Azure

97 endpoints · all healthy · worst uptime 97.35%

	State
Claude Haiku 4.5azure/global	Healthy	100%	99.99%	99.74%	99.89%	647ms	3.90s	65 tps	200K	$1.00 / $5.00
Claude Opus 5azure/global	Healthy	100%	100%	100%	99.99%	2.90s	5.50s	45 tps	1.0M	$5.00 / $25.00
Claude Opus 5.5azure/global	Healthy	100%	99.99%	99.99%	99.96%	3.28s	7.86s	75 tps	1.0M	$4.00 / $20.00
Claude Sonnet 4.5azure/global	Healthy	100%	99.99%	99.97%	99.06%	1.53s	3.60s	35 tps	200K	$3.00 / $15.00
Claude Sonnet 5azure/global	Healthy	100%	99.71%	99.58%	99.74%	1.04s	4.32s	66 tps	1.0M	$2.00 / $10.00
Claude Sonnet 5.5azure/global	Healthy	100%	99.98%	99.80%	99.80%	701ms	4.56s	45 tps	1.0M	$2.00 / $10.00
GPT-4.1 Miniazure	Healthy	100%	99.97%	99.96%	99.96%	1.18s	6.69s	103 tps	1.0M	$0.400 / $1.60
GPT-4o (2024-08-06)azure	Healthy	100%	99.97%	99.85%	99.92%	563ms	1.54s	99 tps	128K	$2.50 / $10.00
GPT-5 Miniazure	Healthy	100%	99.93%	99.97%	99.98%	3.06s	18.0s	80 tps	400K	$0.250 / $2.00
GPT-5 Nanoazure	Healthy	100%	100%	99.97%	99.98%	1.60s	7.22s	118 tps	400K	$0.050 / $0.400
GPT-5.4azure	Healthy	100%	99.99%	99.98%	99.95%	1.51s	4.74s	32 tps	1.1M	$2.50 / $15.00
GPT-5.4azure/eu	Healthy	100%	100%	100%	100%	—	—	—	1.1M	$2.75 / $16.50
GPT-5.4 Miniazure	Healthy	100%	99.97%	99.98%	99.98%	832ms	4.25s	61 tps	400K	$0.750 / $4.50
GPT-5.4 Nanoazure	Healthy	100%	99.99%	99.99%	99.98%	1.90s	15.5s	61 tps	400K	$0.200 / $1.25
GPT-5.5azure	Healthy	100%	99.99%	99.97%	99.92%	6.66s	25.0s	32 tps	1.1M	$5.00 / $30.00
GPT-5.6 Lunaazure/eu	Healthy	100%	100%	99.99%	99.13%	1.52s	8.32s	95 tps	1.1M	$0.220 / $1.32
GPT-5.6 Solazure	Healthy	100%	99.99%	99.99%	99.94%	3.51s	26.9s	76 tps	1.1M	$4.00 / $20.00
GPT-5.6 Terraazure	Healthy	100%	100%	99.99%	99.89%	2.47s	16.1s	85 tps	1.1M	$2.00 / $12.00
GPT-6 Astraazure	Healthy	100%	100%	99.99%	98.81%	5.58s	50.5s	40 tps	1.1M	$10.00 / $50.00
GPT-6 Lunaazure/eu	Healthy	100%	100%	99.98%	99.77%	1.42s	37.7s	83 tps	1.1M	$0.110 / $0.550
GPT-6 Lunaazure/us	Healthy	100%	100%	99.47%	99.22%	1.64s	10.6s	87 tps	1.1M	$0.110 / $0.550
GPT-6 Solazure	Healthy	100%	100%	100%	99.64%	4.06s	16.3s	35 tps	1.1M	$2.00 / $10.00
GPT-6.1 Solazure	Healthy	100%	99.99%	99.96%	99.96%	6.71s	44.3s	52 tps	1.1M	$2.00 / $10.00
GPT-6.1 Solazure/us	Healthy	100%	99.99%	99.84%	99.84%	5.10s	23.2s	50 tps	1.1M	$2.20 / $11.00
GPT-4o-miniazure	Healthy	99.96%	99.97%	99.95%	99.74%	1.31s	3.40s	54 tps	128K	$0.150 / $0.600
GPT-6 Lunaazure	Healthy	99.92%	99.93%	99.96%	98.35%	4.08s	28.8s	126 tps	1.1M	$0.100 / $0.500
GPT-4oazure	Healthy	99.87%	99.89%	99.87%	99.88%	1.06s	4.35s	77 tps	128K	$2.50 / $10.00
