Hugging Face's logo

Inference Providers

·

Metrics for top trending models

Browse all models Learn more
Qwen3.5-35B-A3B
novita
$0.25 $2.00 262,144 1.05 85 Yes No
Qwen3.5-27B
novita
$0.30 $2.40 262,144 0.97 67 Yes No
Qwen3.5-397B-A17B
novita
cheapest fastest
$0.60 $3.60 262,144 0.99 51 Yes No
Qwen3.5-397B-A17B
together
$0.60 $3.60 262,144 0.37 19 Yes No
GLM-5
novita
cheapest
$1.00 $3.20 202,800 1.17 46 Yes No
GLM-5
together
fastest
$1.00 $3.20 202,752 0.66 93 Yes Yes
GLM-5
fireworks-ai
- - 202,752 1.89 63 Yes No
GLM-5
zai-org
- - - 2.97 45 Yes No
MiniMax-M2.5
novita
cheapest
$0.30 $1.20 204,800 1.70 21 No No
MiniMax-M2.5
fireworks-ai
fastest
- - - 0.68 138 Yes No
Qwen3.5-122B-A10B
novita
$0.40 $3.20 262,144 0.95 122 Yes No
Qwen3-Coder-Next
novita
$0.20 $1.50 262,144 0.81 152 Yes Yes
Kimi-K2.5
novita
$0.60 $3.00 262,144 0.89 64 Yes No
Kimi-K2.5
together
cheapest
$0.50 $2.80 262,144 2.18 30 Yes Yes
Kimi-K2.5
fireworks-ai
fastest
- - 262,144 1.02 82 Yes No
Llama-3.1-8B-Instruct
novita
cheapest
$0.02 $0.05 16,384 0.63 70 No No
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10 $0.10 - 0.21 1,065 No No
Llama-3.1-8B-Instruct
sambanova
$0.10 $0.20 16,384 2.94 189 Yes Yes
Llama-3.1-8B-Instruct
nscale
$0.06 $0.06 131,072 0.80 59 No Yes
Llama-3.1-8B-Instruct
scaleway
- - - 0.35 110 Yes Yes
Llama-3.1-8B-Instruct
ovhcloud
$0.11 $0.11 131,072 0.24 45 Yes Yes
gpt-oss-20b
groq
fastest
$0.10 $0.50 131,072 0.11 788 Yes No
gpt-oss-20b
novita
$0.04 $0.15 131,072 0.41 118 No Yes
gpt-oss-20b
nscale
$0.05 $0.20 131,072 0.77 115 Yes Yes
gpt-oss-20b
hyperbolic
cheapest
$0.10 $0.10 131,072 0.54 128 Yes No
gpt-oss-20b
together
$0.05 $0.20 131,072 0.21 121 Yes Yes
gpt-oss-20b
fireworks-ai
$0.05 $0.20 131,072 0.29 148 Yes No
gpt-oss-20b
ovhcloud
$0.05 $0.18 131,072 0.29 90 Yes Yes
DeepSeek-R1
novita
$0.70 $2.50 64,000 1.04 39 Yes No
DeepSeek-R1
sambanova
- - - - - - -
DeepSeek-R1
hyperbolic
cheapest
$2.00 $2.00 163,840 1.60 79 No No
DeepSeek-R1
together
fastest
$3.00 $7.00 163,840 0.36 103 No No
GLM-4.7-Flash
novita
cheapest fastest
$0.07 $0.40 200,000 0.85 104 Yes No
GLM-4.7-Flash
zai-org
- - - 2.10 61 No No
gpt-oss-120b
groq
$0.15 $0.75 131,072 0.09 436 Yes No
gpt-oss-120b
novita
cheapest
$0.05 $0.25 131,072 0.51 63 Yes No
gpt-oss-120b
cerebras
fastest
$0.25 $0.69 - 0.24 1,155 Yes No
gpt-oss-120b
sambanova
$0.22 $0.59 131,072 0.37 642 Yes No
gpt-oss-120b
nscale
$0.10 $0.40 131,072 0.67 87 Yes No
gpt-oss-120b
hyperbolic
$0.30 $0.30 131,072 0.50 378 Yes No
gpt-oss-120b
together
$0.15 $0.60 131,072 0.32 141 Yes Yes
gpt-oss-120b
fireworks-ai
$0.15 $0.60 131,072 0.32 116 Yes No
gpt-oss-120b
scaleway
- - - 0.32 152 Yes Yes
gpt-oss-120b
ovhcloud
$0.09 $0.47 131,072 0.29 133 Yes Yes
Qwen3-VL-8B-Instruct
novita
cheapest fastest
$0.08 $0.50 131,072 0.77 57 Yes No
Qwen3-VL-8B-Instruct
together
