modelstatus.dev

GLM 5.3 Flash

z-ai/glm-5.3-flashInputtextimagevideoOutputtext

Compare its 46 providersIncident RSSCompare with GLM 4.7 Flash, GLM 5.3 Flash (batch), GLM 5.3

Showing only the modal/nvfp4 provider · show all 46

CompareGLM 5.3 Flash
  • Modal100%
    Healthy24h 99.07%
    7d
    99.49%
    30d
    99.56%
    p50
    373ms
    p99
    4.32s
    Throughput
    50 tps
    Context
    1.0M
    $/Mtok
    $0.150 / $0.500
    modal/nvfp4nvfp4

Measured 3m 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
morph/fp8
friendli
phala/fp8
relace/fp8
open-inference/fp4
coreweave/nvfp4
makora
wafer
decart/fp4
atlas-cloud/fp8
io-net/fp8
together
digitalocean
siliconflow/fp8
reka/fp8
parasail/fp8
venice
near-ai/fp8
novita/fp8
fireworks
streamlake/fp8
nextbit/fp8
coreweave/fp8
inceptron/fp8
gmicloud/fp8
cloudflare
sail-research/fp8
crusoe/fp4
deepinfra/fp4
z-ai/fp8
dekallm
inference-net/fp4
modal/fp8
relace
deepinfra/fp8
morph
baseten/fp8
relace/fp4
fireworks/us
modal/nvfp4
sail-research/fp4
sail-research/us
reka
streamlake
primeintellect
parasail/fp4
worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 46 endpoints · 41 days with data, 300 endpoint-days below 90%. Tables and charts above are filtered to modal/nvfp4.

Price changes

  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.031 → $0.027 / $0.688cache read $0.020 → $0.0182026-10-06 03:11 UTC
  • GLM 5.3 FlashRelacerelace$0.028 → $0.024 / $0.500cache read $0.018 → $0.0162026-10-06 03:05 UTC
  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.035 → $0.031 / $0.688cache read $0.023 → $0.0202026-10-06 02:55 UTC
  • GLM 5.3 FlashRelacerelace$0.032 → $0.028 / $0.500cache read $0.021 → $0.0182026-10-06 02:51 UTC
  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.040 → $0.035 / $0.688cache read $0.026 → $0.0232026-10-06 02:46 UTC
  • GLM 5.3 FlashRelacerelace$0.036 → $0.032 / $0.500cache read $0.024 → $0.0212026-10-06 02:41 UTC
  • GLM 5.3 FlashRekareka$0.450 → $0.400 / $2.25 → $2.00cache read $0.090 → $0.0802026-10-06 02:41 UTC
  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.047 → $0.040 / $0.813 → $0.688cache read $0.031 → $0.0262026-10-06 02:31 UTC
  • GLM 5.3 FlashInferenceNetinference-net/fp4$0.072 → $0.045 / $0.500cache read $0.022 → $0.0152026-10-06 01:36 UTC
  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.046 → $0.047 / $0.813cache read $0.030 → $0.0312026-10-06 01:21 UTC
  • GLM 5.3 FlashRelacerelace$0.035 → $0.036 / $0.500cache read $0.023 → $0.0242026-10-06 01:15 UTC
  • GLM 5.3 FlashInferenceNetinference-net/fp4$0.044 → $0.072 / $0.600 → $0.500cache read $0.040 → $0.0222026-10-06 01:05 UTC
  • GLM 5.3 FlashWaferwafer$0.060 → $0.050 / $0.500cache read $0.055 → $0.0452026-10-06 00:55 UTC
  • GLM 5.3 FlashRekareka$0.500 → $0.450 / $2.50 → $2.25cache read $0.100 → $0.0902026-10-06 00:41 UTC
  • GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.046 / $0.650 → $0.8132026-10-06 00:31 UTC
  • GLM 5.3 FlashWaferwafer$0.070 → $0.060 / $0.500cache read $0.065 → $0.0552026-10-06 00:11 UTC
  • GLM 5.3 FlashWaferwafer$0.050 → $0.070 / $0.500cache read $0.045 → $0.0652026-10-05 23:20 UTC
  • GLM 5.3 FlashWaferwafer$0.060 → $0.050 / $0.500cache read $0.055 → $0.0452026-10-05 20:21 UTC
  • GLM 5.3 FlashWaferwafer$0.070 → $0.060 / $0.500cache read $0.065 → $0.0552026-10-05 18:00 UTC
  • GLM 5.3 FlashWaferwafer$0.060 → $0.070 / $0.500cache read $0.055 → $0.0652026-10-05 17:26 UTC
  • GLM 5.3 FlashRekareka$0.300 → $0.500 / $1.50 → $2.50cache read $0.060 → $0.1002026-10-05 17:26 UTC
  • GLM 5.3 FlashRekareka$0.150 → $0.300 / $0.500 → $1.50cache read $0.030 → $0.0602026-10-05 16:41 UTC
  • GLM 5.3 FlashWaferwafer$0.060 / $0.650 → $0.5002026-10-05 16:16 UTC
  • GLM 5.3 FlashWaferwafer$0.060 / $0.500 → $0.6502026-10-05 16:01 UTC
  • GLM 5.3 FlashInceptroninceptron/fp8$0.225 / $0.450 → $0.6002026-10-05 13:21 UTC
  • GLM 5.3 FlashWaferwafer$0.050 → $0.060 / $0.500cache read $0.045 → $0.0552026-10-05 13:06 UTC
  • GLM 5.3 FlashInceptroninceptron/fp8$0.160 → $0.225 / $0.450cache read $0.070 → $0.0902026-10-05 10:31 UTC
  • GLM 5.3 FlashWaferwafer$0.140 → $0.050 / $0.500cache read $0.130 → $0.0452026-10-05 05:15 UTC
  • GLM 5.3 FlashDecartdecart/fp4$0.112 → $0.090 / $0.375 → $0.300cache read $0.022 → $0.0182026-10-05 03:50 UTC
  • GLM 5.3 FlashStreamLakestreamlake/fp8$0.084 → $0.087 / $0.279 → $0.290cache read $0.017 → $0.0172026-10-05 02:31 UTC