DeepInfra

80 endpoints · 4 unhealthy · worst uptime 84.21%

	State
DeepSeek V3.1deepinfra/fp4fp4	Healthy	100%	99.91%	99.84%	99.91%	3.65s	7.75s	6.0 tps	164K	$0.250 / $0.950
R1 0528deepinfra/fp4fp4	Healthy	100%	99.94%	99.94%	99.94%	864ms	6.71s	18 tps	164K	$0.500 / $2.15
DeepSeek V4 Pro 0423deepinfra/fp8fp8	Healthy	100%	99.80%	99.65%	99.39%	1.08s	5.64s	59 tps	1.0M	$1.30 / $2.60
DeepSeek V4 Pro 0813deepinfra/fp8fp8	Healthy	100%	98.93%	99.56%	99.26%	1.34s	12.2s	59 tps	1.0M	$1.30 / $2.60
DeepSeek V4.1 Flashdeepinfra/fp8fp8	Healthy	100%	99.96%	99.94%	98.66%	977ms	5.65s	84 tps	1.0M	$0.140 / $0.420
Gemma 3 4Bdeepinfra/bf16bf16	Healthy	100%	100%	100%	100%	942ms	2.84s	52 tps	131K	$0.050 / $0.100
MythoMax 13Bdeepinfra/fp16fp16	Healthy	100%	99.99%	99.99%	99.97%	209ms	1.56s	47 tps	4K	$0.400 / $0.400
Granite 4.2 8Bdeepinfra/bf16bf16	Healthy	100%	100%	99.97%	99.98%	717ms	2.79s	33 tps	131K	$0.060 / $0.250
Ling 3.0 Flash Findeepinfra/fp4fp4	Healthy	100%	99.97%	99.99%	100%	363ms	1.78s	137 tps	262K	$0.060 / $0.180
Llama 3.1 70B Instructdeepinfra/turbofp8	Healthy	100%	99.49%	97.00%	94.91%	346ms	8.78s	38 tps	131K	$0.400 / $0.400
Llama Guard 4 12Bdeepinfra/bf16bf16	Healthy	100%	100%	100%	100%	—	—	—	164K	$0.180 / $0.180
Muse Glimmer 30Bdeepinfra/bf16bf16	Healthy	100%	100%	99.94%	99.97%	754ms	4.58s	103 tps	131K	$0.300 / $1.20
Phi 4deepinfra/bf16bf16	Healthy	100%	100%	100%	99.98%	2.56s	4.25s	44 tps	16K	$0.070 / $0.140
Mistral Small 3deepinfra/fp8fp8	Healthy	100%	99.99%	99.99%	99.99%	353ms	2.38s	42 tps	33K	$0.050 / $0.080
Kimi K2.6deepinfra/fp4fp4	Degraded	100%	93.26%	96.39%	98.30%	2.67s	13.0s	12 tps	262K	$0.750 / $3.50
Hermes 3 405B Instructdeepinfra/fp8fp8	Healthy	100%	100%	99.99%	99.98%	579ms	4.22s	20 tps	131K	$1.00 / $1.00
Hermes 3 70B Instructdeepinfra/fp8fp8	Healthy	100%	99.99%	99.99%	100%	644ms	8.24s	24 tps	131K	$0.700 / $0.700
Nemotron 3 Superdeepinfra/bf16bf16	Healthy	100%	99.99%	99.98%	99.97%	4.30s	68.4s	64 tps	262K	$0.085 / $0.400
Nemotron 3 Ultradeepinfra/fp4fp4	Healthy	100%	99.96%	99.92%	99.86%	1.00s	3.98s	75 tps	262K	$0.500 / $2.20
Nemotron 3.5 Lightningdeepinfra/bf16bf16	Healthy	100%	99.98%	99.96%	99.83%	225ms	1.54s	222 tps	262K	$0.060 / $0.160
gpt-oss-120bdeepinfra/turbobf16	Healthy	100%	99.95%	99.98%	99.97%	467ms	2.20s	105 tps	131K	$0.150 / $0.600
gpt-oss-20bdeepinfra/bf16bf16	Healthy	100%	99.96%	99.87%	99.89%	218ms	2.48s	91 tps	131K	$0.030 / $0.140
Qwen2.5 72B Instructdeepinfra/fp8fp8	Healthy	100%	99.88%	97.69%	99.00%	961ms	6.14s	29 tps	33K	$0.360 / $0.400
