GLM 5.3 Flash: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.17% | 98.21% | 98.21% | 818ms | 6.85s◆ (best) | 138 tps◆ (best) | 1.0M | $0.150 / $0.500 | |
| Healthy | 100%◆ (best) | 99.91% | 100%◆ (best) | 100%◆ (best) | 2.01s | 25.8s | 10 tps | 262K | $0.150 / $0.500 | |
| Healthy | 100%◆ (best) | 99.16% | 98.75% | 98.75% | 504ms◆ (best) | 52.4s | 43 tps | 1.0M | $0.150 / $0.500 | |
Venicevenice | Down | 100%◆ (best) | 48.42% | 70.45% | 70.45% | 1.78s | 72.5s | 16 tps | 1.0M | $0.094 / $0.313 |
| Healthy | 99.53% | 99.48% | 99.41% | 99.41% | 1.63s | 74.4s | 36 tps | 1.0M | $0.075 / $0.250◆ (best) | |
| Healthy | 99.24% | 99.02% | 96.34% | 96.34% | 1.31s | 127s | 24 tps | 1.0M | $0.150 / $0.500 | |
Cloudflarecloudflare | Healthy | 99.22% | 98.19% | 69.61% | 69.61% | 2.75s | 19.8s | 57 tps | 1.3M | $0.150 / $0.500 |
| Healthy | 99.19% | 99.39% | 99.29% | 99.29% | 5.52s | 64.2s | 29 tps | 1.0M | $0.075 / $0.250◆ (best) | |
| Healthy | 98.51% | 98.20% | 98.66% | 98.66% | 3.07s | 27.7s | 38 tps | 1.0M | $0.075 / $0.250◆ (best) | |
| No data | — | — | 93.11% | 93.11% | — | — | — | 1.0M | $0.150 / $0.500 |
- BaseTen100%◆ (best)Healthy24h 99.17%
- 7d
- 98.21%
- 30d
- 98.21%
- p50
- 818ms
- p99
- 6.85s◆ (best)
- Throughput
- 138 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
baseten/fp8fp8 - Io Net100%◆ (best)Healthy24h 99.91%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.01s
- p99
- 25.8s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.500
io-net/fp8fp8 - Parasail100%◆ (best)Healthy24h 99.16%
- 7d
- 98.75%
- 30d
- 98.75%
- p50
- 504ms◆ (best)
- p99
- 52.4s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
parasail/fp8fp8 - Venice100%◆ (best)Down24h 48.42%
- 7d
- 70.45%
- 30d
- 70.45%
- p50
- 1.78s
- p99
- 72.5s
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $0.094 / $0.313
venice - Novita99.53%Healthy24h 99.48%
- 7d
- 99.41%
- 30d
- 99.41%
- p50
- 1.63s
- p99
- 74.4s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.075 / $0.250◆ (best)
novita/fp8fp8 - DeepInfra99.24%Healthy24h 99.02%
- 7d
- 96.34%
- 30d
- 96.34%
- p50
- 1.31s
- p99
- 127s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
deepinfra/fp8fp8 - Cloudflare99.22%Healthy24h 98.19%
- 7d
- 69.61%
- 30d
- 69.61%
- p50
- 2.75s
- p99
- 19.8s
- Throughput
- 57 tps
- Context
- 1.3M
- $/Mtok
- $0.150 / $0.500
cloudflare - Z.AI99.19%Healthy24h 99.39%
- 7d
- 99.29%
- 30d
- 99.29%
- p50
- 5.52s
- p99
- 64.2s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.075 / $0.250◆ (best)
z-ai/fp8fp8 - GMICloud98.51%Healthy24h 98.20%
- 7d
- 98.66%
- 30d
- 98.66%
- p50
- 3.07s
- p99
- 27.7s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.075 / $0.250◆ (best)
gmicloud/fp8fp8 - No data24h —
- 7d
- 93.11%
- 30d
- 93.11%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
modal/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.