GPT-5.6 Lunaazure	Healthy	98.28%	99.87%	99.91%	92.37%	2.35s	15.7s	72 tps	1.1M	$0.200 / $1.20
DeepSeek V4 Flash 0423azure/us	Healthy	97.35%	97.54%	97.62%	95.75%	1.05s	10.7s	71 tps	1.0M	$0.210 / $0.560
Claude Fable 5azure	No data	—	99.04%	95.39%	96.73%	—	—	—	1.0M	$10.00 / $50.00
Claude Fable 5.1azure	No data	—	99.62%	99.29%	99.76%	7.52s	7.52s	18 tps	1.0M	$10.00 / $50.00
Claude Opus 4.5azure/global	No data	—	—	100%	100%	894ms	894ms	25 tps	200K	$5.00 / $25.00
Claude Opus 4.6azure/global	No data	—	89.92%	87.75%	90.91%	2.03s	4.66s	26 tps	1.0M	$5.00 / $25.00
Claude Opus 4.7azure/global	No data	—	—	100%	100%	903ms	903ms	25 tps	1.0M	$5.00 / $25.00
Claude Opus 4.8azure/global	No data	—	97.70%	100%	99.99%	—	—	—	1.0M	$5.00 / $25.00
Claude Opus 4.8azure/us	No data	—	—	100%	100%	1.15s	1.15s	32 tps	1.0M	$5.50 / $27.50
Claude Opus 5azure/us	No data	—	—	100%	99.94%	—	—	—	1.0M	$5.50 / $27.50
Claude Opus 5.5azure/us	No data	—	—	100%	100%	—	—	—	1.0M	$4.40 / $22.00
Claude Sonnet 4.6azure/global	No data	—	82.26%	89.99%	98.19%	1.11s	1.17s	34 tps	1.0M	$3.00 / $15.00
Claude Sonnet 5azure/us	No data	—	—	100%	99.98%	—	—	—	1.0M	$2.20 / $11.00
Claude Sonnet 5.5azure/us	No data	—	100%	100%	100%	—	—	—	1.0M	$2.20 / $11.00
DeepSeek V4 Pro 0423azure/us	No data	—	99.42%	98.98%	98.53%	1.29s	5.42s	68 tps	1.0M	$1.91 / $3.83
GPT-3.5 Turbo (older v0613)azure	No data	—	100%	100%	100%	1.16s	2.19s	109 tps	4K	$1.00 / $2.00
GPT-3.5 Turbo 16kazure	No data	—	99.83%	100%	99.99%	—	—	—	16K	$3.00 / $4.00
GPT-4azure	No data	—	99.96%	99.98%	99.97%	949ms	2.66s	46 tps	8K	$30.00 / $60.00
GPT-4.1azure	No data	—	99.98%	99.96%	99.96%	1.43s	5.32s	64 tps	1.0M	$2.00 / $8.00
GPT-4.1azure/swedencentral	No data	—	100%	100%	100%	—	—	—	1.0M	$2.20 / $8.80
GPT-4.1 Miniazure/swedencentral	No data	—	100%	99.99%	99.99%	926ms	2.03s	72 tps	1.0M	$0.440 / $1.76
GPT-4.1 Nanoazure	No data	—	99.26%	99.59%	99.78%	2.03s	7.17s	46 tps	1.0M	$0.100 / $0.400
GPT-4.1 Nanoazure/swedencentral	No data	—	100%	100%	100%	601ms	1.18s	190 tps	1.0M	$0.110 / $0.440
GPT-4o (2024-05-13)azure	No data	—	99.82%	98.43%	98.11%	970ms	2.03s	89 tps	128K	$5.00 / $15.00
GPT-4o-miniazure/swedencentral	No data	—	100%	99.96%	99.98%	721ms	1.92s	136 tps	128K	$0.165 / $0.660
GPT-5azure	No data	—	99.99%	99.93%	99.93%	4.03s	34.3s	91 tps	400K	$1.25 / $10.00
GPT-5azure/swedencentral	No data	—	100%	100%	100%	—	—	—	400K	$1.38 / $11.00
GPT-5 Miniazure/swedencentral	No data	—	100%	100%	100%	—	—	—	400K	$0.275 / $2.20
GPT-5 Nanoazure/swedencentral	No data	—	100%	100%	100%	—	—	—	400K	$0.055 / $0.440
GPT-5.1azure	No data	—	99.99%	99.98%	99.98%	978ms	3.53s	49 tps	400K	$1.25 / $10.00
