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 1.44 38 Yes No
Kimi-K2-Thinking
together
fastest
1.2 4 262144 0.36 73 Yes Yes
DeepSeek-OCR
novita
0.03 0.03 8192 0.91 169 No Yes
Llama-3.1-8B-Instruct
novita
cheapest
0.02 0.05 16384 0.70 80 No No
Llama-3.1-8B-Instruct
nebius
0.03 0.09 131072 0.45 177 No Yes
Llama-3.1-8B-Instruct
cerebras
fastest
0.1 0.1 - 0.32 1293 No No
Llama-3.1-8B-Instruct
sambanova
0.1 0.2 16384 0.74 538 Yes Yes
Llama-3.1-8B-Instruct
nscale
0.06 0.06 131072 0.81 60 No Yes
Llama-3.1-8B-Instruct
fireworks-ai
0.2 0.2 131072 0.30 248 No No
Llama-3.1-8B-Instruct
scaleway
- - - 0.31 94 Yes Yes
Llama-3.1-8B-Instruct
ovhcloud
- - - 0.33 42 Yes Yes
gpt-oss-20b
groq
fastest
0.1 0.5 131072 0.10 852 Yes No
gpt-oss-20b
novita
0.04 0.15 131072 0.98 107 No Yes
gpt-oss-20b
nebius
0.05 0.2 131072 0.34 177 Yes Yes
gpt-oss-20b
nscale
0.05 0.2 131072 1.21 61 Yes Yes
gpt-oss-20b
hyperbolic
cheapest
0.1 0.1 131072 0.52 163 No No
gpt-oss-20b
together
0.05 0.2 131072 0.21 166 Yes Yes
gpt-oss-20b
fireworks-ai
0.05 0.2 131072 0.41 119 Yes No
gpt-oss-20b
ovhcloud
- - - 0.38 96 Yes Yes
MiniMax-M2
novita
0.3 1.2 204800 0.91 60 No No
GLM-4.6
novita
cheapest
0.6 2.2 204800 0.64 37 Yes No
GLM-4.6
cerebras
fastest
- - - 0.36 323 Yes No
GLM-4.6
zai-org
- - - 2.72 57 Yes No
DeepSeek-V3.2-Exp
novita
0.27 0.41 163840 0.95 30 Yes Yes
gpt-oss-120b
groq
0.15 0.75 131072 0.11 435 Yes No
gpt-oss-120b
novita
cheapest
0.05 0.25 131072 0.60 153 No Yes
gpt-oss-120b
nebius
0.15 0.6 131072 0.39 45 Yes Yes
gpt-oss-120b
cerebras
fastest
0.25 0.69 - 0.21 1153 Yes No
gpt-oss-120b
sambanova
0.22 0.59 131072 0.87 415 Yes Yes
gpt-oss-120b
nscale
0.1 0.4 131072 0.84 95 Yes Yes
gpt-oss-120b
hyperbolic
0.3 0.3 131072 0.70 274 Yes No
gpt-oss-120b
together
0.15 0.6 131072 0.34 96 No Yes
gpt-oss-120b
fireworks-ai
0.15 0.6 131072 0.54 96 Yes No
gpt-oss-120b
scaleway
- - - 0.56 119 Yes Yes
gpt-oss-120b
ovhcloud
- - - 0.35 109 Yes Yes
cogito-671b-v2.1
together
cheapest fastest
1.25 1.25 163840 0.61 67 No Yes
cogito-671b-v2.1
fireworks-ai
- - 163840 1.75 16 Yes No
Qwen3-VL-8B-Instruct
novita
0.08 0.5 131072 0.56 70 Yes No
DeepSeek-R1
novita
0.7 2.5 64000 0.65 27 Yes No
DeepSeek-R1
sambanova
fastest
- - - 0.81 170 Yes Yes
DeepSeek-R1
hyperbolic
cheapest
2 2 163840 0.81 42 No No
DeepSeek-R1
together
3 7 163840 0.65 38 No Yes
DeepSeek-R1
fireworks-ai
- - - - - - -
Qwen2.5-7B-Instruct
together
0.3 0.3 32768 0.24 143 Yes Yes
gemma-3-27b-it
nebius
cheapest fastest
0.2 0.6 110000 0.21 60 No Yes
gemma-3-27b-it
scaleway
- - - 0.51 43 Yes No
Qwen3-8B
nscale
0.07 0.18 40960 0.92 57 Yes No