$0.18 $0.68 262,144 0.20 51 No Yes
Qwen3-8B
nscale
cheapest
$0.07 $0.18 40,960 0.70 55 Yes No
Qwen3-8B
fireworks-ai
fastest
- - 40,960 0.28 144 Yes No
Qwen2.5-7B-Instruct
together
$0.30 $0.30 32,768 0.19 121 Yes Yes
Qwen3-4B-Instruct-2507
nscale
$0.01 $0.03 262,144 0.79 87 Yes No
DeepSeek-V3.2
novita
cheapest
$0.27 $0.40 163,840 1.13 30 Yes Yes
DeepSeek-V3.2
fireworks-ai
fastest
- - 163,840 1.37 65 No No
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11 $0.34 131,072 0.97 286 Yes No
Llama-4-Scout-17B-16E-Instruct
novita
$0.18 $0.59 131,072 0.35 126 No No
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09 $0.29 890,000 0.86 33 Yes Yes
Qwen3-Coder-Next-FP8
together
$0.50 $1.20 262,144 2.59 114 Yes Yes
tiny-aya-global
cohere
- - - 0.27 121 No No
Qwen3-Coder-30B-A3B-Instruct
scaleway
- - - 0.40 57 Yes No
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest fastest
$0.07 $0.26 262,144 0.30 73 Yes Yes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20 $0.70 131,072 0.80 120 Yes Yes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
- - 262,144 0.33 128 Yes No
gemma-3-27b-it
scaleway
- - - 0.43 48 Yes No
Qwen2.5-VL-7B-Instruct
hyperbolic
$0.20 $0.20 32,768 1.11 103 No No
Meta-Llama-3-8B-Instruct
novita
$0.04 $0.04 8,192 0.69 85 No No
Qwen2.5-Coder-7B-Instruct
nscale
$0.01 $0.03 131,072 0.77 62 No Yes
Llama-3.2-1B-Instruct
novita
- - 131,000 0.58 192 No No
DeepSeek-R1-Distill-Qwen-7B
nscale
$0.15 $0.15 131,072 0.78 66 No No
Qwen3-4B-Thinking-2507
nscale
$0.01 $0.03 262,144 0.81 95 Yes No
rnj-1-instruct
together
$0.15 $0.15 32,768 0.95 115 Yes Yes
MiMo-V2-Flash
novita
$0.10 $0.30 262,144 3.12 73 Yes No
DeepSeek-R1-Distill-Qwen-1.5B
nscale
$0.10 $0.10 131,072 0.77 142 No Yes
DeepSeek-OCR
novita
$0.03 $0.03 8,192 1.11 250 No No
Molmo2-8B
publicai
- - - 2.76 36 No Yes
MiniMax-M2.1
novita
$0.30 $1.20 204,800 2.29 33 Yes No
MiniMax-M2.1
fireworks-ai
- - - - - - -
Qwen3-Next-80B-A3B-Instruct
novita
cheapest
$0.15 $1.50 131,072 0.91 80 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic
- - - - - - -
Qwen3-Next-80B-A3B-Instruct
together
fastest
$0.15 $1.50 262,144 0.35 126 Yes Yes
Kimi-K2-Instruct-0905
groq
fastest
- - 262,144 0.21 193 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
$0.60 $2.50 262,144 0.98 33 Yes Yes
Kimi-K2-Instruct-0905
together
- - - - - - -
Kimi-K2-Instruct-0905
fireworks-ai
- - 262,144 0.92 57 Yes No
Qwen3-14B
nscale
$0.07 $0.20 40,960 0.84 52 Yes No
DeepSeek-V3
novita
$0.40 $1.30 64,000 1.24 38 Yes No
DeepSeek-V3
together
cheapest fastest
$1.25 $1.25 131,072 0.27 47 Yes Yes
gemma-3n-E4B-it
together
$0.02 $0.04 32,768 0.31 52 No Yes
Qwen3-235B-A22B
novita
$0.20 $0.80 40,960 0.68 9 No No
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20 $0.60 32,000 1.06 23 Yes Yes
GLM-4.7
novita
cheapest fastest
$0.60 $2.20 204,800 0.81 98 Yes No