Qwen3 14Bdeepinfra/fp8fp8	Healthy	100%	99.76%	96.76%	98.50%	487ms	4.46s	30 tps	41K	$0.120 / $0.240
Qwen3 30B A3Bdeepinfra/fp8fp8	Healthy	100%	99.99%	99.98%	99.84%	520ms	4.85s	141 tps	41K	$0.120 / $0.500
Qwen3 32Bdeepinfra/fp8fp8	Healthy	100%	99.94%	99.87%	99.78%	371ms	2.38s	27 tps	41K	$0.080 / $0.280
Qwen3 Next 80B A3B Instructdeepinfra/fp8fp8	Healthy	100%	99.71%	99.54%	99.39%	523ms	2.70s	138 tps	262K	$0.090 / $1.10
Qwen3 VL 235B A22B Instructdeepinfra/fp8fp8	Healthy	100%	96.74%	96.66%	95.88%	1.62s	7.34s	22 tps	262K	$0.200 / $0.880
Qwen3.5-27Bdeepinfra/fp8fp8	Healthy	100%	99.97%	99.98%	98.79%	540ms	3.43s	59 tps	262K	$0.260 / $2.60
Qwen3.5-35B-A3Bdeepinfra/fp8fp8	Healthy	100%	99.91%	99.81%	98.80%	802ms	2.92s	52 tps	262K	$0.140 / $1.00
Qwen3.5 397B A17Bdeepinfra/fp8fp8	Healthy	100%	99.61%	98.86%	97.34%	1.11s	5.55s	44 tps	262K	$0.450 / $3.00
Qwen3.5-9Bdeepinfra/bf16bf16	Healthy	100%	99.66%	99.62%	98.00%	1.15s	5.16s	12 tps	262K	$0.100 / $0.150
Qwen3.6 27Bdeepinfra/fp8fp8	Healthy	100%	99.62%	99.63%	97.67%	878ms	4.36s	48 tps	262K	$0.320 / $3.20
Qwen3.6 35B A3Bdeepinfra/fp8fp8	Healthy	100%	99.84%	97.50%	95.77%	762ms	25.5s	146 tps	262K	$0.100 / $0.950
Qwen3.8 27Bdeepinfra/bf16bf16	Healthy	100%	99.87%	98.77%	96.59%	1.23s	31.1s	33 tps	262K	$0.150 / $1.88
Llama 3 8B Lunarisdeepinfra/turbofp8	Healthy	100%	99.97%	99.96%	99.93%	144ms	1.42s	84 tps	8K	$0.040 / $0.050
Hy3deepinfra/fp4fp4	Healthy	100%	99.82%	99.83%	99.55%	868ms	27.8s	69 tps	262K	$0.130 / $0.530
Inklingdeepinfra/fp8fp8	Healthy	100%	99.23%	99.40%	89.54%	1.18s	4.54s	57 tps	524K	$0.950 / $4.05
Inkling Smalldeepinfra/fp8fp8	Healthy	100%	99.98%	100%	96.45%	643ms	18.7s	45 tps	524K	$0.450 / $1.20
MiMo-V2.6-Flashdeepinfra/fp8fp8	Healthy	100%	98.41%	96.41%	94.25%	1.09s	7.71s	78 tps	1.0M	$0.140 / $0.280
MiMo-V2.6-Prodeepinfra/fp8fp8	Healthy	100%	99.89%	99.81%	98.28%	1.73s	24.7s	25 tps	1.0M	$0.430 / $0.870
GLM 4.6deepinfra/fp4fp4	Healthy	100%	99.81%	99.78%	99.78%	1.13s	17.7s	16 tps	203K	$0.500 / $2.00
GLM 5.2deepinfra/fp4fp4	Healthy	100%	99.56%	99.38%	99.17%	1.82s	18.8s	47 tps	1.0M	$0.563 / $1.80
DeepSeek V4 Flash 0423deepinfra/fp8fp8	Healthy	99.99%	99.91%	99.50%	99.50%	1.07s	7.35s	33 tps	1.0M	$0.090 / $0.180
Mistral Nemodeepinfra/fp8fp8	Healthy	99.98%	99.95%	99.94%	99.92%	1.05s	3.90s	20 tps	131K	$0.019 / $0.030
gpt-oss-120bdeepinfra/bf16bf16	Healthy	99.97%	99.92%	98.50%	99.07%	312ms	2.57s	68 tps	131K	$0.037 / $0.170
Gemma 3 12Bdeepinfra/bf16bf16	Healthy	99.96%	99.95%	99.92%	99.93%	1.16s	4.43s	29 tps	131K	$0.050 / $0.150
