GLM 5.3
z-ai/glm-5.3InputOutput
Compare its 72 providersIncident RSSCompare with GLM 5.3 Flash, GLM 5.3 FlashX, GLM 5.3 Prime
Showing only the inference-net/us provider · show all 72
CompareGLM 5.3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 100% | 99.96% | 603ms | 6.08s | 99 tps | 1.0M | $0.080 / $3.60 |
- InferenceNet100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.96%
- p50
- 603ms
- p99
- 6.08s
- Throughput
- 99 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $3.60
inference-net/usfp4
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.
Aug
Sep
Oct
Nov
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 60 endpoints · 66 days with data, 446 endpoint-days below 90%. 9 more not shown. Tables and charts above are filtered to inference-net/us.
Price changes
- GLM 5.3Morphmorph/fp8$0.070 → $0.078 / $1.402026-11-01 22:55 UTC
- GLM 5.3Io Netio-net/fp8$0.330 → $0.190 / $3.20 → $3.00cache read $0.310 → $0.1902026-11-01 19:05 UTC
- GLM 5.3Decartdecart/fp4$0.920 → $0.840 / $2.96 → $2.70cache read $0.210 → $0.1902026-11-01 13:50 UTC
- GLM 5.3Decartdecart/fp4$0.840 → $0.920 / $2.69 → $2.96cache read $0.190 → $0.2102026-11-01 13:20 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.080 / $4.00 → $3.602026-11-01 05:35 UTC
- GLM 5.3InferenceNetinference-net/us$0.080 / $4.00 → $3.602026-11-01 05:35 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.080 / $3.60 → $4.002026-11-01 05:30 UTC
- GLM 5.3InferenceNetinference-net/us$0.080 / $3.60 → $4.002026-11-01 05:30 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.080 / $4.00 → $3.602026-11-01 04:55 UTC
- GLM 5.3InferenceNetinference-net/us$0.080 / $4.00 → $3.602026-11-01 04:55 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.080 / $3.60 → $4.002026-11-01 04:30 UTC
- GLM 5.3InferenceNetinference-net/us$0.080 / $3.60 → $4.002026-11-01 04:30 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.104 → $0.080 / $2.77 → $3.60cache read $0.099 → $0.0762026-10-31 20:35 UTC
- GLM 5.3InferenceNetinference-net/us$0.104 → $0.080 / $2.77 → $3.60cache read $0.099 → $0.0762026-10-31 20:35 UTC
- GLM 5.3Morphmorph/fp8$0.086 → $0.070 / $1.402026-10-31 13:50 UTC
- GLM 5.3Relacerelace/fp4$0.145 → $0.070 / $4.00 → $4.38cache read $0.145 → $0.0702026-10-31 01:20 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.080 → $0.104 / $3.18 → $2.77cache read $0.076 → $0.0992026-10-31 00:35 UTC
- GLM 5.3InferenceNetinference-net/us$0.080 → $0.104 / $3.18 → $2.77cache read $0.076 → $0.0992026-10-31 00:35 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.104 → $0.080 / $2.77 → $3.18cache read $0.099 → $0.0762026-10-30 23:50 UTC
- GLM 5.3InferenceNetinference-net/us$0.104 → $0.080 / $2.77 → $3.18cache read $0.099 → $0.0762026-10-30 23:50 UTC
- GLM 5.3InferenceNetinference-net/fp4$0.080 → $0.104 / $3.60 → $2.77cache read $0.076 → $0.0992026-10-30 22:25 UTC
- GLM 5.3InferenceNetinference-net/us$0.080 → $0.104 / $3.60 → $2.77cache read $0.076 → $0.0992026-10-30 22:25 UTC
- GLM 5.3Inceptroninceptron/fp4$1.40 / $4.55 → $2.642026-10-30 14:10 UTC
- GLM 5.3Inceptroninceptron/fp4$1.40 / $2.86 → $4.552026-10-30 13:20 UTC
- GLM 5.3Inceptroninceptron/fp4$1.40 / $2.42 → $2.862026-10-30 13:05 UTC
- GLM 5.3Inceptroninceptron/fp4$1.20 → $1.40 / $2.20 → $2.422026-10-30 11:05 UTC
- GLM 5.3Morphmorph/fp8$0.123 → $0.086 / $1.402026-10-30 09:05 UTC
- GLM 5.3Morphmorph/fp8$0.176 → $0.123 / $1.54 → $1.402026-10-30 06:50 UTC
- GLM 5.3DekaLLMdekallm$0.250 → $0.180 / $2.95cache read $0.180 → $0.1502026-10-30 02:15 UTC
- GLM 5.3Morphmorph/fp8$0.158 → $0.176 / $1.542026-10-29 16:45 UTC