GLM 5.3 Flash
z-ai/glm-5.3-flashInputOutput
Compare its 12 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3, GLM 5.2
Showing only the baseten/fp8 provider · show all 12
CompareGLM 5.3 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.19% | 98.68% | 98.68% | 826ms | 5.68s | 152 tps | 1.0M | $0.150 / $0.500 |
- BaseTen100%Healthy24h 99.19%
- 7d
- 98.68%
- 30d
- 98.68%
- p50
- 826ms
- p99
- 5.68s
- Throughput
- 152 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
baseten/fp8fp8
Measured 4m 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.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 12 endpoints · 1 day with data, 4 endpoint-days below 90%. Tables and charts above are filtered to baseten/fp8.
Price changes
- GLM 5.3 FlashTogethertogetherfree → $0.150 / free → $0.500cache read — → $0.0302026-08-27 07:15 UTC