Llama 3.1 8B Instructdeepinfra/fp8fp8	Healthy	99.94%	99.96%	99.63%	99.27%	592ms	3.16s	28 tps	131K	$0.020 / $0.040
DeepSeek V4 Flash 0731deepinfra/fp8fp8	Healthy	99.94%	99.92%	99.89%	99.74%	724ms	5.93s	41 tps	1.0M	$0.060 / $0.180
Mistral Small 3.2 24Bdeepinfra/fp8fp8	Healthy	99.93%	99.84%	99.88%	99.82%	862ms	3.88s	33 tps	128K	$0.075 / $0.200
Llama 4 Scoutdeepinfra/fp8fp8	Healthy	99.93%	99.94%	99.92%	99.91%	545ms	2.50s	45 tps	328K	$0.100 / $0.300
DeepSeek V3deepinfra/fp4fp4	Healthy	99.93%	97.89%	95.29%	95.01%	489ms	2.28s	29 tps	164K	$0.320 / $0.890
DeepSeek V4 Flash Vision Expdeepinfra/fp8fp8	Healthy	99.91%	99.72%	99.68%	95.96%	1.30s	10.9s	76 tps	1.0M	$0.216 / $0.647
Ling 3.0 Flashdeepinfra/bf16bf16	Healthy	99.90%	98.80%	98.44%	97.67%	1.73s	8.22s	53 tps	131K	$0.060 / $0.180
Gemma 4 26B A4B deepinfra/fp8fp8	Healthy	99.86%	99.80%	99.62%	99.41%	680ms	9.27s	42 tps	262K	$0.070 / $0.340
GLM 5.3 Flashdeepinfra/fp4fp4	Healthy	99.86%	98.28%	99.51%	98.83%	1.15s	10.8s	44 tps	1.0M	$0.075 / $0.250
Gemma 4 31Bdeepinfra/fp8fp8	Healthy	99.29%	98.66%	97.93%	97.11%	1.42s	9.68s	15 tps	262K	$0.200 / $0.400
Qwen3 VL 30B A3B Instructdeepinfra/fp8fp8	Healthy	98.93%	99.88%	99.77%	91.35%	1.07s	12.2s	24 tps	262K	$0.150 / $0.600
GLM 5.3deepinfra/fp4fp4	Healthy	98.49%	99.04%	99.23%	97.12%	2.37s	31.4s	60 tps	1.0M	$0.563 / $2.50
DeepSeek V3.2deepinfra/fp4fp4	Healthy	98.03%	99.57%	99.09%	99.05%	1.46s	8.97s	17 tps	164K	$0.260 / $0.380
Llama 3.3 70B Instructdeepinfra/turbofp8	Healthy	97.23%	98.44%	97.37%	98.01%	509ms	15.7s	17 tps	131K	$0.100 / $0.320
Gemma 3 27Bdeepinfra/fp8fp8	Healthy	96.61%	99.37%	99.39%	99.46%	2.10s	9.66s	20 tps	131K	$0.080 / $0.160
Qwen3 235B A22B Instruct 2507deepinfra/fp8fp8	Down	87.01%	90.00%	84.26%	90.56%	913ms	31.4s	11 tps	262K	$0.090 / $0.550
Gemma 4 31Bdeepinfra/turbofp4	Down	84.99%	97.02%	98.65%	98.98%	575ms	5.73s	42 tps	262K	$0.090 / $0.340
Qwen3 Coder 480B A35Bdeepinfra/turbofp4	Down	84.21%	98.49%	96.01%	96.19%	707ms	42.1s	52 tps	262K	$0.300 / $1.00
DeepSeek V4.1 Flash (batch)deepinfra/fp8fp8	No data	—	—	—	—	—	—	—	1.0M	$0.112 / $0.336
Ling 3.0 Flash VLdeepinfra/fp16fp16	No data	—	99.95%	99.82%	99.82%	1.45s	10.8s	54 tps	131K	$0.060 / $0.180
MiniMax M3deepinfra/fp8fp8	No data	—	99.82%	99.58%	98.86%	1.39s	9.34s	7.0 tps	524K	$0.280 / $1.10
Kimi K3deepinfra/mxfp4mxfp4	No data	—	99.70%	99.53%	99.53%	1.05s	21.4s	28 tps	1.0M	$2.85 / $14.25
Kimi K3 (batch)deepinfra/bf16bf16	No data	—	—	—	—	—	—	—	1.0M	$2.28 / $11.40
Nemotron 3 Nano 30B A3Bdeepinfra/fp4fp4	No data	—	87.61%	95.22%	98.49%	3.61s	81.4s	25 tps	262K	$0.050 / $0.200