Qwen3-VL-30B-A3B-Instruct
novita
0.2 0.7 131072 1.01 58 Yes Yes
Qwen3-4B-Instruct-2507
nscale
0.01 0.03 262144 1.23 27 Yes No
Qwen2.5-VL-7B-Instruct
hyperbolic
0.2 0.2 32768 0.76 97 No No
Qwen3-Next-80B-A3B-Instruct
novita
0.15 1.5 131072 0.70 129 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
0.3 0.3 262144 0.51 164 Yes No
Qwen3-Next-80B-A3B-Instruct
together
0.15 1.5 262144 0.71 150 Yes Yes
Llama-3.2-1B-Instruct
novita
- - 131000 0.64 215 No No
Llama-3.2-1B-Instruct
sambanova
- - - - - - -
Llama-3.2-3B-Instruct
novita
cheapest
0.03 0.05 32768 0.50 122 Yes No
Llama-3.2-3B-Instruct
sambanova
- - - - - - -
Llama-3.2-3B-Instruct
hyperbolic
0.1 0.1 131072 0.62 140 No No
Llama-3.2-3B-Instruct
together
fastest
0.06 0.06 131072 0.36 151 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
nebius
cheapest
0.1 0.3 262144 0.38 49 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
fireworks-ai
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
scaleway
- - - 0.48 81 Yes No
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
fastest
- - - 0.52 111 Yes Yes
Kimi-K2-Instruct-0905
groq
fastest
- - 262144 0.18 204 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
0.6 2.5 262144 0.52 35 Yes No
Kimi-K2-Instruct-0905
together
1 3 262144 0.55 30 Yes Yes
Qwen3-30B-A3B-Instruct-2507
nebius
0.1 0.3 262144 0.23 108 Yes Yes
Meta-Llama-3-8B-Instruct
groq
- - - - - - -
Meta-Llama-3-8B-Instruct
novita
0.04 0.04 8192 0.73 84 No No
Meta-Llama-3-8B-Instruct
together
- - - - - - -
Qwen3-32B
groq
0.29 0.59 131072 0.23 261 Yes No
Qwen3-32B
novita
0.1 0.45 40960 0.72 39 No No
Qwen3-32B
nebius
0.1 0.3 40960 0.33 47 Yes Yes
Qwen3-32B
cerebras
fastest
0.4 0.8 - 0.25 976 No No
Qwen3-32B
sambanova
0.4 0.8 32768 2.72 190 Yes Yes
Qwen3-32B
nscale
cheapest
0.08 0.25 40960 0.88 25 Yes Yes
Qwen3-32B
ovhcloud
- - - 0.49 42 Yes Yes
Kimi-K2-Instruct
novita
cheapest
0.57 2.3 131072 0.83 30 Yes Yes
Kimi-K2-Instruct
nebius
fastest
0.5 2.4 131072 0.38 50 Yes Yes
Kimi-K2-Instruct
together
1 3 131072 0.62 49 Yes Yes
Kimi-K2-Instruct
fireworks-ai
0.6 2.5 131072 1.11 43 Yes No
DeepSeek-R1-Distill-Qwen-1.5B
nscale
0.1 0.1 131072 0.83 140 No No
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
0.29 1.2 262144 0.87 41 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
nebius
fastest
0.4 1.8 262144 0.32 57 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
cerebras
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
2 2 262144 1.03 49 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
2 2 262144 0.41 43 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
