Hugging Face's logo

Inference Providers

·

Metrics for top trending models

Browse all models Learn more
Kimi-K2-Thinking
novita
cheapest
0.6 2.5 262144 1.12 21 Yes No
Kimi-K2-Thinking
together
fastest
1.2 4 262144 0.71 78 Yes Yes
DeepSeek-OCR
novita
0.03 0.03 8192 0.82 189 No Yes
MiniMax-M2
novita
0.3 1.2 204800 1.20 63 No No
Llama-3.1-8B-Instruct
novita
cheapest
0.02 0.05 16384 0.87 83 No No
Llama-3.1-8B-Instruct
nebius
0.03 0.09 131072 0.36 190 No No
Llama-3.1-8B-Instruct
cerebras
fastest
0.1 0.1 - 0.35 1182 No No
Llama-3.1-8B-Instruct
sambanova
0.1 0.2 16384 1.89 355 Yes Yes
Llama-3.1-8B-Instruct
nscale
- - - - - - -
Llama-3.1-8B-Instruct
fireworks-ai
0.2 0.2 131072 0.49 230 No No
Llama-3.1-8B-Instruct
scaleway
- - - 0.49 102 Yes Yes
gpt-oss-20b
groq
fastest
0.1 0.5 131072 0.20 817 Yes No
gpt-oss-20b
novita
0.04 0.15 131072 0.83 195 No Yes
gpt-oss-20b
nebius
0.05 0.2 131072 0.43 176 Yes Yes
gpt-oss-20b
nscale
- - - - - - -
gpt-oss-20b
hyperbolic
cheapest
0.1 0.1 131072 0.91 157 No No
gpt-oss-20b
together
0.05 0.2 131072 0.58 167 Yes Yes
gpt-oss-20b
fireworks-ai
0.05 0.2 131072 0.67 166 Yes No
GLM-4.6
novita
cheapest
0.6 2.2 204800 1.06 27 Yes No
GLM-4.6
cerebras
fastest
- - - 0.33 449 Yes No
GLM-4.6
zai-org
- - - 3.27 37 Yes No
gpt-oss-120b
groq
0.15 0.75 131072 0.26 409 Yes No
gpt-oss-120b
novita
cheapest
0.05 0.25 131072 0.85 159 No Yes
gpt-oss-120b
nebius
0.15 0.6 131072 0.44 151 Yes Yes
gpt-oss-120b
cerebras
fastest
0.25 0.69 - 0.34 971 Yes No
gpt-oss-120b
sambanova
0.22 0.59 131072 1.03 388 Yes Yes
gpt-oss-120b
nscale
- - - - - - -
gpt-oss-120b
hyperbolic
0.3 0.3 131072 0.78 210 Yes No
gpt-oss-120b
together
0.15 0.6 131072 0.32 127 Yes Yes
gpt-oss-120b
fireworks-ai
0.15 0.6 131072 0.76 114 Yes No
gpt-oss-120b
scaleway
- - - 0.40 135 Yes Yes
Kimi-K2-Instruct-0905
groq
fastest
- - 262144 0.27 184 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
0.6 2.5 262144 0.92 36 Yes No
Kimi-K2-Instruct-0905
together
1 3 262144 0.59 59 Yes Yes
Qwen3-VL-8B-Instruct
novita
0.08 0.5 131072 1.12 47 Yes No
Llama-3.2-3B-Instruct
novita
cheapest
0.03 0.05 32768 0.60 126 Yes No
Llama-3.2-3B-Instruct
sambanova
- - - - - - -
Llama-3.2-3B-Instruct
hyperbolic
0.1 0.1 131072 1.36 122 No No
Llama-3.2-3B-Instruct
together
fastest
0.06 0.06 131072 0.58 135 Yes Yes
DeepSeek-R1
novita
0.7 2.5 64000 0.91 29 Yes No
DeepSeek-R1
sambanova
fastest
- - - 2.54 139 Yes Yes
DeepSeek-R1
hyperbolic
cheapest
2 2 163840 0.88 39 No No
DeepSeek-R1
together
3 7 163840 0.83 36 No Yes
DeepSeek-R1
fireworks-ai
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
nebius
cheapest fastest
0.1 0.3 262144 0.33 130 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
fireworks-ai
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
scaleway
- - - 0.44 108 Yes No
Kimi-K2-Instruct
novita
cheapest
0.57 2.3 131072 1.18 37 Yes Yes
Kimi-K2-Instruct
nebius
fastest
0.5 2.4 131072 0.53 49 Yes Yes