Nemotron 3.5 Content Safetydeepinfra/bf16bf16	No data	—	100%	100%	100%	368ms	1.63s	213 tps	131K	$0.200 / $0.200
gpt-oss-120b (batch)deepinfra/bf16bf16	No data	—	—	—	—	—	—	—	131K	$0.030 / $0.136
gpt-oss-20b (batch)deepinfra/bf16bf16	No data	—	—	—	—	—	—	—	131K	$0.024 / $0.112
Qwen3.8 2.4T A95Bdeepinfra/fp4fp4	No data	—	99.90%	99.75%	99.46%	1.42s	8.94s	73 tps	262K	$2.00 / $6.00
Llama 3.1 Euryale 70B v2.2deepinfra/fp8fp8	No data	—	99.76%	99.72%	99.31%	320ms	2.13s	37 tps	131K	$0.850 / $0.850
Hy4 previewdeepinfra/fp8fp8	No data	—	98.21%	99.75%	99.75%	1.98s	4.28s	27 tps	1.0M	$0.834 / $2.50
GLM 4.7deepinfra/fp4fp4	No data	—	98.18%	93.19%	95.62%	1.34s	11.0s	14 tps	203K	$0.400 / $1.75
GLM 5.3 Flash (batch)deepinfra/fp4fp4	No data	—	—	—	—	—	—	—	1.0M	$0.060 / $0.200
GLM 5.3 (batch)deepinfra/fp4fp4	No data	—	—	—	—	—	—	—	1.0M	$0.450 / $2.00

DeepSeek V3.1100%
Healthy24h 99.91%
7d
99.84%
30d
99.91%
p50
3.65s
p99
7.75s
Throughput
6.0 tps
Context
164K
$/Mtok
$0.250 / $0.950
deepinfra/fp4fp4
R1 0528100%
Healthy24h 99.94%
7d
99.94%
30d
99.94%
p50
864ms
p99
6.71s
Throughput
18 tps
Context
164K
$/Mtok
$0.500 / $2.15
deepinfra/fp4fp4
DeepSeek V4 Pro 0423100%
Healthy24h 99.80%
7d
99.65%
30d
99.39%
p50
1.08s
p99
5.64s
Throughput
59 tps
Context
1.0M
$/Mtok
$1.30 / $2.60
deepinfra/fp8fp8
DeepSeek V4 Pro 0813100%
Healthy24h 98.93%
7d
99.56%
30d
99.26%
p50
1.34s
p99
12.2s
Throughput
59 tps
Context
1.0M
$/Mtok
$1.30 / $2.60
deepinfra/fp8fp8
DeepSeek V4.1 Flash100%
Healthy24h 99.96%
7d
99.94%
30d
98.66%
p50
977ms
p99
5.65s
Throughput
84 tps
Context
1.0M
$/Mtok
$0.140 / $0.420
deepinfra/fp8fp8
Gemma 3 4B100%
Healthy24h 100%
7d
100%
30d
100%
p50
942ms
p99
2.84s
Throughput
52 tps
Context
131K
$/Mtok
$0.050 / $0.100
deepinfra/bf16bf16
MythoMax 13B100%
Healthy24h 99.99%
7d
99.99%
30d
99.97%
p50
209ms
p99
1.56s
Throughput
47 tps
Context
4K
$/Mtok
$0.400 / $0.400
deepinfra/fp16fp16
Granite 4.2 8B100%
Healthy24h 100%
7d
99.97%
30d
99.98%
p50
717ms
p99
2.79s
Throughput
33 tps
Context
131K
$/Mtok
$0.060 / $0.250
deepinfra/bf16bf16
Ling 3.0 Flash Fin100%
Healthy24h 99.97%
7d
99.99%
30d
100%
p50
363ms
p99
1.78s
Throughput
137 tps
Context
262K
$/Mtok
$0.060 / $0.180
deepinfra/fp4fp4
Llama 3.1 70B Instruct100%
Healthy24h 99.49%
7d
97.00%
30d
94.91%
p50
346ms
p99
8.78s
Throughput
38 tps
Context
131K
$/Mtok
$0.400 / $0.400
deepinfra/turbofp8
Llama Guard 4 12B100%
Healthy24h 100%
7d
100%
30d
100%
p50
—
p99
—
Throughput
—
Context
164K
$/Mtok
$0.180 / $0.180
deepinfra/bf16bf16
Muse Glimmer 30B100%
Healthy24h 100%
