GLM 5.3 Flash
z-ai/glm-5.3-flashInputOutput
Compare its 49 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3
Showing only the z-ai/fp8 provider · show all 49
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 99.53% | 99.41% | 3.78s | 19.7s | 42 tps | 1.0M | $0.150 / $0.500 |
- Z.AI100%Healthy24h 100%
- 7d
- 99.53%
- 30d
- 99.41%
- p50
- 3.78s
- p99
- 19.7s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
z-ai/fp8fp8
Measured 2m 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.
Jul
Aug
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 48 endpoints · 46 days with data, 349 endpoint-days below 90%. Tables and charts above are filtered to z-ai/fp8.
Price changes
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.080 → $0.0502026-10-11 07:20 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.080cache read $0.034 → $0.0302026-10-11 05:40 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.080cache read $0.040 → $0.0342026-10-11 04:50 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.150 → $0.080cache read $0.034 → $0.0402026-10-11 04:25 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.150cache read $0.040 → $0.0342026-10-11 02:25 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.300 → $0.1502026-10-11 02:05 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.500 → $0.3002026-10-11 01:45 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.090 → $0.120 / $0.5502026-10-11 01:20 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.075 → $0.070 / $0.5002026-10-11 01:20 UTC
- GLM 5.3 FlashWaferwafer$0.060 → $0.090 / $0.5002026-10-11 01:15 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 → $0.075 / $0.5002026-10-11 01:10 UTC
- GLM 5.3 FlashWaferwafer$0.030 → $0.060 / $0.5002026-10-11 01:00 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.120 → $0.090 / $0.5502026-10-11 01:00 UTC
- GLM 5.3 FlashWaferwafer$0.060 → $0.030 / $0.5002026-10-11 00:40 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.090 → $0.120 / $0.5502026-10-11 00:30 UTC
- GLM 5.3 FlashWaferwafer$0.030 → $0.060 / $0.5002026-10-11 00:10 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.120 → $0.090 / $0.5502026-10-11 00:00 UTC
- GLM 5.3 FlashWaferwafer$0.060 → $0.030 / $0.5002026-10-10 23:40 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.090 → $0.120 / $0.5502026-10-10 23:30 UTC
- GLM 5.3 FlashWaferwafer$0.030 → $0.060 / $0.5002026-10-10 23:10 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.120 → $0.090 / $0.5502026-10-10 20:40 UTC
- GLM 5.3 FlashWaferwafer$0.070 → $0.030 / $0.500cache read $0.030 → $0.0122026-10-10 20:25 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.500cache read $0.036 → $0.0402026-10-10 19:20 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.500cache read $0.040 → $0.0362026-10-10 15:30 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.113 → $0.111 / $0.7502026-10-10 15:25 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.115 → $0.113 / $0.7502026-10-10 13:50 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.117 → $0.115 / $0.7502026-10-10 12:10 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.070 / $0.500cache read $0.046 → $0.0402026-10-10 11:35 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.120 → $0.117 / $0.7502026-10-10 10:35 UTC
- GLM 5.3 FlashStreamLakestreamlake/fp8$0.084 → $0.069 / $0.279 → $0.230cache read $0.017 → $0.0142026-10-10 10:00 UTC