GPT-5.1azure/swedencentral	No data	—	—	100%	100%	—	—	—	400K	$1.38 / $11.00
GPT-5.1-Codexazure	No data	—	99.92%	100%	100%	1.55s	16.2s	99 tps	400K	$1.25 / $10.00
GPT-5.1-Codex-Maxazure	No data	—	99.95%	100%	100%	3.01s	9.19s	91 tps	400K	$1.25 / $10.00
GPT-5.1-Codex-Miniazure	No data	—	100%	99.99%	100%	2.23s	16.9s	75 tps	400K	$0.250 / $2.00
GPT-5.2azure	No data	—	100%	99.98%	99.89%	7.88s	43.1s	77 tps	400K	$1.75 / $14.00
GPT-5.2 Chatazure	No data	—	—	—	—	—	—	—	128K	$1.75 / $14.00
GPT-5.2-Codexazure	No data	—	100%	100%	100%	2.40s	11.6s	45 tps	400K	$1.75 / $14.00
GPT-5.3-Codexazure	No data	—	100%	99.98%	100%	2.65s	28.6s	43 tps	400K	$1.75 / $14.00
GPT-5.4azure/us	No data	—	—	100%	100%	—	—	—	1.1M	$2.75 / $16.50
GPT-5.4 Miniazure/us	No data	—	—	100%	99.02%	—	—	—	400K	$0.825 / $4.95
GPT-5.4 Nanoazure/us	No data	—	—	100%	99.85%	—	—	—	400K	$0.220 / $1.38
GPT-5.4 Proazure	No data	—	—	—	—	—	—	—	1.1M	$30.00 / $180.00
GPT-5.5azure/eu	No data	—	100%	100%	100%	—	—	—	1.1M	$5.50 / $33.00
GPT-5.5azure/us	No data	—	—	100%	99.80%	—	—	—	1.1M	$5.50 / $33.00
GPT-5.6 Lunaazure/us	No data	—	100%	99.92%	92.80%	1.82s	4.58s	64 tps	1.1M	$0.220 / $1.32
GPT-5.6 Luna Proazure	No data	—	99.96%	99.90%	95.22%	7.22s	21.5s	107 tps	1.1M	$0.200 / $1.20
GPT-5.6 Luna Proazure/eu	No data	—	100%	100%	99.76%	—	—	—	1.1M	$0.220 / $1.32
GPT-5.6 Solazure/eu	No data	—	99.95%	100%	100%	6.11s	43.2s	70 tps	1.1M	$4.40 / $22.00
GPT-5.6 Solazure/us	No data	—	100%	99.99%	99.09%	7.73s	29.7s	36 tps	1.1M	$4.40 / $22.00
GPT-5.6 Sol Proazure	No data	—	100%	100%	99.98%	—	—	—	1.1M	$4.00 / $20.00
GPT-5.6 Sol Proazure/eu	No data	—	100%	100%	100%	—	—	—	1.1M	$4.40 / $22.00
GPT-5.6 Terraazure/eu	No data	—	100%	100%	100%	2.76s	10.0s	91 tps	1.1M	$2.20 / $13.20
GPT-5.6 Terraazure/us	No data	—	100%	100%	99.63%	1.24s	5.32s	58 tps	1.1M	$2.20 / $13.20
GPT-5.6 Terra Proazure	No data	—	100%	100%	99.99%	4.03s	8.75s	30 tps	1.1M	$2.00 / $12.00
GPT-5.6 Terra Proazure/eu	No data	—	—	—	100%	—	—	—	1.1M	$2.20 / $13.20
GPT-6 Astraazure/us	No data	—	100%	100%	95.83%	43.8s	248s	30 tps	1.1M	$11.00 / $55.00
GPT-6 Astra Proazure	No data	—	100%	100%	99.18%	20.5s	436s	62 tps	1.1M	$10.00 / $50.00
GPT-6 Astra Proazure/us	No data	—	—	100%	95.05%	—	—	—	1.1M	$11.00 / $55.00
GPT-6 Luna Proazure	No data	—	100%	99.98%	99.66%	7.23s	77.5s	110 tps	1.1M	$0.100 / $0.500
GPT-6 Luna Proazure/eu	No data	—	100%	100%	100%	—	—	—	1.1M	$0.110 / $0.550
GPT-6 Luna Proazure/us	No data	—	—	100%	100%	—	—	—	1.1M	$0.110 / $0.550
GPT-6 Solazure/eu	No data	—	100%	100%	100%	963ms	1.99s	34 tps	1.1M	$2.20 / $11.00