Kimi-K2-Instruct
together
1 3 131072 0.89 41 Yes Yes
Kimi-K2-Instruct
fireworks-ai
0.6 2.5 131072 0.80 46 Yes No
Qwen2.5-7B-Instruct
together
0.3 0.3 32768 0.30 107 Yes Yes
Meta-Llama-3-8B-Instruct
groq
- - - - - - -
Meta-Llama-3-8B-Instruct
novita
0.04 0.04 8192 0.75 85 No No
Meta-Llama-3-8B-Instruct
together
- - - - - - -
Qwen3-VL-30B-A3B-Instruct
novita
0.2 0.7 131072 0.83 86 Yes Yes
SmolLM3-3B
hf-inference
- - - 0.22 86 Yes Yes
Qwen2.5-VL-7B-Instruct
hyperbolic
0.2 0.2 32768 0.63 103 No No
DeepSeek-V3.2-Exp
novita
0.27 0.41 163840 1.01 28 Yes Yes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
0.09 0.58 131072 1.16 31 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nebius
0.2 0.6 262144 0.57 23 Yes Yes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
0.6 1.2 - 0.28 480 Yes No
Qwen3-235B-A22B-Instruct-2507
nscale
- - - - - - -
Qwen3-235B-A22B-Instruct-2507
hyperbolic
2 2 262144 1.65 24 Yes No
Qwen3-235B-A22B-Instruct-2507
together
0.2 0.6 262144 0.59 56 Yes Yes
Qwen3-235B-A22B-Instruct-2507
fireworks-ai
0.22 0.88 262144 1.92 50 Yes No
Qwen3-235B-A22B-Instruct-2507
scaleway
- - - 0.41 80 Yes Yes
Llama-3.2-1B-Instruct
novita
- - 131000 0.88 206 No No
Llama-3.2-1B-Instruct
sambanova
- - - - - - -
Apertus-8B-Instruct-2509
publicai
- - - 1.14 106 No Yes
Llama-3.3-70B-Instruct
groq
0.59 0.79 131072 0.20 286 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
0.13 0.39 131072 0.61 28 Yes No
Llama-3.3-70B-Instruct
nebius
0.25 0.75 131072 0.41 121 Yes Yes
Llama-3.3-70B-Instruct
cerebras
fastest
0.85 1.2 - 0.35 997 Yes No
Llama-3.3-70B-Instruct
sambanova
0.6 1.2 131072 0.48 307 Yes Yes
Llama-3.3-70B-Instruct
nscale
- - - - - - -
Llama-3.3-70B-Instruct
hyperbolic
0.4 0.4 131072 0.87 136 No No
Llama-3.3-70B-Instruct
together
0.88 0.88 131072 1.30 101 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.43 136 No No
Llama-3.3-70B-Instruct
scaleway
- - - 0.68 35 Yes Yes
Qwen3-VL-235B-A22B-Thinking
novita
0.98 3.95 131072 1.35 39 No No
Qwen3-Next-80B-A3B-Instruct
novita
0.15 1.5 131072 0.69 123 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
0.3 0.3 262144 0.66 157 Yes No
Qwen3-Next-80B-A3B-Instruct
together
0.15 1.5 262144 0.71 149 Yes Yes
gpt-oss-safeguard-20b
groq
- - 131072 0.26 729 Yes No
DeepSeek-R1-0528-Qwen3-8B
novita
0.06 0.09 128000 0.79 65 No No
GLM-4.5-Air
novita
cheapest fastest
0.13 0.85 131072 0.62 80 Yes No
GLM-4.5-Air
nebius
0.2 1.2 131072 0.34 69 Yes Yes
GLM-4.5-Air
fireworks-ai
- - - - - - -
GLM-4.5-Air
zai-org
- - - 3.09 56 Yes No
Qwen3-30B-A3B-Instruct-2507
nebius
0.1 0.3 262144 0.47 73 Yes Yes
GLM-4.5V
novita
cheapest fastest
0.6 1.8 65536 1.66 49 Yes No
GLM-4.5V
zai-org
- - - 2.80 49 Yes No
gemma-3-27b-it
nebius
cheapest fastest
0.2 0.6 110000 0.52 76 No Yes
gemma-3-27b-it
scaleway
- - - 0.60 43 Yes No
Qwen3-VL-235B-A22B-Instruct
novita
0.3 1.5 131072 0.94 35 Yes Yes
Qwen3-32B
groq
0.29 0.59 131072 0.26 262 Yes No