7d
99.94%
30d
99.97%
p50
754ms
p99
4.58s
Throughput
103 tps
Context
131K
$/Mtok
$0.300 / $1.20
deepinfra/bf16bf16
Phi 4100%
Healthy24h 100%
7d
100%
30d
99.98%
p50
2.56s
p99
4.25s
Throughput
44 tps
Context
16K
$/Mtok
$0.070 / $0.140
deepinfra/bf16bf16
Mistral Small 3100%
Healthy24h 99.99%
7d
99.99%
30d
99.99%
p50
353ms
p99
2.38s
Throughput
42 tps
Context
33K
$/Mtok
$0.050 / $0.080
deepinfra/fp8fp8
Kimi K2.6100%
Degraded24h 93.26%
7d
96.39%
30d
98.30%
p50
2.67s
p99
13.0s
Throughput
12 tps
Context
262K
$/Mtok
$0.750 / $3.50
deepinfra/fp4fp4
Hermes 3 405B Instruct100%
Healthy24h 100%
7d
99.99%
30d
99.98%
p50
579ms
p99
4.22s
Throughput
20 tps
Context
131K
$/Mtok
$1.00 / $1.00
deepinfra/fp8fp8
Hermes 3 70B Instruct100%
Healthy24h 99.99%
7d
99.99%
30d
100%
p50
644ms
p99
8.24s
Throughput
24 tps
Context
131K
$/Mtok
$0.700 / $0.700
deepinfra/fp8fp8
Nemotron 3 Super100%
Healthy24h 99.99%
7d
99.98%
30d
99.97%
p50
4.30s
p99
68.4s
Throughput
64 tps
Context
262K
$/Mtok
$0.085 / $0.400
deepinfra/bf16bf16
Nemotron 3 Ultra100%
Healthy24h 99.96%
7d
99.92%
30d
99.86%
p50
1.00s
p99
3.98s
Throughput
75 tps
Context
262K
$/Mtok
$0.500 / $2.20
deepinfra/fp4fp4
Nemotron 3.5 Lightning100%
Healthy24h 99.98%
7d
99.96%
30d
99.83%
p50
225ms
p99
1.54s
Throughput
222 tps
Context
262K
$/Mtok
$0.060 / $0.160
deepinfra/bf16bf16
gpt-oss-120b100%
Healthy24h 99.95%
7d
99.98%
30d
99.97%
p50
467ms
p99
2.20s
Throughput
105 tps
Context
131K
$/Mtok
$0.150 / $0.600
deepinfra/turbobf16
gpt-oss-20b100%
Healthy24h 99.96%
7d
99.87%
30d
99.89%
p50
218ms
p99
2.48s
Throughput
91 tps
Context
131K
$/Mtok
$0.030 / $0.140
deepinfra/bf16bf16
Qwen2.5 72B Instruct100%
Healthy24h 99.88%
7d
97.69%
30d
99.00%
p50
961ms
p99
6.14s
Throughput
29 tps
Context
33K
$/Mtok
$0.360 / $0.400
deepinfra/fp8fp8
Qwen3 14B100%
Healthy24h 99.76%
7d
96.76%
30d
98.50%
p50
487ms
p99
4.46s
Throughput
30 tps
Context
41K
$/Mtok
$0.120 / $0.240
deepinfra/fp8fp8
Qwen3 30B A3B100%
Healthy24h 99.99%
7d
99.98%
30d
99.84%
p50
520ms
p99
4.85s
Throughput
141 tps
Context
41K
$/Mtok
$0.120 / $0.500
deepinfra/fp8fp8
Qwen3 32B100%
Healthy24h 99.94%
7d
99.87%
30d
99.78%
p50
371ms
p99
2.38s
Throughput
27 tps
Context
41K
$/Mtok
$0.080 / $0.280
deepinfra/fp8fp8
Qwen3 Next 80B A3B Instruct100%
Healthy24h 99.71%
7d
99.54%
30d
99.39%
p50
523ms
p99
2.70s
Throughput
138 tps
Context
262K
$/Mtok
$0.090 / $1.10
deepinfra/fp8fp8
Qwen3 VL 235B A22B Instruct100%
Healthy24h 96.74%
7d
96.66%
30d
95.88%
p50
1.62s
p99
7.34s
Throughput
22 tps
Context
262K
$/Mtok
$0.200 / $0.880
