modelstatus.dev

GLM 5.3

z-ai/glm-5.3InputtextOutputtext

Compare its 55 providersIncident RSSCompare with GLM 5.3 Flash, GLM 5.3 FlashX, GLM 5.3 Prime

Showing only the inference-net provider · show all 55

CompareGLM 5.3
  • InferenceNet100%
    Healthy24h 99.97%
    7d
    99.38%
    30d
    99.49%
    p50
    491ms
    p99
    3.79s
    Throughput
    123 tps
    Context
    1.0M
    $/Mtok
    $0.080 / $5.00
    inference-net

Measured 52s 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
baseten/fp8
crusoe/fp4
morph/fp8
baidu/fp8
makora/fp4
digitalocean
reka/fast
inference-net/fp4
modal
deepinfra/fp4
venice
morph/fp4
fireworks
wafer
akashml/fp8
reka/fp8
alibaba
atlas-cloud/fp8
together
inceptron/fp4
parasail/fp8
deepinfra/bf16
io-net/fp8
baseten/fast
phala
baseten/fp4
siliconflow/fp8
decart/fp4
sail-research/us
gmicloud/fp8
inference-net
sail-research/fp8
novita/fp8
relace
mistral/nvfp4
friendli
deepinfra/fp8
mistral/zdr
streamlake/fp8
reka
morph
nebius/fp4
cloudflare
crusoe/fp8
wafer/us
z-ai/fp8
alibaba/fast
io-net/fp4
relace/fp4
primeintellect
mistral
streamlake
fireworks/fast
worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 53 endpoints · 47 days with data, 185 endpoint-days below 90%. Tables and charts above are filtered to inference-net.

Price changes

  • GLM 5.3Waferwafer$0.220 / $3.39 → $4.00cache read $0.200 → $0.2092026-10-04 23:51 UTC
  • GLM 5.3Waferwafer/us$0.220 → $0.660 / $3.39 → $4.40cache read $0.200 → $0.2602026-10-04 22:46 UTC
  • GLM 5.3InferenceNetinference-net$0.060 → $0.080 / $5.00cache read $0.050 → $0.0702026-10-04 19:36 UTC
  • GLM 5.3InferenceNetinference-net$0.080 → $0.060 / $5.00cache read $0.070 → $0.0502026-10-04 18:26 UTC
  • GLM 5.3Relacerelace$0.080 → $0.136 / $4.40cache read $0.053 → $0.0902026-10-04 18:11 UTC
  • GLM 5.3InferenceNetinference-net$0.100 → $0.080 / $5.00cache read $0.090 → $0.0702026-10-04 17:56 UTC
  • GLM 5.3Relacerelace$0.136 → $0.080 / $4.40cache read $0.090 → $0.0532026-10-04 17:16 UTC
  • GLM 5.3InferenceNetinference-net$0.080 → $0.100 / $5.00cache read $0.070 → $0.0902026-10-04 17:06 UTC
  • GLM 5.3InferenceNetinference-net$0.050 → $0.080 / $5.00cache read $0.040 → $0.0702026-10-04 14:46 UTC
  • GLM 5.3Inceptroninceptron/fp4$0.600 → $0.550 / $3.39cache read $0.175 → $0.1652026-10-04 12:50 UTC
  • GLM 5.3Rekareka/fast$1.33 → $0.865 / $4.40 → $2.86cache read $0.196 → $0.1272026-10-04 11:05 UTC
  • GLM 5.3Morphmorph/fp8$0.071 → $0.190 / $3.182026-10-04 09:11 UTC
  • GLM 5.3Morphmorph/fp8$0.214 → $0.071 / $3.74 → $3.182026-10-04 08:11 UTC
  • GLM 5.3Morphmorph/fp8$0.298 → $0.214 / $3.742026-10-04 07:36 UTC
  • GLM 5.3InferenceNetinference-net$0.050 / $4.40 → $5.002026-10-04 07:11 UTC
  • GLM 5.3Morphmorph/fp8$1.19 → $0.298 / $3.742026-10-04 07:01 UTC
  • GLM 5.3Morphmorph/fp8$0.280 → $1.19 / $2.83 → $3.742026-10-04 06:06 UTC
  • GLM 5.3Morphmorph/fp8$0.357 → $0.280 / $3.07 → $2.832026-10-04 04:10 UTC
  • GLM 5.3Relacerelace$0.080 → $0.136 / $4.40cache read $0.053 → $0.0902026-10-04 02:31 UTC
  • GLM 5.3InferenceNetinference-net$0.100 → $0.050 / $4.40cache read $0.080 → $0.0402026-10-04 02:20 UTC
  • GLM 5.3Morphmorph/fp8$0.119 → $0.357 / $3.072026-10-04 01:56 UTC
  • GLM 5.3Relacerelace$0.095 → $0.080 / $4.40cache read $0.063 → $0.0532026-10-04 01:20 UTC
  • GLM 5.3InferenceNetinference-net$0.075 → $0.100 / $4.40cache read $0.065 → $0.0802026-10-04 01:11 UTC
  • GLM 5.3Relacerelace$0.136 → $0.095 / $4.40cache read $0.090 → $0.0632026-10-04 01:05 UTC
  • GLM 5.3Morphmorph/fp8$0.179 → $0.119 / $3.072026-10-04 00:56 UTC
  • GLM 5.3Relacerelace$0.136 / $8.00 → $4.402026-10-04 00:35 UTC
  • GLM 5.3Relacerelace$0.060 → $0.136 / $8.00cache read $0.054 → $0.0902026-10-04 00:31 UTC
  • GLM 5.3Waferwafer$0.220 / $3.39cache read $0.176 → $0.2002026-10-04 00:11 UTC
  • GLM 5.3Waferwafer/us$0.220 / $3.39cache read $0.176 → $0.2002026-10-04 00:11 UTC
  • GLM 5.3Relacerelace$0.060 / $8.00cache read $0.045 → $0.0542026-10-03 23:55 UTC