GLM 5.3
z-ai/glm-5.3InputOutput
Compare its 40 providersIncident RSSCompare with GLM 5.3 Flash, GLM 5.2, GLM 5.1
CompareGLM 5.3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.97% | 98.35% | 98.35% | 898ms | 5.22s | 80 tps | 1.0M | $1.40 / $4.40 |
| Healthy | 100% | 99.75% | 97.93% | 98.53% | 1.35s | 39.1s | 63 tps | 1.0M | $1.40 / $4.40 | |
| Healthy | 100% | 97.39% | 94.09% | 95.69% | 627ms | 12.1s | 104 tps | 1.0M | $1.40 / $4.40 | |
DigitalOceandigitalocean | Healthy | 100% | 98.96% | 95.83% | 97.53% | 858ms | 4.43s | 46 tps | 1.0M | $1.08 / $3.39 |
Fireworksfireworks | Healthy | 100% | 99.60% | 99.73% | 99.56% | 1.23s | 41.5s | 47 tps | 1.0M | $1.40 / $4.40 |
Friendlifriendli | Healthy | 100% | 99.93% | 99.98% | 99.92% | 678ms | 7.61s | 111 tps | 1.0M | $1.26 / $3.96 |
| Healthy | 100% | 99.62% | 99.64% | 98.98% | 1.89s | 18.8s | 43 tps | 262K | $0.910 / $3.08 | |
| Healthy | 100% | 99.40% | 98.63% | 98.63% | 1.58s | 12.7s | 65 tps | 1.0M | $1.01 / $3.18 | |
| Healthy | 100% | 99.19% | 99.03% | 97.09% | 874ms | 56.8s | 99 tps | 1.0M | $1.40 / $4.40 | |
Phalaphala | Healthy | 100% | 99.71% | 99.03% | 98.95% | 1.22s | 14.0s | 45 tps | 1.0M | $1.05 / $3.30 |
| Healthy | 100% | 99.92% | 99.93% | 99.94% | 1.18s | 4.27s | 65 tps | 1.0M | $1.00 / $3.16 | |
| Healthy | 100% | 99.94% | 99.78% | 99.91% | 3.07s | 18.1s | 49 tps | 1.0M | $1.40 / $4.40 | |
Modalmodal | Healthy | 99.84% | 98.13% | 99.28% | 99.55% | 867ms | 33.2s | 72 tps | 1.0M | $1.40 / $4.40 |
Waferwafer | Healthy | 99.77% | 99.47% | 98.31% | 97.45% | 535ms | 15.4s | 108 tps | 1.0M | $1.40 / $4.40 |
| Healthy | 99.71% | 97.68% | 99.43% | 99.62% | 3.85s | 58.8s | 32 tps | 1.0M | $0.910 / $2.86 | |
| Healthy | 99.64% | 99.89% | 99.91% | 99.91% | 1.06s | 9.12s | 64 tps | 1.0M | $1.00 / $3.16 | |
| Degraded | 99.27% | 95.49% | 97.04% | 96.24% | 3.40s | 57.5s | 22 tps | 1.0M | $0.900 / $3.00 | |
| Healthy | 99.17% | 95.86% | 96.83% | 94.23% | 880ms | 43.4s | 84 tps | 980K | $1.05 / $4.20 | |
| Healthy | 98.98% | 98.48% | 98.52% | 98.16% | 893ms | 14.2s | 78 tps | 1.0M | $1.07 / $4.09 | |
| Healthy | 98.86% | 92.50% | 52.67% | 52.67% | 881ms | 47.4s | 60 tps | 1.0M | $0.900 / $3.00 | |
| Healthy | 97.96% | 98.93% | 99.26% | 97.14% | 2.35s | 42.4s | 19 tps | 262K | $0.877 / $2.97 | |
Togethertogether | Down | 84.11% | 94.58% | 96.78% | 96.76% | 329ms | 39.3s | 105 tps | 1.0M | $1.40 / $4.40 |
| No data | — | 99.77% | 99.36% | 97.76% | 767ms | 3.15s | 78 tps | 1.0M | $1.30 / $4.40 | |
| No data | — | 99.90% | 99.92% | 99.62% | 3.54s | 8.35s | 59 tps | 1.0M | $1.40 / $4.40 | |
| No data | — | 100% | 100% | 100% | 766ms | 1.31s | 63 tps | 1.0M | $1.40 / $4.40 | |
| No data | — | 95.89% | 99.21% | 99.59% | 1.23s | 47.0s | 58 tps | 1.0M | $2.10 / $6.60 | |
Cloudflarecloudflare | No data | — | 99.95% | 99.78% | 99.72% | 3.18s | 58.4s | 35 tps | 1.3M | $1.40 / $4.40 |
| No data | — | — | — | 99.41% | — | — | — | 1.0M | $1.40 / $4.40 | |
| Degraded | — | 98.18% | 99.30% | 97.95% | 1.24s | 14.3s | 95 tps | 1.0M | $1.19 / $3.74 | |
| No data | — | — | — | 88.65% | — | — | — | 1.0M | $1.20 / $4.00 | |
| No data | — | — | — | 95.08% | — | — | — | 1.0M | $1.20 / $4.00 | |
Fireworksfireworks/us | No data | — | — | — | — | — | — | — | 1.0M | $2.10 / $6.60 |
| No data | — | 98.53% | 99.26% | 98.74% | 3.42s | 34.7s | 37 tps | 1.0M | $1.05 / $3.30 | |
| No data | — | — | 100% | 99.72% | — | — | — | 262K | $1.13 / $4.32 | |