GLM-4.7
fireworks-ai
- - 202,752 1.89 27 Yes No
GLM-4.7
zai-org
- - - 1.81 87 Yes No
Trinity-Mini
together
$0.05 $0.15 128,000 0.17 129 Yes Yes
DeepSeek-V3.2-Exp
novita
$0.27 $0.41 163,840 1.02 26 Yes Yes
GLM-4.6V-Flash
novita
cheapest
$0.30 $0.90 131,072 1.00 46 Yes No
GLM-4.6V-Flash
zai-org
fastest
- - - 1.86 86 Yes No
DeepSeek-R1-Distill-Llama-8B
nscale
$0.05 $0.05 131,072 0.84 56 No No
DeepSeek-R1-Distill-Llama-70B
novita
$0.80 $0.80 8,192 0.41 63 No No
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
$0.70 $1.40 131,072 3.91 132 No No
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75 $0.75 131,072 0.86 16 No Yes
DeepSeek-R1-Distill-Llama-70B
scaleway
- - - 0.50 38 No Yes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30 $1.30 262,144 0.83 56 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
$2.00 $2.00 262,144 0.72 58 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00 $2.00 262,144 0.36 60 Yes Yes
DeepSeek-R1-0528
novita
$0.70 $2.50 163,840 1.17 42 Yes No
DeepSeek-R1-0528
sambanova
- - - - - - -
DeepSeek-R1-0528
hyperbolic
$3.00 $3.00 163,840 1.33 80 No No
DeepSeek-R1-0528
together
cheapest fastest
$0.00 $0.00 163,840 0.84 95 No Yes
c4ai-command-a-03-2025
cohere
- - - 0.56 39 Yes No
QwQ-32B
nscale
$0.18 $0.20 131,072 0.95 28 Yes Yes
Qwen3-32B
groq
fastest
$0.29 $0.59 131,072 0.22 290 Yes No
Qwen3-32B
novita
$0.10 $0.45 40,960 2.66 9 No No
Qwen3-32B
sambanova
$0.40 $0.80 32,768 2.87 186 Yes Yes
Qwen3-32B
nscale
cheapest
$0.08 $0.25 40,960 0.70 28 Yes No
Qwen3-32B
ovhcloud
$0.09 $0.25 32,768 0.35 32 Yes Yes
GLM-4.7-FP8
together
cheapest
$0.45 $2.00 202,752 0.80 38 Yes Yes
GLM-4.7-FP8
zai-org
fastest
- - - 1.82 93 Yes No
GLM-4.6V
zai-org
- - - 3.02 41 Yes No
GLM-4.5-Air
novita
cheapest fastest
$0.13 $0.85 131,072 0.64 76 Yes No
GLM-4.5-Air
zai-org
- - - 2.42 73 Yes No
Olmo-3-7B-Instruct
publicai
$0.10 $0.20 - - - Yes No
Olmo-3.1-32B-Instruct
publicai
$0.20 $0.60 - 1.50 37 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest fastest
$0.20 $0.60 131,072 0.17 491 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova
$0.63 $1.80 131,072 1.05 366 Yes Yes
tiny-aya-fire
cohere
- - - 1.15 111 No No
Qwen3-Next-80B-A3B-Thinking
novita
$0.15 $1.50 131,072 0.90 159 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30 $0.30 262,144 0.49 191 Yes No
Qwen3-30B-A3B
novita
$0.09 $0.45 40,960 0.90 107 Yes No
Qwen3-VL-235B-A22B-Instruct
novita
$0.30 $1.50 131,072 0.75 33 Yes Yes
L3-8B-Stheno-v3.2
novita
$0.05 $0.05 8,192 0.92 36 No No
Qwen3-VL-235B-A22B-Thinking
novita
$0.98 $3.95 131,072 1.18 35 Yes No
Kimi-K2-Thinking
novita
cheapest
$0.60 $2.50 262,144 0.86 32 No No
Kimi-K2-Thinking
together
- - - - - - -
Kimi-K2-Thinking
fireworks-ai
fastest
- - - 0.57 78 Yes No
Arch-Router-1.5B
hf-inference
- - - 0.11 69 No Yes
aya-expanse-32b
cohere
- - - 0.19 43 No No
