GLM 5.2
z-ai/glm-5.2InputOutput
Compare its 50 providersIncident RSSCompare with GLM 5.3, GLM 5.3 Flash, GLM 5.3 FlashX
Showing only the baidu/fast provider · show all 50
CompareGLM 5.2
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | 99.67% | 99.98% | 99.76% | 843ms | 1.56s | 69 tps | 1.0M | $2.25 / $7.88 |
- No data24h 99.67%
- 7d
- 99.98%
- 30d
- 99.76%
- p50
- 843ms
- p99
- 1.56s
- Throughput
- 69 tps
- Context
- 1.0M
- $/Mtok
- $2.25 / $7.88
baidu/fastfp4
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 · 50 endpoints · 47 days with data, 203 endpoint-days below 90%. Tables and charts above are filtered to baidu/fast.
Price changes
- GLM 5.2Waferwafer$0.380 / $1.70cache read $0.260 → $0.3102026-10-04 23:51 UTC
- GLM 5.2Waferwafer$0.380 / $3.49 → $1.702026-10-04 23:16 UTC
- GLM 5.2Relacerelace$0.079 → $0.104 / $8.00cache read $0.079 → $0.1002026-10-04 22:41 UTC
- GLM 5.2InferenceNetinference-net$0.099 → $0.130 / $4.00cache read $0.095 → $0.1102026-10-04 22:31 UTC
- GLM 5.2Relacerelace$0.104 → $0.079 / $8.00cache read $0.100 → $0.0792026-10-04 22:21 UTC
- GLM 5.2InferenceNetinference-net$0.130 → $0.099 / $4.00cache read $0.110 → $0.0952026-10-04 22:15 UTC
- GLM 5.2Decartdecart/mxfp4$0.403 → $0.494 / $2.48 → $3.04cache read $0.155 → $0.1902026-10-04 20:06 UTC
- GLM 5.2InferenceNetinference-net$0.130 / $4.00cache read $0.099 → $0.1102026-10-04 19:41 UTC
- GLM 5.2InferenceNetinference-net$0.130 / $4.00cache read $0.110 → $0.0992026-10-04 19:21 UTC
- GLM 5.2Waferwafer$0.240 → $0.380 / $3.49cache read $0.160 → $0.2602026-10-04 19:16 UTC
- GLM 5.2Waferwafer$0.380 → $0.240 / $3.49cache read $0.260 → $0.1602026-10-04 18:26 UTC
- GLM 5.2Relacerelace$0.079 → $0.104 / $8.00cache read $0.079 → $0.1002026-10-04 18:16 UTC
- GLM 5.2InferenceNetinference-net$0.099 → $0.130 / $4.00cache read $0.095 → $0.1102026-10-04 18:06 UTC
- GLM 5.2Relacerelace$0.198 → $0.079 / $8.00cache read $0.200 → $0.0792026-10-04 18:02 UTC
- GLM 5.2InferenceNetinference-net$0.049 → $0.099 / $4.00cache read $0.045 → $0.0952026-10-04 17:51 UTC
- GLM 5.2Relacerelace$0.192 → $0.198 / $8.00cache read $0.190 → $0.2002026-10-04 17:41 UTC
- GLM 5.2Waferwafer$0.240 → $0.380 / $3.49cache read $0.160 → $0.2602026-10-04 17:31 UTC
- GLM 5.2Relacerelace$0.050 → $0.192 / $8.00cache read $0.050 → $0.1902026-10-04 17:26 UTC
- GLM 5.2InferenceNetinference-net$0.063 → $0.049 / $4.00cache read $0.060 → $0.0452026-10-04 17:16 UTC
- GLM 5.2InferenceNetinference-net$0.063 / $4.40 → $4.002026-10-04 17:06 UTC
- GLM 5.2Waferwafer$0.380 → $0.240 / $3.49cache read $0.260 → $0.1602026-10-04 16:36 UTC
- GLM 5.2InferenceNetinference-net$0.063 / $4.00 → $4.402026-10-04 16:11 UTC
- GLM 5.2Relacerelace$0.064 → $0.050 / $8.00cache read $0.064 → $0.0502026-10-04 15:11 UTC
- GLM 5.2InferenceNetinference-net$0.085 → $0.063 / $4.00cache read $0.075 → $0.0602026-10-04 15:02 UTC
- GLM 5.2InferenceNetinference-net$0.085 / $4.40 → $4.002026-10-04 14:51 UTC
- GLM 5.2InferenceNetinference-net$0.085 / $4.00 → $4.402026-10-04 14:21 UTC
- GLM 5.2Waferwafer$0.240 → $0.380 / $3.49cache read $0.220 → $0.2602026-10-04 14:01 UTC
- GLM 5.2InferenceNetinference-net$0.085 / $3.50 → $4.002026-10-04 13:55 UTC
- GLM 5.2Decartdecart/mxfp4$0.390 → $0.403 / $2.40 → $2.48cache read $0.150 → $0.1552026-10-04 13:46 UTC
- GLM 5.2InferenceNetinference-net$0.085 / $3.00 → $3.502026-10-04 13:36 UTC