| No data | — | 98.84% | 99.34% | 99.34% | 4.57s | 310s | 45 tps | 1.0M | $1.40 / $4.40 | |
| No data | — | — | 100% | 95.37% | — | — | — | 1.0M | $1.00 / $3.41 | |
| No data | — | 99.60% | 99.22% | 99.29% | 1.83s | 15.2s | 48 tps | 1.0M | $1.12 / $3.52 | |
StreamLakestreamlake | No data | — | — | — | 100% | — | — | — | 1.0M | $1.11 / $3.50 |
| No data | — | — | 99.65% | 98.85% | — | — | — | 1.0M | $0.700 / $2.20 | |
Venicevenice | No data | — | 97.41% | 98.51% | 96.21% | 635ms | 4.40s | 47 tps | 1.0M | $1.40 / $4.40 |
- Alibaba100%Healthy24h 99.97%
- 7d
- 98.35%
- 30d
- 98.35%
- p50
- 898ms
- p99
- 5.22s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
alibaba - BaseTen100%Healthy24h 99.75%
- 7d
- 97.93%
- 30d
- 98.53%
- p50
- 1.35s
- p99
- 39.1s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
baseten/fp4fp4 - Crusoe100%Healthy24h 97.39%
- 7d
- 94.09%
- 30d
- 95.69%
- p50
- 627ms
- p99
- 12.1s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
crusoe/fp4fp4 - DigitalOcean100%Healthy24h 98.96%
- 7d
- 95.83%
- 30d
- 97.53%
- p50
- 858ms
- p99
- 4.43s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $1.08 / $3.39
digitalocean - Fireworks100%Healthy24h 99.60%
- 7d
- 99.73%
- 30d
- 99.56%
- p50
- 1.23s
- p99
- 41.5s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
fireworks - Friendli100%Healthy24h 99.93%
- 7d
- 99.98%
- 30d
- 99.92%
- p50
- 678ms
- p99
- 7.61s
- Throughput
- 111 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
friendli - Io Net100%Healthy24h 99.62%
- 7d
- 99.64%
- 30d
- 98.98%
- p50
- 1.89s
- p99
- 18.8s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.910 / $3.08
io-net/fp8fp8 - Morph100%Healthy24h 99.40%
- 7d
- 98.63%
- 30d
- 98.63%
- p50
- 1.58s
- p99
- 12.7s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $1.01 / $3.18
morph/fp8fp8 - Parasail100%Healthy24h 99.19%
- 7d
- 99.03%
- 30d
- 97.09%
- p50
- 874ms
- p99
- 56.8s
- Throughput
- 99 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
parasail/fp8fp8 - Phala100%Healthy24h 99.71%
- 7d
- 99.03%
- 30d
- 98.95%
- p50
- 1.22s
- p99
- 14.0s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.05 / $3.30
phala - Sail Research100%Healthy24h 99.92%
- 7d
- 99.93%
- 30d
- 99.94%
- p50
- 1.18s
- p99
- 4.27s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.16
sail-research/fp8fp8 - Z.AI100%Healthy24h 99.94%
- 7d
- 99.78%
- 30d
- 99.91%
- p50
- 3.07s
- p99
- 18.1s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
z-ai/fp8fp8 - Modal99.84%Healthy24h 98.13%
- 7d
- 99.28%
- 30d
- 99.55%
- p50
- 867ms
- p99
- 33.2s
- Throughput
- 72 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
modal - Wafer99.77%Healthy24h 99.47%
- 7d
- 98.31%
- 30d
- 97.45%
- p50
- 535ms
- p99
- 15.4s
- Throughput
- 108 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
wafer - Novita99.71%Healthy24h 97.68%
- 7d
- 99.43%
- 30d
- 99.62%
- p50
- 3.85s
- p99
- 58.8s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.910 / $2.86
novita/fp8fp8 - Sail Research99.64%Healthy24h 99.89%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 1.06s
- p99
- 9.12s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.16
sail-research/usfp8 - DeepInfra99.27%Degraded24h 95.49%
- 7d
- 97.04%
- 30d
- 96.24%
- p50
- 3.40s
- p99
- 57.5s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $3.00
deepinfra/fp4fp4 - Makora99.17%Healthy24h 95.86%
- 7d