GPT-6 Solazure/us	No data	—	100%	100%	99.99%	9.40s	19.2s	35 tps	1.1M	$2.20 / $11.00
GPT-6 Sol Proazure	No data	—	100%	100%	99.98%	10.6s	26.1s	74 tps	1.1M	$2.00 / $10.00
GPT-6 Sol Proazure/eu	No data	—	100%	—	—	—	—	—	1.1M	$2.20 / $11.00
GPT-6 Sol Proazure/us	No data	—	—	—	100%	—	—	—	1.1M	$2.20 / $11.00
GPT-6.1 Solazure/eu	No data	—	99.99%	99.99%	99.99%	—	—	—	1.1M	$2.20 / $11.00
GPT-6.1 Sol Proazure	No data	—	100%	99.99%	99.99%	3.61s	18.6s	26 tps	1.1M	$2.00 / $10.00
GPT-6.1 Sol Proazure/eu	No data	—	100%	—	—	—	—	—	1.1M	$2.20 / $11.00
GPT-6.1 Sol Proazure/us	No data	—	100%	100%	100%	12.2s	37.3s	83 tps	1.1M	$2.20 / $11.00

Claude Haiku 4.5100%
Healthy24h 99.99%
7d
99.74%
30d
99.89%
p50
647ms
p99
3.90s
Throughput
65 tps
Context
200K
$/Mtok
$1.00 / $5.00
azure/global
Claude Opus 5100%
Healthy24h 100%
7d
100%
30d
99.99%
p50
2.90s
p99
5.50s
Throughput
45 tps
Context
1.0M
$/Mtok
$5.00 / $25.00
azure/global
Claude Opus 5.5100%
Healthy24h 99.99%
7d
99.99%
30d
99.96%
p50
3.28s
p99
7.86s
Throughput
75 tps
Context
1.0M
$/Mtok
$4.00 / $20.00
azure/global
Claude Sonnet 4.5100%
Healthy24h 99.99%
7d
99.97%
30d
99.06%
p50
1.53s
p99
3.60s
Throughput
35 tps
Context
200K
$/Mtok
$3.00 / $15.00
azure/global
Claude Sonnet 5100%
Healthy24h 99.71%
7d
99.58%
30d
99.74%
p50
1.04s
p99
4.32s
Throughput
66 tps
Context
1.0M
$/Mtok
$2.00 / $10.00
azure/global
Claude Sonnet 5.5100%
Healthy24h 99.98%
7d
99.80%
30d
99.80%
p50
701ms
p99
4.56s
Throughput
45 tps
Context
1.0M
$/Mtok
$2.00 / $10.00
azure/global
GPT-4.1 Mini100%
Healthy24h 99.97%
7d
99.96%
30d
99.96%
p50
1.18s
p99
6.69s
Throughput
103 tps
Context
1.0M
$/Mtok
$0.400 / $1.60
azure
GPT-4o (2024-08-06)100%
Healthy24h 99.97%
7d
99.85%
30d
99.92%
p50
563ms
p99
1.54s
Throughput
99 tps
Context
128K
$/Mtok
$2.50 / $10.00
azure
GPT-5 Mini100%
Healthy24h 99.93%
7d
99.97%
30d
99.98%
p50
3.06s
p99
18.0s
Throughput
80 tps
Context
400K
$/Mtok
$0.250 / $2.00
azure
GPT-5 Nano100%
Healthy24h 100%
7d
99.97%
30d
99.98%
p50
1.60s
p99
7.22s
Throughput
118 tps
Context
400K
$/Mtok
$0.050 / $0.400
azure
GPT-5.4100%
Healthy24h 99.99%
7d
99.98%
30d
99.95%
p50
1.51s
p99
4.74s
Throughput
32 tps
Context
1.1M
$/Mtok
$2.50 / $15.00
azure
GPT-5.4100%
Healthy24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.75 / $16.50
azure/eu
GPT-5.4 Mini100%
Healthy24h 99.97%
7d
99.98%
30d
99.98%
p50
832ms
p99
4.25s
Throughput
61 tps
Context
400K
$/Mtok
$0.750 / $4.50
azure
GPT-5.4 Nano100%
Healthy24h 99.99%
7d
99.99%
30d
99.98%
p50
1.90s
p99
15.5s
Throughput
61 tps
Context
400K
$/Mtok
$0.200 / $1.25
azure
GPT-5.5100%
Healthy24h 99.99%
7d
99.97%
30d
99.92%
p50
6.66s
p99