Kimi-K2-Instruct
novita
$0.57 $2.30 131,072 1.02 50 Yes No
Kimi-K2-Instruct
together
- - - - - - -
command-a-reasoning-08-2025
cohere
- - - 0.28 80 Yes No
Llama-3.3-70B-Instruct
groq
fastest
$0.59 $0.79 131,072 0.32 289 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
$0.14 $0.40 131,072 0.75 45 Yes No
Llama-3.3-70B-Instruct
sambanova
$0.60 $1.20 131,072 1.28 258 Yes Yes
Llama-3.3-70B-Instruct
nscale
$0.40 $0.40 131,072 0.77 17 No Yes
Llama-3.3-70B-Instruct
hyperbolic
$0.40 $0.40 131,072 0.69 68 Yes No
Llama-3.3-70B-Instruct
together
$0.88 $0.88 131,072 0.56 77 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai
$0.90 $0.90 131,072 0.33 129 No No
Llama-3.3-70B-Instruct
scaleway
- - - 0.33 82 Yes Yes
Llama-3.3-70B-Instruct
ovhcloud
$0.74 $0.74 131,072 0.36 40 Yes Yes
GLM-4.6
novita
cheapest fastest
$0.55 $2.20 204,800 0.63 92 Yes No
GLM-4.6
together
$0.60 $2.20 202,752 0.79 39 Yes Yes
GLM-4.6
zai-org
- - - 1.84 65 Yes No
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20 $1.00 131,072 0.90 110 Yes No
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
- - 262,144 0.60 131 Yes No
ERNIE-4.5-VL-28B-A3B-PT
novita
$0.14 $0.56 30,000 0.89 75 No No
EuroLLM-22B-Instruct-2512
publicai
$0.10 $0.20 - - - No No
ERNIE-4.5-300B-A47B-Base-PT
novita
$0.28 $1.10 123,000 1.19 23 No Yes
DeepSeek-Prover-V2-671B
novita
$0.70 $2.50 160,000 1.24 7 No No
Qwen3-Coder-480B-A35B-Instruct-FP8
together
$2.00 $2.00 262,144 0.43 66 Yes Yes
Qwen2.5-72B-Instruct
novita
$0.38 $0.40 32,000 0.88 24 Yes No
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06 $0.20 131,072 0.80 28 No Yes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
- - - 0.39 57 Yes No
Hermes-2-Pro-Llama-3-8B
novita
$0.14 $0.14 8,192 0.67 99 No No
Apriel-1.6-15b-Thinker
together
$0.00 $0.00 131,072 0.19 75 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest fastest
$0.27 $0.85 1,048,576 0.30 102 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together
$0.27 $0.85 1,048,576 0.26 98 Yes Yes
L3-70B-Euryale-v2.1
novita
$1.48 $1.48 8,192 0.70 38 No No
Llama-3.1-70B-Instruct
scaleway
- - - 0.32 82 Yes Yes
L3-8B-Lunaris-v1
novita
$0.05 $0.05 8,192 0.68 34 No No
AutoGLM-Phone-9B-Multilingual
novita
$0.04 $0.14 65,536 0.69 67 No No
DeepSeek-R1-Distill-Qwen-32B
nscale
$0.30 $0.30 131,072 0.80 27 No Yes
MiniMax-M2
novita
$0.30 $1.20 204,800 1.18 41 Yes No
DeepSeek-V3.1-Terminus
novita
$0.27 $1.00 131,072 1.05 39 Yes Yes
GLM-4.5V
novita
cheapest fastest
$0.60 $1.80 65,536 0.70 44 Yes No
GLM-4.5V
zai-org
- - - 2.55 30 Yes No
Qwen2.5-Coder-3B-Instruct
nscale
$0.01 $0.03 32,768 0.81 89 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
$0.60 $0.60 32,768 0.44 44 No No
Qwen2.5-VL-72B-Instruct
ovhcloud
$1.01 $1.01 32,768 0.47 34 No Yes
Apertus-8B-Instruct-2509
publicai
$0.10 $0.20 - 1.36 89 No Yes
