GLM 5.3 Flash
z-ai/glm-5.3-flashInputOutput
Compare its 66 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3
Showing only the cohere/nvfp4 provider · show all 66
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 97.96% | 99.50% | 99.50% | 1.25s | 11.3s | 52 tps | 1.0M | $0.150 / $0.500 |
- Cohere100%Healthy24h 97.96%
- 7d
- 99.50%
- 30d
- 99.50%
- p50
- 1.25s
- p99
- 11.3s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
cohere/nvfp4nvfp4
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.
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 · 77 days with data, 614 endpoint-days below 90%. 5 more not shown. Tables and charts above are filtered to cohere/nvfp4.
Price changes
- GLM 5.3 FlashInceptroninceptron/fp8$0.175 / $0.450 → $0.5002026-11-11 09:10 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.083 → $0.093 / $0.122cache read $0.036 → $0.0402026-11-11 07:40 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.074 → $0.083 / $0.122cache read $0.032 → $0.0362026-11-10 19:05 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.066 → $0.074 / $0.122cache read $0.028 → $0.0322026-11-10 18:15 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.108 / $0.350cache read $0.034 → $0.0352026-11-10 15:40 UTC
- GLM 5.3 FlashInferenceNetinference-net/us$0.108 / $0.350cache read $0.034 → $0.0352026-11-10 15:40 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.060 → $0.066 / $0.122cache read $0.026 → $0.0282026-11-10 14:55 UTC
- GLM 5.3 FlashParticle AIparticle-ai/nvfp4$0.100 → $0.120 / $0.5002026-11-10 13:55 UTC
- GLM 5.3 FlashWaferwafer/nvfp4$0.054 → $0.065 / $0.200 → $0.240cache read $0.053 → $0.0642026-11-10 12:50 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.034 → $0.040 / $0.083 → $0.0782026-11-10 11:40 UTC
- GLM 5.3 FlashWaferwafer/us$0.035 → $0.042 / $0.184cache read $0.034 → $0.0412026-11-10 11:20 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.085 → $0.060 / $0.173 → $0.122cache read $0.036 → $0.0262026-11-09 18:35 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.122 → $0.085 / $0.248 → $0.173cache read $0.052 → $0.0362026-11-09 16:05 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.175 / $0.450cache read $0.040 → $0.0302026-11-09 09:45 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.108 / $0.350cache read $0.033 → $0.0342026-11-09 06:45 UTC
- GLM 5.3 FlashInferenceNetinference-net/us$0.108 / $0.350cache read $0.033 → $0.0342026-11-09 06:45 UTC
- GLM 5.3 FlashPrimeIntellectprimeintellect$0.105 → $0.052 / $0.500 → $0.250cache read $0.021 → $0.0102026-11-09 04:00 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.060 / $0.280 → $0.3002026-11-09 02:05 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.060 / $0.240 → $0.2802026-11-09 01:15 UTC
- GLM 5.3 FlashPrimeIntellectprimeintellect$0.150 → $0.105 / $0.500cache read $0.030 → $0.0212026-11-08 09:20 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.108 / $0.350cache read $0.032 → $0.0332026-11-08 06:45 UTC
- GLM 5.3 FlashInferenceNetinference-net/us$0.108 / $0.350cache read $0.032 → $0.0332026-11-08 06:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.040 → $0.060 / $0.2402026-11-07 23:50 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.040 / $0.240cache read $0.022 → $0.0302026-11-07 23:45 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.032 → $0.034 / $0.0832026-11-07 21:10 UTC
- GLM 5.3 FlashWaferwafer/us$0.033 → $0.035 / $0.184cache read $0.032 → $0.0342026-11-07 20:55 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.034 → $0.032 / $0.0832026-11-07 20:10 UTC
- GLM 5.3 FlashWaferwafer/us$0.035 → $0.033 / $0.184cache read $0.034 → $0.0322026-11-07 19:55 UTC
- GLM 5.3 FlashRelacerelace/fp4$0.029 → $0.034 / $0.092 → $0.083cache read $0.029 → $0.0302026-11-07 19:35 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.030 → $0.040 / $0.2402026-11-07 19:25 UTC