25.0s
Throughput
32 tps
Context
1.1M
$/Mtok
$5.00 / $30.00
azure
GPT-5.6 Luna100%
Healthy24h 100%
7d
99.99%
30d
99.13%
p50
1.52s
p99
8.32s
Throughput
95 tps
Context
1.1M
$/Mtok
$0.220 / $1.32
azure/eu
GPT-5.6 Sol100%
Healthy24h 99.99%
7d
99.99%
30d
99.94%
p50
3.51s
p99
26.9s
Throughput
76 tps
Context
1.1M
$/Mtok
$4.00 / $20.00
azure
GPT-5.6 Terra100%
Healthy24h 100%
7d
99.99%
30d
99.89%
p50
2.47s
p99
16.1s
Throughput
85 tps
Context
1.1M
$/Mtok
$2.00 / $12.00
azure
GPT-6 Astra100%
Healthy24h 100%
7d
99.99%
30d
98.81%
p50
5.58s
p99
50.5s
Throughput
40 tps
Context
1.1M
$/Mtok
$10.00 / $50.00
azure
GPT-6 Luna100%
Healthy24h 100%
7d
99.98%
30d
99.77%
p50
1.42s
p99
37.7s
Throughput
83 tps
Context
1.1M
$/Mtok
$0.110 / $0.550
azure/eu
GPT-6 Luna100%
Healthy24h 100%
7d
99.47%
30d
99.22%
p50
1.64s
p99
10.6s
Throughput
87 tps
Context
1.1M
$/Mtok
$0.110 / $0.550
azure/us
GPT-6 Sol100%
Healthy24h 100%
7d
100%
30d
99.64%
p50
4.06s
p99
16.3s
Throughput
35 tps
Context
1.1M
$/Mtok
$2.00 / $10.00
azure
GPT-6.1 Sol100%
Healthy24h 99.99%
7d
99.96%
30d
99.96%
p50
6.71s
p99
44.3s
Throughput
52 tps
Context
1.1M
$/Mtok
$2.00 / $10.00
azure
GPT-6.1 Sol100%
Healthy24h 99.99%
7d
99.84%
30d
99.84%
p50
5.10s
p99
23.2s
Throughput
50 tps
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/us
GPT-4o-mini99.96%
Healthy24h 99.97%
7d
99.95%
30d
99.74%
p50
1.31s
p99
3.40s
Throughput
54 tps
Context
128K
$/Mtok
$0.150 / $0.600
azure
GPT-6 Luna99.92%
Healthy24h 99.93%
7d
99.96%
30d
98.35%
p50
4.08s
p99
28.8s
Throughput
126 tps
Context
1.1M
$/Mtok
$0.100 / $0.500
azure
GPT-4o99.87%
Healthy24h 99.89%
7d
99.87%
30d
99.88%
p50
1.06s
p99
4.35s
Throughput
77 tps
Context
128K
$/Mtok
$2.50 / $10.00
azure
GPT-5.6 Luna98.28%
Healthy24h 99.87%
7d
99.91%
30d
92.37%
p50
2.35s
p99
15.7s
Throughput
72 tps
Context
1.1M
$/Mtok
$0.200 / $1.20
azure
DeepSeek V4 Flash 042397.35%
Healthy24h 97.54%
7d
97.62%
30d
95.75%
p50
1.05s
p99
10.7s
Throughput
71 tps
Context
1.0M
$/Mtok
$0.210 / $0.560
azure/us
Claude Fable 5—
No data24h 99.04%
7d
95.39%
30d
96.73%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$10.00 / $50.00
azure
Claude Fable 5.1—
No data24h 99.62%
7d
99.29%
30d
99.76%
p50
7.52s
p99
7.52s
Throughput
18 tps
Context
1.0M
$/Mtok
$10.00 / $50.00
azure
Claude Opus 4.5—
No data24h —
7d
100%
30d
100%
p50
894ms
p99
894ms
Throughput
25 tps
Context
200K
$/Mtok
$5.00 / $25.00
azure/global
Claude Opus 4.6—
No data24h 89.92%
7d
87.75%
30d
90.91%
p50
2.03s
p99
4.66s
Throughput
26 tps
Context
1.0M
$/Mtok
$5.00 / $25.00
azure/global
Claude Opus 4.7—
No data24h —
7d
100%
30d
100%
p50
