modelstatus.dev

GLM 5.3 Flash

z-ai/glm-5.3-flashInputtextimagevideoOutputtext

Compare its 37 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3

Showing only the inceptron/fp8 provider · show all 37

CompareGLM 5.3 Flash
  • Inceptron—
    No data24h —
    7d
    91.53%
    30d
    91.53%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    1.0M
    $/Mtok
    $0.150 / $0.500
    inceptron/fp8fp8

No recent measurement.

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.

Jun
Jul
Aug
Sep
cloudflare
reka/fp8
morph/fp8
friendli
phala/fp8
relace/fp8
makora
wafer
atlas-cloud/fp8
open-inference/fp4
io-net/fp8
together
digitalocean
siliconflow/fp8
parasail/fp8
venice
near-ai/fp8
novita/fp8
streamlake/fp8
nextbit/fp8
coreweave/fp8
inceptron/fp8
z-ai/fp8
gmicloud/fp8
fireworks
sail-research/fp8
crusoe/fp4
deepinfra/fp4
inference-net/fp4
relace
deepinfra/fp8
coreweave/nvfp4
modal/fp8
baseten/fp8
relace/fp4
streamlake
sail-research/us
worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 37 endpoints · 22 days with data, 202 endpoint-days below 90%. Tables and charts above are filtered to inceptron/fp8.

Price changes

  • GLM 5.3 FlashNextBitnextbit/fp8$0.200 → $0.180 / $0.675 → $0.600cache read $0.040 → $0.0362026-09-17 14:50 UTC
  • GLM 5.3 FlashRekareka/fp8$0.225 → $0.150 / $0.750 → $0.500cache read $0.045 → $0.0302026-09-17 11:40 UTC
  • GLM 5.3 FlashStreamLakestreamlake/fp8$0.105 → $0.141 / $0.349 → $0.470cache read $0.021 → $0.0282026-09-17 02:46 UTC
  • GLM 5.3 FlashRelacerelace$0.070 → $0.090 / $0.233 → $0.300cache read $0.014 → $0.0182026-09-17 00:46 UTC
  • GLM 5.3 FlashRelacerelace$0.090 → $0.070 / $0.300 → $0.233cache read $0.018 → $0.0142026-09-16 23:01 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.250 → $0.200 / $0.900 → $0.675cache read $0.050 → $0.0402026-09-16 15:26 UTC
  • GLM 5.3 FlashRelacerelace$0.100 → $0.090 / $0.333 → $0.300cache read $0.020 → $0.0182026-09-16 11:11 UTC
  • GLM 5.3 FlashStreamLakestreamlake/fp8$0.112 → $0.105 / $0.374 → $0.349cache read $0.022 → $0.0212026-09-16 08:05 UTC
  • GLM 5.3 FlashGMICloudgmicloud/fp8$0.112 → $0.105 / $0.375 → $0.350cache read $0.022 → $0.0212026-09-16 07:45 UTC
  • GLM 5.3 FlashRekareka/fp8$0.150 → $0.225 / $0.500 → $0.750cache read $0.030 → $0.0452026-09-15 14:55 UTC
  • GLM 5.3 FlashRelacerelace$0.090 → $0.100 / $0.300 → $0.333cache read $0.018 → $0.0202026-09-15 14:55 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.210 → $0.250 / $0.900cache read $0.042 → $0.0502026-09-15 14:25 UTC
  • GLM 5.3 FlashRekareka/fp8$0.132 → $0.150 / $0.440 → $0.500cache read $0.026 → $0.0302026-09-15 13:55 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.195 → $0.210 / $0.650 → $0.900cache read $0.040 → $0.0422026-09-15 12:10 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.177 → $0.195 / $0.590 → $0.650cache read $0.036 → $0.0402026-09-15 10:30 UTC
  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.075 → $0.150 / $0.250 → $0.500cache read $0.015 → $0.0302026-09-13 20:25 UTC
  • GLM 5.3 FlashRekareka/fp8$0.150 → $0.132 / $0.500 → $0.440cache read $0.030 → $0.0262026-09-12 16:36 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.150 → $0.177 / $0.500 → $0.590cache read $0.030 → $0.0362026-09-12 09:11 UTC
  • GLM 5.3 FlashStreamLakestreamlake/fp8$0.135 → $0.112 / $0.450 → $0.374cache read $0.027 → $0.0222026-09-11 09:16 UTC
  • GLM 5.3 FlashModalmodal/fp8$0.150 → $0.450 / $0.500 → $1.50cache read $0.030 → $0.0902026-09-10 22:30 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.172 → $0.150 / $0.575 → $0.500cache read $0.034 → $0.0302026-09-10 20:35 UTC
  • GLM 5.3 FlashNextBitnextbit/fp8$0.150 → $0.172 / $0.500 → $0.575cache read $0.030 → $0.0342026-09-10 20:30 UTC
  • GLM 5.3 FlashZ.AIz-ai/fp8$0.075 → $0.150 / $0.250 → $0.500cache read $0.015 → $0.0302026-09-10 09:50 UTC
  • GLM 5.3 FlashZ.AIz-ai/fp8$0.150 → $0.075 / $0.500 → $0.250cache read $0.030 → $0.0152026-09-10 06:25 UTC
  • GLM 5.3 FlashZ.AIz-ai/fp8$0.075 → $0.150 / $0.250 → $0.500cache read $0.015 → $0.0302026-09-10 06:20 UTC
  • GLM 5.3 FlashRelacerelace/fp4$0.070 → $0.090 / $0.233 → $0.300cache read $0.014 → $0.0182026-09-10 04:25 UTC
  • GLM 5.3 FlashZ.AIz-ai/fp8$0.150 → $0.075 / $0.500 → $0.250cache read $0.030 → $0.0152026-09-10 02:45 UTC
  • GLM 5.3 FlashZ.AIz-ai/fp8$0.075 → $0.150 / $0.250 → $0.500cache read $0.015 → $0.0302026-09-10 02:40 UTC
  • GLM 5.3 FlashMorphmorph/fp8$0.388 → $0.100 / $1.36 → $0.350cache read $0.078 → $0.0202026-09-10 02:20 UTC
  • GLM 5.3 FlashRelacerelace/fp4$0.090 → $0.070 / $0.300 → $0.233cache read $0.018 → $0.0142026-09-09 22:45 UTC