GLM 5.3 Flash
z-ai/glm-5.3-flashInputOutput
Compare its 62 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3
Showing only the fireworks provider · show all 62
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Fireworksfireworks | Healthy | 100% | 99.93% | 99.75% | 97.73% | 1.20s | 15.6s | 118 tps | 1.0M | $0.150 / $0.500 |
- Fireworks100%Healthy24h 99.93%
- 7d
- 99.75%
- 30d
- 97.73%
- p50
- 1.20s
- p99
- 15.6s
- Throughput
- 118 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
fireworks
Measured 5m 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.
Aug
Sep
Oct
Nov
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 60 endpoints · 69 days with data, 563 endpoint-days below 90%. 1 more not shown. Tables and charts above are filtered to fireworks.
Price changes
- GLM 5.3 FlashSail Researchsail-research/us$0.350 → $0.175 / $1.25 → $0.625cache read $0.045 → $0.0222026-11-03 01:05 UTC
- GLM 5.3 FlashSail Researchsail-research/fp4$0.350 → $0.175 / $1.25 → $0.625cache read $0.045 → $0.0222026-11-03 01:05 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.030 / $0.160 → $0.2202026-11-02 22:55 UTC
- GLM 5.3 FlashSail Researchsail-research/us$0.225 → $0.350 / $0.750 → $1.252026-11-02 19:05 UTC
- GLM 5.3 FlashNextBitnextbit/fp4$0.110 → $0.120 / $0.450cache read $0.030 → $0.0452026-11-02 17:15 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.190 → $0.160 / $0.6002026-11-02 12:30 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.190 / $0.600cache read $0.060 → $0.0402026-11-02 09:50 UTC
- GLM 5.3 FlashMakoramakora$0.140 / $0.470 → $0.240cache read $0.024 → $0.0402026-11-02 06:15 UTC
- GLM 5.3 FlashNextBitnextbit/fp4$0.150 → $0.110 / $0.500 → $0.4502026-11-01 11:35 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.016 → $0.029 / $0.182 → $0.092cache read $0.016 → $0.0292026-11-01 07:30 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.017 → $0.030 / $0.035 → $0.160cache read $0.016 → $0.0202026-11-01 07:15 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.009 → $0.016 / $0.182cache read $0.009 → $0.0162026-11-01 06:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.009 → $0.017 / $0.170 → $0.035cache read $0.009 → $0.0162026-11-01 06:35 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.009 → $0.009 / $0.170 → $0.182cache read $0.009 → $0.0092026-11-01 06:30 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.010 → $0.009 / $0.170cache read $0.010 → $0.0092026-11-01 06:20 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.010 → $0.009 / $0.170cache read $0.010 → $0.0092026-11-01 06:15 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.010 → $0.010 / $0.170cache read $0.010 → $0.0102026-11-01 06:05 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.010 → $0.010 / $0.170cache read $0.010 → $0.0102026-11-01 06:00 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.011 → $0.010 / $0.170cache read $0.011 → $0.0102026-11-01 05:50 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.011 → $0.010 / $0.170cache read $0.011 → $0.0102026-11-01 05:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.011 → $0.011 / $0.170cache read $0.011 → $0.0112026-11-01 05:35 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.011 → $0.011 / $0.170cache read $0.011 → $0.0112026-11-01 05:30 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.011 / $0.158 → $0.1702026-11-01 05:30 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.011 / $0.158 → $0.1702026-11-01 05:25 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.012 → $0.011 / $0.158cache read $0.012 → $0.0112026-11-01 05:20 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.012 → $0.011 / $0.158cache read $0.012 → $0.0112026-11-01 05:15 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.013 → $0.012 / $0.158cache read $0.013 → $0.0122026-11-01 05:05 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.013 → $0.012 / $0.158cache read $0.013 → $0.0122026-11-01 05:00 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.013 → $0.013 / $0.158cache read $0.013 → $0.0132026-11-01 04:50 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.013 → $0.013 / $0.158cache read $0.013 → $0.0132026-11-01 04:45 UTC