GLM 5.3
z-ai/glm-5.3InputOutput
Compare its 55 providersIncident RSSCompare with GLM 5.3 Flash, GLM 5.3 FlashX, GLM 5.3 Prime
Showing only the fireworks/fast provider · show all 55
CompareGLM 5.3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Fireworksfireworks/fast | Healthy | 99.52% | 99.72% | 99.62% | 99.62% | 1.06s | 5.52s | 122 tps | 1.0M | $2.10 / $6.60 |
- Fireworks99.52%Healthy24h 99.72%
- 7d
- 99.62%
- 30d
- 99.62%
- p50
- 1.06s
- p99
- 5.52s
- Throughput
- 122 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
fireworks/fast
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.
Jul
Aug
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 53 endpoints · 49 days with data, 194 endpoint-days below 90%. Tables and charts above are filtered to fireworks/fast.
Price changes
- GLM 5.3InferenceNetinference-net$0.200 → $0.140 / $4.40cache read $0.100 → $0.0702026-10-06 06:41 UTC
- GLM 5.3InferenceNetinference-net$0.200 / $4.40cache read $0.065 → $0.1002026-10-06 05:30 UTC
- GLM 5.3InferenceNetinference-net$0.120 → $0.200 / $4.40cache read $0.040 → $0.0652026-10-06 04:50 UTC
- GLM 5.3Waferwafer$0.100 / $4.30 → $7.002026-10-06 03:46 UTC
- GLM 5.3Waferwafer$0.100 / $7.00 → $4.302026-10-06 03:40 UTC
- GLM 5.3Morphmorph/fp8$0.238 → $0.179 / $3.552026-10-06 03:40 UTC
- GLM 5.3Morphmorph/fp8$0.298 → $0.238 / $2.88 → $3.55cache read $0.156 → $0.1372026-10-06 03:11 UTC
- GLM 5.3Morphmorph/fp8$0.214 → $0.298 / $2.88cache read $0.166 → $0.1562026-10-06 03:05 UTC
- GLM 5.3Morphmorph/fp8$0.071 → $0.214 / $2.882026-10-06 02:51 UTC
- GLM 5.3Morphmorph/fp8$0.167 → $0.071 / $3.18 → $2.882026-10-06 02:41 UTC
- GLM 5.3Morphmorph/fp8$0.131 → $0.167 / $3.18cache read $0.147 → $0.1662026-10-06 02:06 UTC
- GLM 5.3InferenceNetinference-net$0.140 → $0.120 / $4.40cache read $0.047 → $0.0402026-10-05 23:40 UTC
- GLM 5.3InferenceNetinference-net$0.160 → $0.140 / $4.40cache read $0.053 → $0.0472026-10-05 22:51 UTC
- GLM 5.3InferenceNetinference-net$0.140 → $0.160 / $4.40cache read $0.047 → $0.0532026-10-05 22:31 UTC
- GLM 5.3Waferwafer$0.120 → $0.100 / $7.002026-10-05 22:26 UTC
- GLM 5.3Waferwafer/us$0.085 → $0.070 / $7.002026-10-05 22:26 UTC
- GLM 5.3Waferwafer$0.100 → $0.120 / $7.002026-10-05 22:20 UTC
- GLM 5.3Waferwafer/us$0.070 → $0.085 / $7.002026-10-05 22:20 UTC
- GLM 5.3Waferwafer/us$0.060 → $0.070 / $7.00cache read $0.055 → $0.0652026-10-05 21:21 UTC
- GLM 5.3InferenceNetinference-net$0.120 → $0.140 / $4.40cache read $0.040 → $0.0472026-10-05 20:46 UTC
- GLM 5.3Waferwafer$0.120 → $0.100 / $7.00cache read $0.110 → $0.0952026-10-05 20:01 UTC
- GLM 5.3Waferwafer/us$0.070 → $0.060 / $7.00cache read $0.065 → $0.0552026-10-05 19:36 UTC
- GLM 5.3Makoramakora/fp4$0.240 → $0.180 / $3.93 → $4.402026-10-05 19:16 UTC
- GLM 5.3Waferwafer$0.100 → $0.120 / $7.00cache read $0.095 → $0.1102026-10-05 18:36 UTC
- GLM 5.3Waferwafer/us$0.050 → $0.070 / $7.00cache read $0.045 → $0.0652026-10-05 18:36 UTC
- GLM 5.3InferenceNetinference-net$0.100 → $0.120 / $4.40cache read $0.033 → $0.0402026-10-05 17:56 UTC
- GLM 5.3AkashMLakashml/fp8$1.17 → $0.190 / $3.96 → $4.40cache read $0.260 → $0.1902026-10-05 17:35 UTC
- GLM 5.3InferenceNetinference-net$0.120 → $0.100 / $4.40cache read $0.040 → $0.0332026-10-05 17:01 UTC
- GLM 5.3AkashMLakashml/fp8$1.05 → $1.17 / $3.56 → $3.96cache read $0.234 → $0.2602026-10-05 16:36 UTC
- GLM 5.3Morphmorph/fp8$0.131 / $3.18cache read $0.166 → $0.1472026-10-05 15:56 UTC