903ms
p99
903ms
Throughput
25 tps
Context
1.0M
$/Mtok
$5.00 / $25.00
azure/global
Claude Opus 4.8—
No data24h 97.70%
7d
100%
30d
99.99%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$5.00 / $25.00
azure/global
Claude Opus 4.8—
No data24h —
7d
100%
30d
100%
p50
1.15s
p99
1.15s
Throughput
32 tps
Context
1.0M
$/Mtok
$5.50 / $27.50
azure/us
Claude Opus 5—
No data24h —
7d
100%
30d
99.94%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$5.50 / $27.50
azure/us
Claude Opus 5.5—
No data24h —
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$4.40 / $22.00
azure/us
Claude Sonnet 4.6—
No data24h 82.26%
7d
89.99%
30d
98.19%
p50
1.11s
p99
1.17s
Throughput
34 tps
Context
1.0M
$/Mtok
$3.00 / $15.00
azure/global
Claude Sonnet 5—
No data24h —
7d
100%
30d
99.98%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$2.20 / $11.00
azure/us
Claude Sonnet 5.5—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$2.20 / $11.00
azure/us
DeepSeek V4 Pro 0423—
No data24h 99.42%
7d
98.98%
30d
98.53%
p50
1.29s
p99
5.42s
Throughput
68 tps
Context
1.0M
$/Mtok
$1.91 / $3.83
azure/us
GPT-3.5 Turbo (older v0613)—
No data24h 100%
7d
100%
30d
100%
p50
1.16s
p99
2.19s
Throughput
109 tps
Context
4K
$/Mtok
$1.00 / $2.00
azure
GPT-3.5 Turbo 16k—
No data24h 99.83%
7d
100%
30d
99.99%
p50
—
p99
—
Throughput
—
Context
16K
$/Mtok
$3.00 / $4.00
azure
GPT-4—
No data24h 99.96%
7d
99.98%
30d
99.97%
p50
949ms
p99
2.66s
Throughput
46 tps
Context
8K
$/Mtok
$30.00 / $60.00
azure
GPT-4.1—
No data24h 99.98%
7d
99.96%
30d
99.96%
p50
1.43s
p99
5.32s
Throughput
64 tps
Context
1.0M
$/Mtok
$2.00 / $8.00
azure
GPT-4.1—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$2.20 / $8.80
azure/swedencentral
GPT-4.1 Mini—
No data24h 100%
7d
99.99%
30d
99.99%
p50
926ms
p99
2.03s
Throughput
72 tps
Context
1.0M
$/Mtok
$0.440 / $1.76
azure/swedencentral
GPT-4.1 Nano—
No data24h 99.26%
7d
99.59%
30d
99.78%
p50
2.03s
p99
7.17s
Throughput
46 tps
Context
1.0M
$/Mtok
$0.100 / $0.400
azure
GPT-4.1 Nano—
No data24h 100%
7d
100%
30d
100%
p50
601ms
p99
1.18s
Throughput
190 tps
Context
1.0M
$/Mtok
$0.110 / $0.440
azure/swedencentral
GPT-4o (2024-05-13)—
No data24h 99.82%
7d
98.43%
30d
98.11%
p50
970ms
p99
2.03s
Throughput
89 tps
Context
128K
$/Mtok
$5.00 / $15.00
azure
GPT-4o-mini—
No data24h 100%
7d
99.96%
30d
99.98%
p50
721ms
p99
1.92s
Throughput
136 tps
Context
128K
$/Mtok
$0.165 / $0.660
azure/swedencentral
GPT-5—
No data24h 99.99%
7d
99.93%
30d
99.93%
p50
4.03s
p99
34.3s
Throughput
91 tps
Context
400K
$/Mtok
$1.25 / $10.00
azure
GPT-5—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$1.38 / $11.00