Qwen3-32B
novita
0.1 0.45 40960 1.59 56 No No
Qwen3-32B
nebius
cheapest
0.1 0.3 40960 0.42 42 Yes Yes
Qwen3-32B
cerebras
fastest
0.4 0.8 - 0.31 786 No No
Qwen3-32B
sambanova
0.4 0.8 32768 2.83 189 Yes Yes
Qwen3-32B
nscale
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
groq
cheapest fastest
0.11 0.34 131072 0.39 343 Yes No
Llama-4-Scout-17B-16E-Instruct
novita
0.1 0.5 131072 0.88 22 No No
Llama-4-Scout-17B-16E-Instruct
sambanova
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
nscale
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
together
0.18 0.59 1048576 0.39 89 Yes Yes
Llama-4-Scout-17B-16E-Instruct
fireworks-ai
0.15 0.6 1048576 0.69 66 Yes No
DeepSeek-V3-0324
novita
0.27 1.12 163840 1.27 32 Yes No
DeepSeek-V3-0324
nebius
0.75 2.25 32768 0.84 147 No No
DeepSeek-V3-0324
sambanova
fastest
3 4.5 131072 0.78 160 Yes Yes
DeepSeek-V3-0324
hyperbolic
1.25 1.25 163840 1.14 54 No No
DeepSeek-V3-0324
together
1.25 1.25 131072 0.63 55 Yes Yes
DeepSeek-V3-0324
fireworks-ai
cheapest
0.9 0.9 163840 1.02 44 Yes No
DeepSeek-V3
novita
0.4 1.3 64000 1.43 28 Yes No
DeepSeek-V3
together
cheapest fastest
1.25 1.25 131072 0.65 54 Yes Yes
DeepSeek-V3
fireworks-ai
- - - - - - -
ERNIE-4.5-VL-424B-A47B-Base-PT
novita
0.42 1.25 123000 1.46 39 No No
GLM-4.5
novita
0.6 2.2 131072 0.66 23 Yes No
GLM-4.5
nebius
0.6 2.2 131072 0.37 28 Yes Yes
GLM-4.5
fireworks-ai
cheapest fastest
0.55 2.19 131072 1.05 79 Yes No
GLM-4.5
zai-org
- - - - - - -
gemma-2-2b-it
nebius
0.02 0.06 8192 0.49 150 No Yes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
0.29 1.2 262144 1.10 32 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
nebius
fastest
0.4 1.8 262144 0.49 65 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
cerebras
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
2 2 262144 2.43 50 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
2 2 262144 0.56 48 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
fireworks-ai
0.45 1.8 262144 0.74 52 No No
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest
0.2 0.6 131072 2.02 213 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova
fastest
0.63 1.8 131072 1.45 317 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
fireworks-ai
0.22 0.88 1048576 0.55 58 Yes No
DeepSeek-R1-Distill-Qwen-14B
novita
0.15 0.15 32768 0.98 52 No No
DeepSeek-R1-Distill-Qwen-14B
nscale
- - - - - - -
L3-70B-Euryale-v2.1
novita
1.48 1.48 8192 0.83 37 No No
Qwen3-235B-A22B
novita
0.2 0.8 40960 1.29 22 No No
Qwen3-235B-A22B
nscale
- - - - - - -
Qwen3-235B-A22B
together
0.2 0.6 40960 0.50 36 Yes Yes
Qwen3-235B-A22B
fireworks-ai
fastest
0.22 0.88 131072 1.00 78 Yes No
Qwen3-30B-A3B
novita
cheapest
0.09 0.45 40960 0.79 90 No No
Qwen3-30B-A3B
fireworks-ai
fastest
0.15 0.6 131072 0.77 136 Yes No
Qwen3-30B-A3B-Thinking-2507
nebius
0.1 0.3 262144 0.45 109 Yes Yes
Qwen2.5-Coder-32B-Instruct
nscale
- - - - - - -
Qwen2.5-Coder-32B-Instruct