- 96.83%
- 30d
- 94.23%
- p50
- 880ms
- p99
- 43.4s
- Throughput
- 84 tps
- Context
- 980K
- $/Mtok
- $1.05 / $4.20
makora/fp4fp4 - Inceptron98.98%Healthy24h 98.48%
- 7d
- 98.52%
- 30d
- 98.16%
- p50
- 893ms
- p99
- 14.2s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $1.07 / $4.09
inceptron/fp4fp4 - InferenceNet98.86%Healthy24h 92.50%
- 7d
- 52.67%
- 30d
- 52.67%
- p50
- 881ms
- p99
- 47.4s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $3.00
inference-net/fp4fp4 - Reka97.96%Healthy24h 98.93%
- 7d
- 99.26%
- 30d
- 97.14%
- p50
- 2.35s
- p99
- 42.4s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.877 / $2.97
reka/fp8fp8 - Together84.11%Down24h 94.58%
- 7d
- 96.78%
- 30d
- 96.76%
- p50
- 329ms
- p99
- 39.3s
- Throughput
- 105 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
together - No data24h 99.77%
- 7d
- 99.36%
- 30d
- 97.76%
- p50
- 767ms
- p99
- 3.15s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $4.40
akashml/fp8fp8 - No data24h 99.90%
- 7d
- 99.92%
- 30d
- 99.62%
- p50
- 3.54s
- p99
- 8.35s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
atlas-cloud/fp8fp8 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 766ms
- p99
- 1.31s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
baidu/fp8fp8 - No data24h 95.89%
- 7d
- 99.21%
- 30d
- 99.59%
- p50
- 1.23s
- p99
- 47.0s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
baseten/fp8fp8 - No data24h 99.95%
- 7d
- 99.78%
- 30d
- 99.72%
- p50
- 3.18s
- p99
- 58.4s
- Throughput
- 35 tps
- Context
- 1.3M
- $/Mtok
- $1.40 / $4.40
cloudflare - No data24h —
- 7d
- —
- 30d
- 99.41%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
crusoe/fp8fp8 - Degraded24h 98.18%
- 7d
- 99.30%
- 30d
- 97.95%
- p50
- 1.24s
- p99
- 14.3s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $1.19 / $3.74
decart/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 88.65%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.20 / $4.00
deepinfra/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 95.08%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.20 / $4.00
deepinfra/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
fireworks/us - No data24h 98.53%
- 7d
- 99.26%
- 30d
- 98.74%
- p50
- 3.42s
- p99
- 34.7s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $1.05 / $3.30
gmicloud/fp8fp8 - No data24h —
- 7d
- 100%
- 30d
- 99.72%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $1.13 / $4.32
io-net/fp4fp4 - No data24h 98.84%
- 7d
- 99.34%
- 30d
- 99.34%
- p50
- 4.57s
- p99
- 310s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
mistral/nvfp4nvfp4 - No data24h —
- 7d
- 100%
- 30d
- 95.37%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.41
morph/fp4fp4 - No data24h 99.60%
- 7d
- 99.22%
- 30d
- 99.29%
- p50
- 1.83s
- p99
- 15.2s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.12 / $3.52
siliconflow/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.11 / $3.50
streamlake - No data24h —
- 7d
- 99.65%
- 30d
- 98.85%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.700 / $2.20
streamlake/fp8fp8 - No data24h 97.41%
- 7d
- 98.51%
- 30d
- 96.21%
- p50
- 635ms
- p99
- 4.40s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has no chartable data in this range.
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
Jun
Jul
Aug
Sep
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 39 endpoints · 30 days with data, 127 endpoint-days below 90%.