deepinfra/fp8fp8
Qwen3.5-27B100%
Healthy24h 99.97%
7d
99.98%
30d
98.79%
p50
540ms
p99
3.43s
Throughput
59 tps
Context
262K
$/Mtok
$0.260 / $2.60
deepinfra/fp8fp8
Qwen3.5-35B-A3B100%
Healthy24h 99.91%
7d
99.81%
30d
98.80%
p50
802ms
p99
2.92s
Throughput
52 tps
Context
262K
$/Mtok
$0.140 / $1.00
deepinfra/fp8fp8
Qwen3.5 397B A17B100%
Healthy24h 99.61%
7d
98.86%
30d
97.34%
p50
1.11s
p99
5.55s
Throughput
44 tps
Context
262K
$/Mtok
$0.450 / $3.00
deepinfra/fp8fp8
Qwen3.5-9B100%
Healthy24h 99.66%
7d
99.62%
30d
98.00%
p50
1.15s
p99
5.16s
Throughput
12 tps
Context
262K
$/Mtok
$0.100 / $0.150
deepinfra/bf16bf16
Qwen3.6 27B100%
Healthy24h 99.62%
7d
99.63%
30d
97.67%
p50
878ms
p99
4.36s
Throughput
48 tps
Context
262K
$/Mtok
$0.320 / $3.20
deepinfra/fp8fp8
Qwen3.6 35B A3B100%
Healthy24h 99.84%
7d
97.50%
30d
95.77%
p50
762ms
p99
25.5s
Throughput
146 tps
Context
262K
$/Mtok
$0.100 / $0.950
deepinfra/fp8fp8
Qwen3.8 27B100%
Healthy24h 99.87%
7d
98.77%
30d
96.59%
p50
1.23s
p99
31.1s
Throughput
33 tps
Context
262K
$/Mtok
$0.150 / $1.88
deepinfra/bf16bf16
Llama 3 8B Lunaris100%
Healthy24h 99.97%
7d
99.96%
30d
99.93%
p50
144ms
p99
1.42s
Throughput
84 tps
Context
8K
$/Mtok
$0.040 / $0.050
deepinfra/turbofp8
Hy3100%
Healthy24h 99.82%
7d
99.83%
30d
99.55%
p50
868ms
p99
27.8s
Throughput
69 tps
Context
262K
$/Mtok
$0.130 / $0.530
deepinfra/fp4fp4
Inkling100%
Healthy24h 99.23%
7d
99.40%
30d
89.54%
p50
1.18s
p99
4.54s
Throughput
57 tps
Context
524K
$/Mtok
$0.950 / $4.05
deepinfra/fp8fp8
Inkling Small100%
Healthy24h 99.98%
7d
100%
30d
96.45%
p50
643ms
p99
18.7s
Throughput
45 tps
Context
524K
$/Mtok
$0.450 / $1.20
deepinfra/fp8fp8
MiMo-V2.6-Flash100%
Healthy24h 98.41%
7d
96.41%
30d
94.25%
p50
1.09s
p99
7.71s
Throughput
78 tps
Context
1.0M
$/Mtok
$0.140 / $0.280
deepinfra/fp8fp8
MiMo-V2.6-Pro100%
Healthy24h 99.89%
7d
99.81%
30d
98.28%
p50
1.73s
p99
24.7s
Throughput
25 tps
Context
1.0M
$/Mtok
$0.430 / $0.870
deepinfra/fp8fp8
GLM 4.6100%
Healthy24h 99.81%
7d
99.78%
30d
99.78%
p50
1.13s
p99
17.7s
Throughput
16 tps
Context
203K
$/Mtok
$0.500 / $2.00
deepinfra/fp4fp4
GLM 5.2100%
Healthy24h 99.56%
7d
99.38%
30d
99.17%
p50
1.82s
p99
18.8s
Throughput
47 tps
Context
1.0M
$/Mtok
$0.563 / $1.80
deepinfra/fp4fp4
DeepSeek V4 Flash 042399.99%
Healthy24h 99.91%
7d
99.50%
30d
99.50%
p50
1.07s
p99
7.35s
Throughput
33 tps
Context
1.0M
$/Mtok
$0.090 / $0.180
deepinfra/fp8fp8
Mistral Nemo99.98%
Healthy24h 99.95%
7d
99.94%
30d
99.92%
p50
1.05s
p99
3.90s
Throughput
20 tps
Context
131K
$/Mtok
$0.019 / $0.030
deepinfra/fp8fp8
