Novita | Oct 26, 15:00 | 54 tok/s | 54 tok/s | 54 tok/s |
| Novita | Oct 26, 19:00 | 45 tok/s | 45 tok/s | 45 tok/s |
| Novita | Oct 26, 23:00 | 31 tok/s | 31 tok/s | 31 tok/s |
| Novita | Oct 27, 04:00 | 65 tok/s | 65 tok/s | 65 tok/s |
| Novita | Last 24 hours | 54 tok/s | 31 tok/s | 31 tok/s |
- DeepInfra0.69 s
- Scaleway0.23 s
- Prime Intellect0.83 s
- Novita2.07 s
Data table
| Provider | From (UTC) | p50 | p90 | p99 |
|---|---|---|---|---|
| DeepInfra | Oct 26, 06:00 | 1.00 s | 1.00 s | 1.00 s |
| DeepInfra | Oct 26, 11:00 | 0.69 s | 0.69 s | 0.69 s |
| DeepInfra | Oct 26, 15:00 | 0.83 s | 0.83 s | 0.83 s |
| DeepInfra | Oct 26, 19:00 | 0.83 s | 0.83 s | 0.83 s |
| DeepInfra | Oct 26, 23:00 | 0.69 s | 0.69 s | 0.69 s |
| DeepInfra | Oct 27, 04:00 | 0.69 s | 0.69 s | 0.69 s |
| DeepInfra | Last 24 hours | 0.69 s | 1.00 s | 1.00 s |
| Scaleway | Oct 26, 07:00 | 0.23 s | 0.23 s | 0.23 s |
| Scaleway | Oct 26, 12:00 | 0.33 s | 0.33 s | 0.33 s |
| Scaleway | Oct 26, 17:00 | 0.23 s | 0.23 s | 0.23 s |
| Scaleway | Oct 26, 21:00 | 0.23 s | 0.23 s | 0.23 s |
| Scaleway | Oct 27, 02:00 | 0.33 s | 0.33 s | 0.33 s |
| Scaleway | Last 24 hours | 0.23 s | 0.33 s | 0.33 s |
| Prime Intellect | Oct 26, 07:00 | 0.58 s | 0.58 s | 0.58 s |
| Prime Intellect | Oct 26, 11:00 | 1.00 s | 1.00 s | 1.00 s |
| Prime Intellect | Oct 26, 16:00 | 0.83 s | 0.83 s | 0.83 s |
| Prime Intellect | Oct 27, 01:00 | 1.44 s | 1.44 s | 1.44 s |
| Prime Intellect | Last 24 hours | 0.83 s | 1.44 s | 1.44 s |
| Novita | Oct 26, 05:00 | 4.29 s | 4.29 s | 4.29 s |
| Novita | Oct 26, 10:00 | 2.48 s | 2.48 s | 2.48 s |
| Novita | Oct 26, 15:00 | 1.44 s | 1.44 s | 1.44 s |
| Novita | Oct 26, 19:00 | 2.48 s | 2.48 s | 2.48 s |
| Novita | Oct 26, 23:00 | 2.07 s | 2.07 s | 2.07 s |
| Novita | Oct 27, 04:00 | 1.20 s | 1.20 s | 1.20 s |
| Novita | Last 24 hours | 2.07 s | 4.29 s | 4.29 s |
Uptime
Last 72 hours, by hourThis model
DeepInfra
Scaleway
Prime Intellect
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.