fireworks-ai
0.45 1.8 262144 2.06 44 Yes No
SmolLM3-3B
hf-inference
- - - 0.15 87 Yes Yes
Llama-3.3-70B-Instruct
groq
0.59 0.79 131072 0.13 267 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
0.13 0.39 131072 0.50 35 Yes No
Llama-3.3-70B-Instruct
nebius
0.25 0.75 131072 0.35 130 Yes Yes
Llama-3.3-70B-Instruct
cerebras
fastest
0.85 1.2 - 0.23 1171 Yes No
Llama-3.3-70B-Instruct
sambanova
0.6 1.2 131072 0.36 333 Yes Yes
Llama-3.3-70B-Instruct
nscale
0.4 0.4 131072 0.99 16 No Yes
Llama-3.3-70B-Instruct
hyperbolic
0.4 0.4 131072 1.95 99 No No
Llama-3.3-70B-Instruct
together
0.88 0.88 131072 0.63 121 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.42 144 No No
Llama-3.3-70B-Instruct
scaleway
- - - 0.74 36 Yes Yes
Llama-3.3-70B-Instruct
ovhcloud
- - - 0.39 37 Yes Yes
cogito-671b-v2.1-FP8
together
1.25 1.25 163840 0.69 67 Yes Yes
Qwen3-4B-Thinking-2507
nscale
0.01 0.03 262144 1.06 93 Yes No
gemma-2-2b-it
nebius
0.02 0.06 8192 0.30 157 No Yes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
0.09 0.58 131072 0.74 25 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nebius
0.2 0.6 262144 0.39 69 Yes Yes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
0.6 1.2 - 0.22 520 Yes No
Qwen3-235B-A22B-Instruct-2507
nscale
0.2 0.6 32768 0.94 24 Yes Yes
Qwen3-235B-A22B-Instruct-2507
hyperbolic
2 2 262144 0.92 41 Yes No
Qwen3-235B-A22B-Instruct-2507
together
0.2 0.6 262144 0.35 55 Yes Yes
Qwen3-235B-A22B-Instruct-2507
fireworks-ai
0.22 0.88 262144 0.63 66 Yes No
Qwen3-235B-A22B-Instruct-2507
scaleway
- - - 0.42 68 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest
0.2 0.6 131072 3.08 177 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova
fastest
0.63 1.8 131072 1.79 293 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
fireworks-ai
0.22 0.88 1048576 0.51 71 Yes No
Llama-3.1-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.38 173 No No
GLM-4.5-Air
novita
cheapest fastest
0.13 0.85 131072 0.51 82 Yes No
GLM-4.5-Air
nebius
0.2 1.2 131072 0.29 54 Yes Yes
GLM-4.5-Air
fireworks-ai
- - - - - - -
GLM-4.5-Air
zai-org
- - - 2.50 69 Yes No
Qwen3-30B-A3B
novita
cheapest
0.09 0.45 40960 0.85 114 No No
Qwen3-30B-A3B
fireworks-ai
fastest
0.15 0.6 131072 0.63 165 Yes No
DeepSeek-V3.1-Terminus
novita
0.27 1 131072 0.77 37 No Yes
DeepSeek-V3.1
novita
cheapest
0.27 1 131072 0.87 31 Yes No
DeepSeek-V3.1
together
fastest
0.6 1.7 131072 1.15 82 Yes No
DeepSeek-V3.1
fireworks-ai
- - 163840 0.67 76 Yes No
Qwen3-VL-235B-A22B-Thinking
novita
0.98 3.95 131072 0.91 44 No No
DeepSeek-R1-Distill-Qwen-14B
novita
cheapest fastest