Qwen3-235B-A22B-Thinking-2507
novita
$0.30 $3.00 131,072 0.67 64 Yes No
DictaLM-3.0-24B-Thinking
publicai
$0.20 $0.40 - 2.60 40 Yes Yes
c4ai-command-r7b-12-2024
cohere
- - - 0.19 115 Yes No
WizardLM-2-8x22B
novita
$0.62 $0.62 65,535 2.17 7 No No
DeepSeek-V3.1
novita
cheapest
$0.27 $1.00 131,072 1.26 37 Yes Yes
DeepSeek-V3.1
together
$0.60 $1.70 131,072 1.68 47 Yes Yes
DeepSeek-V3.1
fireworks-ai
fastest
- - 163,840 0.67 57 Yes No
cogito-671b-v2.1-FP8
together
$1.25 $1.25 163,840 0.27 76 No No
aya-vision-32b
cohere
- - - 0.37 37 No No
Llama-Guard-4-12B
groq
$0.20 $0.20 131,072 0.18 11 No No
gpt-oss-safeguard-20b
groq
- - 131,072 0.35 730 Yes No
cogito-671b-v2.1
together
cheapest fastest
$1.25 $1.25 163,840 0.31 77 No No
cogito-671b-v2.1
fireworks-ai
- - 163,840 0.41 43 No No
GLM-4.6V-FP8
zai-org
- - - 3.20 38 Yes No
GLM-4.5V-FP8
zai-org
- - - 2.84 24 Yes No
GLM-4.6-FP8
zai-org
- - - 1.79 73 Yes No
GLM-4.5
novita
cheapest
$0.60 $2.20 131,072 0.89 53 Yes No
GLM-4.5
zai-org
fastest
- - - 2.31 56 Yes No
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09 $0.58 131,072 0.71 33 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nscale
$0.20 $0.60 32,768 0.87 23 Yes Yes
Qwen3-235B-A22B-Instruct-2507
hyperbolic
$2.00 $2.00 262,144 0.86 42 Yes No
Qwen3-235B-A22B-Instruct-2507
together
$0.20 $0.60 262,144 0.49 33 Yes Yes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
- - - 0.33 88 Yes Yes
DeepSeek-V3-0324
novita
cheapest
$0.27 $1.12 163,840 0.84 37 Yes Yes
DeepSeek-V3-0324
sambanova
fastest
$3.00 $4.50 131,072 1.02 171 No Yes
DeepSeek-V3-0324
hyperbolic
$1.25 $1.25 163,840 0.54 51 Yes No
DeepSeek-V3-0324
together
$1.25 $1.25 131,072 0.29 48 Yes Yes
c4ai-command-r-08-2024
cohere
- - - 0.20 48 No No
command-a-translate-08-2025
cohere
- - - 0.31 65 Yes No
Mixtral-8x22B-Instruct-v0.1
nscale
$1.20 $1.20 65,536 0.91 20 No Yes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
- - - - - - -
tiny-aya-earth
cohere
- - - 0.31 121 No No
tiny-aya-water
cohere
- - - 0.37 120 No No
Apertus-70B-Instruct-2509
publicai
$0.82 $2.92 - 1.81 49 No Yes
Gemma-SEA-LION-v4-27B-IT
publicai
$0.20 $0.40 - 3.06 40 No Yes
Qwen-SEA-LION-v4-32B-IT
publicai
$0.25 $0.50 - 1.98 39 Yes Yes
Olmo-3.1-32B-Think
publicai
$0.15 $0.50 - 3.10 63 No No
GLM-4.5-Air-FP8
together
$0.20 $1.10 131,072 3.21 103 Yes Yes
ERNIE-4.5-VL-424B-A47B-Base-PT
novita
$0.42 $1.25 123,000 1.24 43 No No
ERNIE-4.5-21B-A3B-PT
novita
$0.07 $0.28 120,000 0.93 69 No No
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova
$0.60 $1.20 131,072 3.44 140 No Yes
MiniMax-M1-80k
novita
$0.55 $2.20 1,000,000 2.11 38 Yes No
command-a-vision-07-2025
cohere
- - - 0.21 39 No No
GLM-4-32B-0414
novita
$0.55 $1.66 32,000 1.05 48 No No
c4ai-command-r7b-arabic-02-2025
cohere
- - - 0.23 76 Yes No
Meta-Llama-3-70B-Instruct
novita
$0.51 $0.74 8,192 0.69 29 No Yes