gpt-oss-120b99.97%
Healthy24h 99.92%
7d
98.50%
30d
99.07%
p50
312ms
p99
2.57s
Throughput
68 tps
Context
131K
$/Mtok
$0.037 / $0.170
deepinfra/bf16bf16
Gemma 3 12B99.96%
Healthy24h 99.95%
7d
99.92%
30d
99.93%
p50
1.16s
p99
4.43s
Throughput
29 tps
Context
131K
$/Mtok
$0.050 / $0.150
deepinfra/bf16bf16
Llama 3.1 8B Instruct99.94%
Healthy24h 99.96%
7d
99.63%
30d
99.27%
p50
592ms
p99
3.16s
Throughput
28 tps
Context
131K
$/Mtok
$0.020 / $0.040
deepinfra/fp8fp8
DeepSeek V4 Flash 073199.94%
Healthy24h 99.92%
7d
99.89%
30d
99.74%
p50
724ms
p99
5.93s
Throughput
41 tps
Context
1.0M
$/Mtok
$0.060 / $0.180
deepinfra/fp8fp8
Mistral Small 3.2 24B99.93%
Healthy24h 99.84%
7d
99.88%
30d
99.82%
p50
862ms
p99
3.88s
Throughput
33 tps
Context
128K
$/Mtok
$0.075 / $0.200
deepinfra/fp8fp8
Llama 4 Scout99.93%
Healthy24h 99.94%
7d
99.92%
30d
99.91%
p50
545ms
p99
2.50s
Throughput
45 tps
Context
328K
$/Mtok
$0.100 / $0.300
deepinfra/fp8fp8
DeepSeek V399.93%
Healthy24h 97.89%
7d
95.29%
30d
95.01%
p50
489ms
p99
2.28s
Throughput
29 tps
Context
164K
$/Mtok
$0.320 / $0.890
deepinfra/fp4fp4
DeepSeek V4 Flash Vision Exp99.91%
Healthy24h 99.72%
7d
99.68%
30d
95.96%
p50
1.30s
p99
10.9s
Throughput
76 tps
Context
1.0M
$/Mtok
$0.216 / $0.647
deepinfra/fp8fp8
Ling 3.0 Flash99.90%
Healthy24h 98.80%
7d
98.44%
30d
97.67%
p50
1.73s
p99
8.22s
Throughput
53 tps
Context
131K
$/Mtok
$0.060 / $0.180
deepinfra/bf16bf16
Gemma 4 26B A4B 99.86%
Healthy24h 99.80%
7d
99.62%
30d
99.41%
p50
680ms
p99
9.27s
Throughput
42 tps
Context
262K
$/Mtok
$0.070 / $0.340
deepinfra/fp8fp8
GLM 5.3 Flash99.86%
Healthy24h 98.28%
7d
99.51%
30d
98.83%
p50
1.15s
p99
10.8s
Throughput
44 tps
Context
1.0M
$/Mtok
$0.075 / $0.250
deepinfra/fp4fp4
Gemma 4 31B99.29%
Healthy24h 98.66%
7d
97.93%
30d
97.11%
p50
1.42s
p99
9.68s
Throughput
15 tps
Context
262K
$/Mtok
$0.200 / $0.400
deepinfra/fp8fp8
Qwen3 VL 30B A3B Instruct98.93%
Healthy24h 99.88%
7d
99.77%
30d
91.35%
p50
1.07s
p99
12.2s
Throughput
24 tps
Context
262K
$/Mtok
$0.150 / $0.600
deepinfra/fp8fp8
GLM 5.398.49%
Healthy24h 99.04%
7d
99.23%
30d
97.12%
p50
2.37s
p99
31.4s
Throughput
60 tps
Context
1.0M
$/Mtok
$0.563 / $2.50
deepinfra/fp4fp4
DeepSeek V3.298.03%
Healthy24h 99.57%
7d
99.09%
30d
99.05%
p50
1.46s
p99
8.97s
Throughput
17 tps
Context
164K
$/Mtok
$0.260 / $0.380
deepinfra/fp4fp4
Llama 3.3 70B Instruct97.23%
Healthy24h 98.44%
7d
97.37%
30d
98.01%
p50
509ms
p99
15.7s
Throughput
17 tps
Context
131K
$/Mtok
$0.100 / $0.320
deepinfra/turbofp8
Gemma 3 27B96.61%
Healthy24h 99.37%
7d
99.39%
30d
99.46%
p50
