GLM 5.3 Flash
z-ai/glm-5.3-flashInputOutput
Compare its 45 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3
Showing only the parasail/fp4 provider · show all 45
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.82% | 99.61% | 99.49% | 99.49% | 913ms | 14.7s | 142 tps | 1.0M | $0.150 / $0.500 |
- Parasail99.82%Healthy24h 99.61%
- 7d
- 99.49%
- 30d
- 99.49%
- p50
- 913ms
- p99
- 14.7s
- Throughput
- 142 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
parasail/fp4fp4
Measured 1m 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
Aug
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 45 endpoints · 39 days with data, 296 endpoint-days below 90%. Tables and charts above are filtered to parasail/fp4.
Price changes
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.044 / $0.600cache read $0.035 → $0.0402026-10-04 22:31 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.044 / $0.600cache read $0.040 → $0.0352026-10-04 21:31 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.046 / $0.650cache read $0.046 → $0.0302026-10-04 18:56 UTC
- GLM 5.3 FlashRelacerelace$0.035 / $0.500cache read $0.035 → $0.0232026-10-04 18:46 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.160 → $0.135 / $0.444 → $0.3572026-10-04 16:11 UTC
- GLM 5.3 FlashInceptroninceptron/fp8$0.225 → $0.160 / $0.450cache read $0.080 → $0.0702026-10-04 12:50 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.044 / $0.600cache read $0.043 → $0.0402026-10-04 12:16 UTC
- GLM 5.3 FlashDecartdecart/fp4$0.128 → $0.112 / $0.425 → $0.375cache read $0.025 → $0.0222026-10-04 08:36 UTC
- GLM 5.3 FlashDekaLLMdekallm$0.100 / $0.400 → $1.002026-10-04 07:51 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.044 / $0.600cache read $0.040 → $0.0432026-10-04 06:51 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.046 / $0.650cache read $0.041 → $0.0462026-10-04 05:25 UTC
- GLM 5.3 FlashRelacerelace$0.035 / $0.500cache read $0.032 → $0.0352026-10-04 05:21 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.045 → $0.046 / $0.650cache read $0.040 → $0.0412026-10-04 04:31 UTC
- GLM 5.3 FlashRelacerelace$0.034 → $0.035 / $0.500cache read $0.031 → $0.0322026-10-04 04:26 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.043 → $0.045 / $0.650cache read $0.039 → $0.0402026-10-04 04:16 UTC
- GLM 5.3 FlashRelacerelace$0.033 → $0.034 / $0.500cache read $0.030 → $0.0312026-10-04 04:10 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.042 → $0.043 / $0.650cache read $0.038 → $0.0392026-10-04 04:01 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.042 → $0.044 / $0.600cache read $0.038 → $0.0402026-10-04 04:01 UTC
- GLM 5.3 FlashRelacerelace$0.033 → $0.033 / $0.500cache read $0.029 → $0.0302026-10-04 03:51 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.042 → $0.042 / $0.650cache read $0.037 → $0.0382026-10-04 03:46 UTC
- GLM 5.3 FlashRelacerelace$0.032 → $0.033 / $0.500cache read $0.029 → $0.0292026-10-04 03:41 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.041 → $0.042 / $0.650cache read $0.037 → $0.0372026-10-04 03:41 UTC
- GLM 5.3 FlashRelacerelace$0.031 → $0.032 / $0.500cache read $0.028 → $0.0292026-10-04 03:35 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.040 → $0.042 / $0.600cache read $0.036 → $0.0382026-10-04 03:31 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.039 → $0.041 / $0.650cache read $0.035 → $0.0372026-10-04 03:25 UTC
- GLM 5.3 FlashRelacerelace$0.030 → $0.031 / $0.500cache read $0.027 → $0.0282026-10-04 03:20 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.038 → $0.039 / $0.650cache read $0.034 → $0.0352026-10-04 03:10 UTC
- GLM 5.3 FlashRelacerelace$0.029 → $0.030 / $0.500cache read $0.026 → $0.0272026-10-04 03:00 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.037 → $0.038 / $0.650cache read $0.033 → $0.0342026-10-04 02:46 UTC
- GLM 5.3 FlashRelacerelace$0.028 → $0.029 / $0.500cache read $0.025 → $0.0262026-10-04 02:41 UTC