azure/swedencentral
GPT-5 Mini—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.275 / $2.20
azure/swedencentral
GPT-5 Nano—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.055 / $0.440
azure/swedencentral
GPT-5.1—
No data24h 99.99%
7d
99.98%
30d
99.98%
p50
978ms
p99
3.53s
Throughput
49 tps
Context
400K
$/Mtok
$1.25 / $10.00
azure
GPT-5.1—
No data24h —
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$1.38 / $11.00
azure/swedencentral
GPT-5.1-Codex—
No data24h 99.92%
7d
100%
30d
100%
p50
1.55s
p99
16.2s
Throughput
99 tps
Context
400K
$/Mtok
$1.25 / $10.00
azure
GPT-5.1-Codex-Max—
No data24h 99.95%
7d
100%
30d
100%
p50
3.01s
p99
9.19s
Throughput
91 tps
Context
400K
$/Mtok
$1.25 / $10.00
azure
GPT-5.1-Codex-Mini—
No data24h 100%
7d
99.99%
30d
100%
p50
2.23s
p99
16.9s
Throughput
75 tps
Context
400K
$/Mtok
$0.250 / $2.00
azure
GPT-5.2—
No data24h 100%
7d
99.98%
30d
99.89%
p50
7.88s
p99
43.1s
Throughput
77 tps
Context
400K
$/Mtok
$1.75 / $14.00
azure
GPT-5.2 Chat—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
128K
$/Mtok
$1.75 / $14.00
azure
GPT-5.2-Codex—
No data24h 100%
7d
100%
30d
100%
p50
2.40s
p99
11.6s
Throughput
45 tps
Context
400K
$/Mtok
$1.75 / $14.00
azure
GPT-5.3-Codex—
No data24h 100%
7d
99.98%
30d
100%
p50
2.65s
p99
28.6s
Throughput
43 tps
Context
400K
$/Mtok
$1.75 / $14.00
azure
GPT-5.4—
No data24h —
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.75 / $16.50
azure/us
GPT-5.4 Mini—
No data24h —
7d
100%
30d
99.02%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.825 / $4.95
azure/us
GPT-5.4 Nano—
No data24h —
7d
100%
30d
99.85%
p50
—
p99
—
Throughput
—
Context
400K
$/Mtok
$0.220 / $1.38
azure/us
GPT-5.4 Pro—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$30.00 / $180.00
azure
GPT-5.5—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$5.50 / $33.00
azure/eu
GPT-5.5—
No data24h —
7d
100%
30d
99.80%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$5.50 / $33.00
azure/us
GPT-5.6 Luna—
No data24h 100%
7d
99.92%
30d
92.80%
p50
1.82s
p99
4.58s
Throughput
64 tps
Context
1.1M
$/Mtok
$0.220 / $1.32
azure/us
GPT-5.6 Luna Pro—
No data24h 99.96%
7d
99.90%
30d
95.22%
p50
7.22s
p99
21.5s
Throughput
107 tps
Context
1.1M
$/Mtok
$0.200 / $1.20
azure
GPT-5.6 Luna Pro—
No data24h 100%
7d
100%
30d
99.76%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$0.220 / $1.32
azure/eu
GPT-5.6 Sol—
No data24h 99.95%
7d
100%
30d
100%
p50
6.11s
p99
43.2s
Throughput
70 tps
Context
1.1M
$/Mtok
$4.40 / $22.00
azure/eu
GPT-5.6 Sol—
No data24h 100%
7d
99.99%
30d
99.09%
p50
7.73s
p99
29.7s
Throughput
