GLM 5.3 Flash
z-ai/glm-5.3-flashInputOutput
Compare its 60 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3
Showing only the darkbloom/fp4 provider · show all 60
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 100% | 94.47% | 94.25% | 94.25% | 3.34s | 18.4s | 29 tps | 262K | $0.065 / $0.180 |
- Darkbloom100%Degraded24h 94.47%
- 7d
- 94.25%
- 30d
- 94.25%
- p50
- 3.34s
- p99
- 18.4s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.065 / $0.180
darkbloom/fp4fp4
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
Jul
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 59 endpoints · 63 days with data, 543 endpoint-days below 90%. Tables and charts above are filtered to darkbloom/fp4.
Price changes
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.030 → $0.033 / $0.029 → $0.032cache read $0.027 → $0.0302026-10-28 22:20 UTC
- GLM 5.3 FlashRelacerelace$0.026 → $0.029 / $0.104 → $0.092cache read $0.026 → $0.0292026-10-28 21:55 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.027 → $0.030 / $0.027 → $0.029cache read $0.025 → $0.0272026-10-28 21:45 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.128 → $0.143 / $0.322cache read $0.047 → $0.0522026-10-28 20:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.027 / $0.024 → $0.027cache read $0.023 → $0.0252026-10-28 20:40 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.115 → $0.128 / $0.322cache read $0.042 → $0.0472026-10-28 18:40 UTC
- GLM 5.3 FlashDigitalOceandigitalocean$0.131 → $0.112 / $0.438 → $0.3752026-10-28 18:05 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.027 / $0.024cache read $0.025 → $0.0232026-10-28 17:45 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.103 → $0.115 / $0.322cache read $0.038 → $0.0422026-10-28 17:30 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.092 → $0.103 / $0.322cache read $0.034 → $0.0382026-10-28 16:25 UTC
- GLM 5.3 FlashRelacerelace$0.024 → $0.026 / $0.114 → $0.104cache read $0.024 → $0.0262026-10-28 16:20 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.025 → $0.027 / $0.027 → $0.024cache read $0.023 → $0.0252026-10-28 16:10 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.025 / $0.029 → $0.027cache read $0.021 → $0.0232026-10-28 15:30 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.025 / $0.029cache read $0.023 → $0.0212026-10-28 15:01 UTC
- GLM 5.3 FlashRekareka$0.120 / $0.500 → $0.3002026-10-28 14:50 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.082 → $0.092 / $0.322cache read $0.030 → $0.0342026-10-28 14:35 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.025 / $0.032 → $0.0292026-10-28 14:20 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.025 / $0.035 → $0.0322026-10-28 14:00 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.025 / $0.039 → $0.0352026-10-28 13:10 UTC
- GLM 5.3 FlashRelacerelace$0.024 / $0.132 → $0.1142026-10-28 13:05 UTC
- GLM 5.3 FlashRelacerelace$0.022 → $0.024 / $0.132cache read $0.022 → $0.0242026-10-28 12:40 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.073 → $0.082 / $0.322cache read $0.027 → $0.0302026-10-28 12:30 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.023 → $0.025 / $0.043 → $0.039cache read $0.021 → $0.0232026-10-28 12:30 UTC
- GLM 5.3 FlashNextBitnextbit/fp4$0.125 → $0.120 / $0.500 → $0.480cache read $0.050 → $0.0402026-10-28 12:25 UTC
- GLM 5.3 FlashRelacerelace$0.020 → $0.022 / $0.132cache read $0.020 → $0.0222026-10-28 12:05 UTC
- GLM 5.3 FlashRelacerelace$0.020 / $0.124 → $0.1322026-10-28 12:00 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.021 → $0.023 / $0.047 → $0.043cache read $0.019 → $0.0212026-10-28 11:50 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.021 / $0.052 → $0.0472026-10-28 11:30 UTC
- GLM 5.3 FlashRelacerelace$0.022 → $0.020 / $0.124cache read $0.022 → $0.0202026-10-28 11:05 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.023 → $0.021 / $0.057 → $0.052cache read $0.021 → $0.0192026-10-28 11:00 UTC