0.15 0.15 32768 0.81 62 No No
DeepSeek-R1-Distill-Qwen-14B
nscale
0.2 0.2 131072 0.92 37 No Yes
Qwen2.5-72B-Instruct
novita
cheapest
0.38 0.4 32000 0.55 37 Yes No
Qwen2.5-72B-Instruct
hyperbolic
0.4 0.4 131072 0.88 45 No No
Qwen2.5-72B-Instruct
together
fastest
1.2 1.2 131072 0.35 78 Yes Yes
Qwen2.5-72B-Instruct
fireworks-ai
- - - - - - -
NVIDIA-Nemotron-Nano-12B-v2
nebius
0.07 0.2 131072 0.30 126 No Yes
QwQ-32B
groq
- - - - - - -
QwQ-32B
nebius
- - - - - - -
QwQ-32B
sambanova
- - - - - - -
QwQ-32B
nscale
cheapest
0.18 0.2 131072 0.86 27 Yes Yes
QwQ-32B
hyperbolic
fastest
0.4 0.4 131072 1.93 40 Yes No
QwQ-32B
fireworks-ai
- - - - - - -
gpt-oss-safeguard-20b
groq
- - 131072 0.12 871 Yes No
Qwen2.5-Coder-7B-Instruct
nscale
0.01 0.03 131072 1.09 60 No Yes
DeepSeek-V3-0324
novita
0.27 1.12 163840 1.32 32 Yes Yes
DeepSeek-V3-0324
nebius
0.75 2.25 32768 0.93 117 No No
DeepSeek-V3-0324
sambanova
fastest
3 4.5 131072 0.74 132 Yes Yes
DeepSeek-V3-0324
hyperbolic
1.25 1.25 163840 0.97 44 No No
DeepSeek-V3-0324
together
1.25 1.25 131072 0.55 41 Yes Yes
DeepSeek-V3-0324
fireworks-ai
cheapest
0.9 0.9 163840 0.71 64 Yes No
Qwen3-Next-80B-A3B-Thinking
novita
0.15 1.5 131072 0.87 144 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest
0.3 0.3 262144 0.54 192 Yes No
Qwen3-Next-80B-A3B-Thinking
together
fastest
0.15 1.5 262144 0.46 194 Yes Yes
Qwen2.5-VL-72B-Instruct
nebius
0.25 0.75 32000 0.33 35 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
0.6 0.6 32768 0.46 43 No No
Qwen2.5-VL-72B-Instruct
ovhcloud
- - - 0.41 31 No Yes
Apertus-8B-Instruct-2509
publicai
- - - 0.95 93 No Yes
GLM-4.5
novita
0.6 2.2 131072 0.73 62 Yes No
GLM-4.5
nebius
0.6 2.2 131072 0.36 39 Yes Yes
GLM-4.5
fireworks-ai
cheapest fastest
0.55 2.19 131072 0.76 79 Yes No
GLM-4.5
zai-org
- - - 3.12 49 Yes No
Qwen3-VL-235B-A22B-Instruct
novita
0.3 1.5 131072 0.99 33 Yes Yes
Qwen3-14B
nscale
0.07 0.2 40960 0.77 50 Yes Yes
DeepSeek-R1-Distill-Qwen-32B
novita
cheapest
0.3 0.3 64000 0.75 24 No Yes
DeepSeek-R1-Distill-Qwen-32B
nscale
fastest
0.3 0.3 131072 0.99 25 No No
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
0.06 0.2 131072 0.85 26 No Yes
Qwen2.5-Coder-32B-Instruct
hyperbolic
fastest
0.2 0.2 32768 0.87 72 No No
Qwen2.5-Coder-32B-Instruct
together
- - - - - - -
Qwen2.5-Coder-32B-Instruct
scaleway
- - - 0.38 38 Yes No
DeepSeek-V3
novita
0.4 1.3 64000 1.38 30 Yes No
DeepSeek-V3
together
cheapest fastest
1.25 1.25 131072 0.54 44 Yes Yes
DeepSeek-V3
fireworks-ai
- - - - - - -
L3-70B-Euryale-v2.1
novita
1.48 1.48 8192 0.76 42 No No
DeepSeek-R1-Distill-Llama-70B
groq