36 tps
Context
1.1M
$/Mtok
$4.40 / $22.00
azure/us
GPT-5.6 Sol Pro—
No data24h 100%
7d
100%
30d
99.98%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$4.00 / $20.00
azure
GPT-5.6 Sol Pro—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$4.40 / $22.00
azure/eu
GPT-5.6 Terra—
No data24h 100%
7d
100%
30d
100%
p50
2.76s
p99
10.0s
Throughput
91 tps
Context
1.1M
$/Mtok
$2.20 / $13.20
azure/eu
GPT-5.6 Terra—
No data24h 100%
7d
100%
30d
99.63%
p50
1.24s
p99
5.32s
Throughput
58 tps
Context
1.1M
$/Mtok
$2.20 / $13.20
azure/us
GPT-5.6 Terra Pro—
No data24h 100%
7d
100%
30d
99.99%
p50
4.03s
p99
8.75s
Throughput
30 tps
Context
1.1M
$/Mtok
$2.00 / $12.00
azure
GPT-5.6 Terra Pro—
No data24h —
7d
—
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.20 / $13.20
azure/eu
GPT-6 Astra—
No data24h 100%
7d
100%
30d
95.83%
p50
43.8s
p99
248s
Throughput
30 tps
Context
1.1M
$/Mtok
$11.00 / $55.00
azure/us
GPT-6 Astra Pro—
No data24h 100%
7d
100%
30d
99.18%
p50
20.5s
p99
436s
Throughput
62 tps
Context
1.1M
$/Mtok
$10.00 / $50.00
azure
GPT-6 Astra Pro—
No data24h —
7d
100%
30d
95.05%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$11.00 / $55.00
azure/us
GPT-6 Luna Pro—
No data24h 100%
7d
99.98%
30d
99.66%
p50
7.23s
p99
77.5s
Throughput
110 tps
Context
1.1M
$/Mtok
$0.100 / $0.500
azure
GPT-6 Luna Pro—
No data24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$0.110 / $0.550
azure/eu
GPT-6 Luna Pro—
No data24h —
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$0.110 / $0.550
azure/us
GPT-6 Sol—
No data24h 100%
7d
100%
30d
100%
p50
963ms
p99
1.99s
Throughput
34 tps
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/eu
GPT-6 Sol—
No data24h 100%
7d
100%
30d
99.99%
p50
9.40s
p99
19.2s
Throughput
35 tps
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/us
GPT-6 Sol Pro—
No data24h 100%
7d
100%
30d
99.98%
p50
10.6s
p99
26.1s
Throughput
74 tps
Context
1.1M
$/Mtok
$2.00 / $10.00
azure
GPT-6 Sol Pro—
No data24h 100%
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/eu
GPT-6 Sol Pro—
No data24h —
7d
—
30d
100%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/us
GPT-6.1 Sol—
No data24h 99.99%
7d
99.99%
30d
99.99%
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/eu
GPT-6.1 Sol Pro—
No data24h 100%
7d
99.99%
30d
99.99%
p50
3.61s
p99
18.6s
Throughput
26 tps
Context
1.1M
$/Mtok
$2.00 / $10.00
azure
GPT-6.1 Sol Pro—
No data24h 100%
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/eu
GPT-6.1 Sol Pro—
No data24h 100%
7d
100%
30d
100%
p50
12.2s
p99
37.3s
Throughput
83 tps
Context
1.1M
$/Mtok
$2.20 / $11.00
azure/us