2.10s
p99
9.66s
Throughput
20 tps
Context
131K
$/Mtok
$0.080 / $0.160
deepinfra/fp8fp8
Qwen3 235B A22B Instruct 250787.01%
Down24h 90.00%
7d
84.26%
30d
90.56%
p50
913ms
p99
31.4s
Throughput
11 tps
Context
262K
$/Mtok
$0.090 / $0.550
deepinfra/fp8fp8
Gemma 4 31B84.99%
Down24h 97.02%
7d
98.65%
30d
98.98%
p50
575ms
p99
5.73s
Throughput
42 tps
Context
262K
$/Mtok
$0.090 / $0.340
deepinfra/turbofp4
Qwen3 Coder 480B A35B84.21%
Down24h 98.49%
7d
96.01%
30d
96.19%
p50
707ms
p99
42.1s
Throughput
52 tps
Context
262K
$/Mtok
$0.300 / $1.00
deepinfra/turbofp4
DeepSeek V4.1 Flash (batch)—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.112 / $0.336
deepinfra/fp8fp8
Ling 3.0 Flash VL—
No data24h 99.95%
7d
99.82%
30d
99.82%
p50
1.45s
p99
10.8s
Throughput
54 tps
Context
131K
$/Mtok
$0.060 / $0.180
deepinfra/fp16fp16
MiniMax M3—
No data24h 99.82%
7d
99.58%
30d
98.86%
p50
1.39s
p99
9.34s
Throughput
7.0 tps
Context
524K
$/Mtok
$0.280 / $1.10
deepinfra/fp8fp8
Kimi K3—
No data24h 99.70%
7d
99.53%
30d
99.53%
p50
1.05s
p99
21.4s
Throughput
28 tps
Context
1.0M
$/Mtok
$2.85 / $14.25
deepinfra/mxfp4mxfp4
Kimi K3 (batch)—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$2.28 / $11.40
deepinfra/bf16bf16
Nemotron 3 Nano 30B A3B—
No data24h 87.61%
7d
95.22%
30d
98.49%
p50
3.61s
p99
81.4s
Throughput
25 tps
Context
262K
$/Mtok
$0.050 / $0.200
deepinfra/fp4fp4
Nemotron 3.5 Content Safety—
No data24h 100%
7d
100%
30d
100%
p50
368ms
p99
1.63s
Throughput
213 tps
Context
131K
$/Mtok
$0.200 / $0.200
deepinfra/bf16bf16
gpt-oss-120b (batch)—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.030 / $0.136
deepinfra/bf16bf16
gpt-oss-20b (batch)—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.024 / $0.112
deepinfra/bf16bf16
Qwen3.8 2.4T A95B—
No data24h 99.90%
7d
99.75%
30d
99.46%
p50
1.42s
p99
8.94s
Throughput
73 tps
Context
262K
$/Mtok
$2.00 / $6.00
deepinfra/fp4fp4
Llama 3.1 Euryale 70B v2.2—
No data24h 99.76%
7d
99.72%
30d
99.31%
p50
320ms
p99
2.13s
Throughput
37 tps
Context
131K
$/Mtok
$0.850 / $0.850
deepinfra/fp8fp8
Hy4 preview—
No data24h 98.21%
7d
99.75%
30d
99.75%
p50
1.98s
p99
4.28s
Throughput
27 tps
Context
1.0M
$/Mtok
$0.834 / $2.50
deepinfra/fp8fp8
GLM 4.7—
No data24h 98.18%
7d
93.19%
30d
95.62%
p50
1.34s
p99
11.0s
Throughput
14 tps
Context
203K
$/Mtok
$0.400 / $1.75
deepinfra/fp4fp4
GLM 5.3 Flash (batch)—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.060 / $0.200
deepinfra/fp4fp4
GLM 5.3 (batch)—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$0.450 / $2.00
deepinfra/fp4fp4