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 baseten/fp8/us provider · show all 60
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | — | — | 96.70% | 498ms | 6.52s | 93 tps | 1.0M | $0.150 / $0.500 |
- No data24h —
- 7d
- —
- 30d
- 96.70%
- p50
- 498ms
- p99
- 6.52s
- Throughput
- 93 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
baseten/fp8/usfp8
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.
Aug
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 59 endpoints · 64 days with data, 548 endpoint-days below 90%. Tables and charts above are filtered to baseten/fp8/us.
Price changes
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.053 / $0.133cache read $0.048 → $0.0442026-10-29 23:45 UTC
- GLM 5.3 FlashRelacerelace$0.051 → $0.050 / $0.0702026-10-29 23:25 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.058 → $0.053 / $0.121 → $0.133cache read $0.053 → $0.0482026-10-29 23:15 UTC
- GLM 5.3 FlashRelacerelace$0.050 → $0.051 / $0.0702026-10-29 22:55 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.053 → $0.058 / $0.110 → $0.121cache read $0.048 → $0.0532026-10-29 22:45 UTC
- GLM 5.3 FlashRelacerelace$0.046 → $0.050 / $0.0702026-10-29 22:20 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.048 → $0.053 / $0.100 → $0.110cache read $0.044 → $0.0482026-10-29 22:10 UTC
- GLM 5.3 FlashRelacerelace$0.050 → $0.046 / $0.0702026-10-29 21:55 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.053 → $0.048 / $0.091 → $0.100cache read $0.048 → $0.0442026-10-29 21:40 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.053 / $0.083 → $0.0912026-10-29 21:10 UTC
- GLM 5.3 FlashRelacerelace$0.051 → $0.050 / $0.0702026-10-29 20:55 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.058 → $0.053 / $0.075 → $0.083cache read $0.053 → $0.0482026-10-29 20:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.064 → $0.058 / $0.069 → $0.075cache read $0.058 → $0.0532026-10-29 20:05 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.058 → $0.064 / $0.063 → $0.069cache read $0.053 → $0.0582026-10-29 19:05 UTC
- GLM 5.3 FlashRelacerelace$0.050 → $0.051 / $0.071 → $0.0702026-10-29 18:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.053 → $0.058 / $0.057 → $0.063cache read $0.048 → $0.0532026-10-29 18:30 UTC
- GLM 5.3 FlashNextBitnextbit/fp4$0.120 / $0.480cache read $0.030 → $0.0402026-10-29 18:15 UTC
- GLM 5.3 FlashRelacerelace$0.051 → $0.050 / $0.0712026-10-29 18:05 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.058 → $0.053 / $0.052 → $0.0572026-10-29 17:55 UTC
- GLM 5.3 FlashRelacerelace$0.050 → $0.051 / $0.0712026-10-29 17:35 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.053 → $0.058 / $0.057 → $0.052cache read $0.044 → $0.0482026-10-29 17:25 UTC
- GLM 5.3 FlashRelacerelace$0.046 → $0.050 / $0.074 → $0.0712026-10-29 17:10 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.048 → $0.053 / $0.063 → $0.057cache read $0.040 → $0.0442026-10-29 16:55 UTC
- GLM 5.3 FlashNextBitnextbit/fp4$0.120 / $0.480cache read $0.040 → $0.0302026-10-29 13:05 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.124 → $0.138 / $0.226cache read $0.045 → $0.0502026-10-29 07:10 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.177 → $0.124 / $0.322 → $0.226cache read $0.065 → $0.0452026-10-29 06:50 UTC
- GLM 5.3 FlashGMICloudgmicloud/fp8$0.150 → $0.075 / $0.500 → $0.250cache read $0.030 → $0.0152026-10-29 06:00 UTC
- GLM 5.3 FlashGMICloudgmicloud/fp8$0.075 → $0.150 / $0.250 → $0.500cache read $0.015 → $0.0302026-10-29 05:55 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.159 → $0.177 / $0.322cache read $0.058 → $0.0652026-10-29 04:20 UTC
- GLM 5.3 FlashRelacerelace$0.046 / $0.077 → $0.0742026-10-29 03:40 UTC