hyperbolic
fastest
0.2 0.2 32768 1.03 77 No No
Qwen2.5-Coder-32B-Instruct
together
- - - - - - -
Qwen2.5-Coder-32B-Instruct
scaleway
- - - 0.61 39 Yes No
Qwen3-VL-30B-A3B-Thinking
novita
0.2 1 131072 1.41 87 Yes Yes
DeepSeek-V3.1-Terminus
novita
0.27 1 131072 1.08 25 Yes Yes
DeepSeek-V3.1
novita
cheapest
0.27 1 131072 1.05 27 Yes No
DeepSeek-V3.1
together
fastest
0.6 1.7 131072 0.51 81 No No
DeepSeek-V3.1
fireworks-ai
- - 163840 0.97 61 Yes No
Qwen3-Next-80B-A3B-Thinking
novita
0.15 1.5 131072 1.20 114 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
0.3 0.3 262144 0.59 174 Yes No
Qwen3-Next-80B-A3B-Thinking
together
0.15 1.5 262144 0.39 141 Yes Yes
NVIDIA-Nemotron-Nano-12B-v2
nebius
0.07 0.2 131072 0.47 82 No Yes
gemma-2-9b-it
groq
- - - - - - -
gemma-2-9b-it
nebius
0.03 0.09 8192 0.39 126 No Yes
ERNIE-4.5-VL-28B-A3B-PT
novita
0.14 0.56 30000 0.92 74 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
0.17 0.85 1048576 0.79 45 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
0.27 0.85 1048576 1.04 72 Yes Yes
GLM-4.5V-FP8
zai-org
- - - 2.93 55 Yes No
DeepSeek-R1-Distill-Llama-70B
groq
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
0.8 0.8 8192 2.79 29 No Yes
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
0.7 1.4 131072 0.86 195 No No
DeepSeek-R1-Distill-Llama-70B
nscale
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
scaleway
- - - 0.82 24 No Yes
Qwen2.5-72B-Instruct
novita
cheapest
0.38 0.4 32000 0.61 25 Yes No
Qwen2.5-72B-Instruct
hyperbolic
0.4 0.4 131072 1.58 56 Yes No
Qwen2.5-72B-Instruct
together
fastest
1.2 1.2 131072 0.39 87 Yes Yes
Qwen2.5-72B-Instruct
fireworks-ai
- - - - - - -
Qwen2.5-VL-72B-Instruct
nebius
0.25 0.75 32000 0.54 33 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
0.6 0.6 32768 0.59 43 No No
Llama-Guard-4-12B
groq
0.2 0.2 131072 0.30 6 No No
Arch-Router-1.5B
hf-inference
- - - 0.27 38 No Yes
ERNIE-4.5-21B-A3B-PT
novita
0.07 0.28 120000 1.10 78 No No
aya-expanse-32b
cohere
- - - 0.37 41 No No
c4ai-command-a-03-2025
cohere
- - - 0.38 35 Yes No
Baichuan-M2-32B
novita
0.07 0.07 131072 1.96 41 No Yes
Meta-Llama-3-70B-Instruct
groq
- - - - - - -
Meta-Llama-3-70B-Instruct
novita
0.51 0.74 8192 1.09 25 No Yes
Meta-Llama-3-70B-Instruct
hyperbolic
cheapest
0.4 0.4 8192 0.88 91 No No
Meta-Llama-3-70B-Instruct
together
fastest
0.88 0.88 8192 0.33 109 No Yes
DeepSeek-R1-0528
novita
0.7 2.5 163840 1.12 27 Yes No
DeepSeek-R1-0528
nebius
cheapest
0.8 2.4 163840 0.59 37 Yes Yes
DeepSeek-R1-0528
sambanova
fastest
5 7 131072 2.98 149 Yes No
DeepSeek-R1-0528
hyperbolic
3 3 163840 1.70 38 No No
DeepSeek-R1-0528
together
3 7 163840 1.20 33 No Yes
DeepSeek-R1-0528
fireworks-ai
3 8 163840 1.59 32 Yes No
QwQ-32B
groq
- - - - - - -
QwQ-32B
nebius
- - - - - - -
QwQ-32B
sambanova
- - - - - - -
QwQ-32B
nscale
- - - - - - -
QwQ-32B
hyperbolic
0.4 0.4 131072 1.31 59 No No
QwQ-32B
fireworks-ai