Price changes
- GLM 5.3Sail Researchsail-research/fp8$0.966 → $1.00 / $3.04 → $3.16cache read $0.171 → $0.1792026-09-17 21:05 UTC
- GLM 5.3Sail Researchsail-research/us$0.966 → $1.00 / $3.04 → $3.16cache read $0.171 → $0.1792026-09-17 21:05 UTC
- GLM 5.3Morphmorph/fp8$0.952 → $1.01 / $2.99 → $3.18cache read $0.156 → $0.1662026-09-17 20:55 UTC
- GLM 5.3Inceptroninceptron/fp4$1.06 → $1.07 / $4.07 → $4.09cache read $0.177 → $0.1862026-09-17 20:40 UTC
- GLM 5.3Morphmorph/fp8$0.893 → $0.952 / $2.80 → $2.99cache read $0.147 → $0.1562026-09-17 20:30 UTC
- GLM 5.3Sail Researchsail-research/fp8$1.02 → $0.966 / $3.19 → $3.04cache read $0.180 → $0.1712026-09-17 20:10 UTC
- GLM 5.3Sail Researchsail-research/us$1.02 → $0.966 / $3.19 → $3.04cache read $0.180 → $0.1712026-09-17 20:10 UTC
- GLM 5.3Inceptroninceptron/fp4$1.07 → $1.06 / $4.09 → $4.07cache read $0.186 → $0.1772026-09-17 19:35 UTC
- GLM 5.3Morphmorph/fp8$0.952 → $0.893 / $2.99 → $2.80cache read $0.156 → $0.1472026-09-17 19:20 UTC
- GLM 5.3Inceptroninceptron/fp4$1.06 → $1.07 / $4.07 → $4.09cache read $0.177 → $0.1862026-09-17 19:10 UTC
- GLM 5.3Sail Researchsail-research/fp8$1.13 → $1.02 / $3.55 → $3.19cache read $0.200 → $0.1802026-09-17 19:05 UTC
- GLM 5.3Sail Researchsail-research/us$1.13 → $1.02 / $3.55 → $3.19cache read $0.200 → $0.1802026-09-17 19:05 UTC
- GLM 5.3Morphmorph/fp8$0.893 → $0.952 / $2.80 → $2.99cache read $0.147 → $0.1562026-09-17 19:00 UTC
- GLM 5.3Inceptroninceptron/fp4$1.07 → $1.06 / $4.09 → $4.07cache read $0.186 → $0.1772026-09-17 17:35 UTC
- GLM 5.3Morphmorph/fp8$0.916 → $0.893 / $2.88 → $2.80cache read $0.151 → $0.1472026-09-17 17:20 UTC
- GLM 5.3Morphmorph/fp8$0.952 → $0.916 / $2.99 → $2.88cache read $0.156 → $0.1512026-09-17 17:15 UTC
- GLM 5.3Sail Researchsail-research/fp8$1.26 → $1.13 / $3.95 → $3.55cache read $0.230 → $0.2002026-09-17 17:05 UTC
- GLM 5.3Sail Researchsail-research/us$1.26 → $1.13 / $3.95 → $3.55cache read $0.230 → $0.2002026-09-17 17:05 UTC
- GLM 5.3Morphmorph/fp8$1.01 → $0.952 / $3.18 → $2.99cache read $0.166 → $0.1562026-09-17 16:25 UTC
- GLM 5.3Phalaphala$0.910 → $1.05 / $2.86 → $3.30cache read $0.169 → $0.1952026-09-17 14:10 UTC
- GLM 5.3Io Netio-net/fp8$1.03 → $0.910 / $3.48 → $3.08cache read $0.205 → $0.1822026-09-17 12:35 UTC
- GLM 5.3Makoramakora/fp4$1.35 → $1.05 / $4.40 → $4.20cache read $0.230 → $0.1902026-09-17 12:15 UTC
- GLM 5.3Phalaphala$1.05 → $0.910 / $3.30 → $2.86cache read $0.195 → $0.1692026-09-17 08:20 UTC
- GLM 5.3Inceptroninceptron/fp4$1.06 → $1.07 / $4.07 → $4.09cache read $0.177 → $0.1862026-09-17 08:10 UTC
- GLM 5.3Morphmorph/fp8$0.893 → $1.01 / $2.80 → $3.18cache read $0.147 → $0.1662026-09-17 07:55 UTC
- GLM 5.3Phalaphala$0.910 → $1.05 / $2.86 → $3.30cache read $0.169 → $0.1952026-09-17 04:16 UTC
- GLM 5.3Inceptroninceptron/fp4$1.07 → $1.06 / $4.00 → $4.07cache read $0.166 → $0.1772026-09-17 04:01 UTC
- GLM 5.3Rekareka/fp8$0.936 → $0.877 / $3.17 → $2.97cache read $0.187 → $0.1752026-09-17 03:51 UTC
- GLM 5.3Rekareka/fp8$0.994 → $0.936 / $3.37 → $3.17cache read $0.199 → $0.1872026-09-17 03:41 UTC
- GLM 5.3Inceptroninceptron/fp4$1.08 → $1.07 / $4.10 → $4.00cache read $0.176 → $0.1662026-09-17 03:41 UTC