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
novita
0.3 3 131072 0.87 27 No No
Qwen3-235B-A22B-Thinking-2507
cerebras
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
fireworks-ai
cheapest fastest
0.22 0.88 262144 0.97 63 Yes No
Qwen2.5-VL-32B-Instruct
fireworks-ai
0.22 0.88 128000 0.58 42 No No
Llama-3.1-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.51 123 No No
AFM-4.5B
together
0.048 0.15 65536 0.70 179 No Yes
command-a-translate-08-2025
cohere
- - - 0.31 62 Yes No
c4ai-command-r7b-arabic-02-2025
cohere
- - - 0.31 30 Yes No
GLM-4.6-FP8
zai-org
- - - 3.76 38 Yes No
ERNIE-4.5-0.3B-PT
novita
- - 120000 1.02 104 No No
MiniMax-M1-80k
novita
0.55 2.2 1000000 1.30 60 Yes No
L3-8B-Stheno-v3.2
novita
0.05 0.05 8192 0.81 55 No No
Apertus-70B-Instruct-2509
publicai
- - - 1.29 39 Yes Yes
DeepSeek-R1-Distill-Qwen-32B
novita
0.3 0.3 64000 0.54 95 No Yes
DeepSeek-R1-Distill-Qwen-32B
nscale
- - - - - - -
GLM-4.1V-9B-Thinking
novita
0.035 0.138 65536 0.74 70 No No
GLM-4-32B-0414
novita
0.55 1.66 32000 0.93 37 No Yes
DeepSeek-Prover-V2-671B
novita
0.7 2.5 160000 0.65 37 No No
command-a-vision-07-2025
cohere
- - - 0.34 45 No No
Mixtral-8x22B-Instruct-v0.1
nscale
- - - - - - -
Mixtral-8x22B-Instruct-v0.1
together
- - - - - - -
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
1.2 1.2 65536 0.47 68 No No
Llama-3.1-405B-Instruct
sambanova
- - - - - - -
Llama-3.1-405B-Instruct
fireworks-ai
3 3 131072 0.55 64 Yes No
Qwen3-Coder-480B-A35B-Instruct-FP8
together
2 2 262144 0.60 47 Yes Yes
GLM-4.5-Air-FP8
together
0.2 1.1 131072 0.32 100 Yes Yes
ERNIE-4.5-300B-A47B-Base-PT
novita
0.28 1.1 123000 1.01 29 No Yes
command-a-reasoning-08-2025
cohere
- - - 0.25 88 Yes No
Hermes-2-Pro-Llama-3-8B
novita
0.14 0.14 8192 0.62 115 No No
cogito-v2-preview-deepseek-671B-MoE
together
1.25 1.25 163840 0.40 42 No Yes
cogito-v2-preview-llama-405B
together
3.5 3.5 32768 1.12 26 Yes Yes
cogito-v2-preview-llama-109B-MoE
together
0.18 0.59 32767 1.40 77 Yes Yes
cogito-v2-preview-llama-70B
together
0.88 0.88 32768 0.91 52 Yes Yes
aya-vision-32b
cohere
- - - 0.52 55 No No
c4ai-command-r-08-2024
cohere
- - - 0.31 58 Yes No
c4ai-command-r7b-12-2024
cohere
- - - 0.32 92 Yes No
Qwen2.5-Coder-7B
nebius
0.03 0.09 32768 0.31 185 No Yes
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova
0.6 1.2 131072 2.23 182 No Yes
Hermes-4-405B
nebius
1 3 131072 0.45 37 No No
Hermes-4-70B
nebius
0.13 0.4 131072 0.47 76 No No
Hermes-3-Llama-3.1-70B
hyperbolic
0.4 0.4 12288 0.41 30 No No
marin-8b-instruct
together
0.18 0.18 4096 0.23 180 No Yes
WizardLM-2-8x22B
novita
0.62 0.62 65535 0.39 40 No No
Gemma-SEA-LION-v4-27B-IT
publicai
- - - 1.82 48 No Yes
Llama-3_1-Nemotron-Ultra-253B-v1
nebius
0.6 1.8 131072 0.43 39 No Yes
Dobby-Unhinged-Llama-3.3-70B
fireworks-ai
0.9 0.9 131072 0.43 51 No No
L3-8B-Lunaris-v1
novita
0.05 0.05 8192 0.81 70 No No
Qwen3-235B-A22B-FP8
together
0.2 0.6 40960 0.54 37 Yes Yes