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
novita
0.8 0.8 8192 0.91 32 No Yes
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
0.7 1.4 131072 1.65 155 No No
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
0.75 0.75 131072 1.02 16 No No
DeepSeek-R1-Distill-Llama-70B
scaleway
- - - 0.64 25 No Yes
DeepSeek-R1-Distill-Llama-70B
ovhcloud
- - - 0.48 30 No Yes
Qwen3-235B-A22B
novita
0.2 0.8 40960 0.92 39 No No
Qwen3-235B-A22B
nscale
cheapest
0.2 0.6 32000 1.44 23 Yes Yes
Qwen3-235B-A22B
together
0.2 0.6 40960 0.38 48 Yes Yes
Qwen3-235B-A22B
fireworks-ai
fastest
0.22 0.88 131072 0.68 66 Yes No
Qwen3-30B-A3B-Thinking-2507
nebius
0.1 0.3 262144 0.25 110 Yes Yes
DeepSeek-R1-Distill-Qwen-7B
nscale
0.15 0.15 131072 0.79 67 No No
GLM-4.6-FP8
zai-org
- - - 2.86 62 Yes No
Llama-3.1-405B-Instruct
sambanova
- - - - - - -
Llama-3.1-405B-Instruct
fireworks-ai
3 3 131072 0.50 64 Yes No
Qwen3-VL-30B-A3B-Thinking
novita
0.2 1 131072 0.70 85 Yes Yes
Qwen3-Coder-480B-A35B-Instruct-FP8
together
2 2 262144 0.45 44 Yes Yes
DeepSeek-R1-Distill-Llama-8B
novita
- - - - - - -
DeepSeek-R1-Distill-Llama-8B
nscale
0.05 0.05 131072 0.85 57 No Yes
Baichuan-M2-32B
novita
0.07 0.07 131072 1.76 32 No Yes
GLM-4.5-Air-FP8
together
0.2 1.1 131072 0.32 42 Yes Yes
GLM-4.5V-FP8
zai-org
- - - 3.45 43 Yes No
GLM-4.5V
novita
cheapest fastest
0.6 1.8 65536 0.86 73 Yes No
GLM-4.5V
zai-org
- - - 2.94 51 Yes No
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
0.17 0.85 1048576 0.68 26 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
0.27 0.85 1048576 0.82 78 Yes Yes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
0.11 0.34 131072 0.16 359 Yes No
Llama-4-Scout-17B-16E-Instruct
novita
0.1 0.5 131072 0.28 45 No No
Llama-4-Scout-17B-16E-Instruct
sambanova
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
0.09 0.29 890000 1.00 33 Yes Yes
Llama-4-Scout-17B-16E-Instruct
together
0.18 0.59 1048576 0.40 114 Yes Yes
Llama-4-Scout-17B-16E-Instruct
fireworks-ai
0.15 0.6 1048576 0.52 48 Yes No
marin-8b-instruct
together
0.18 0.18 4096 0.17 183 No Yes
Qwen3-235B-A22B-Thinking-2507
novita
0.3 3 131072 0.44 26 Yes No
Qwen3-235B-A22B-Thinking-2507
cerebras
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
fireworks-ai
cheapest fastest
0.22 0.88 262144 0.62 49 Yes No
Hermes-2-Pro-Llama-3-8B
novita
0.14 0.14 8192 1.26 89 No No
L3-8B-Stheno-v3.2
novita
0.05 0.05 8192 0.66 58 No No
Hermes-4-405B
nebius
1 3 131072 0.33 38 No No
Qwen2.5-Coder-7B
nebius
0.03 0.09 32768 0.27 168 No Yes
Arch-Router-1.5B
hf-inference
- - - 0.12 71 No Yes
Llama-Guard-4-12B
groq
0.2 0.2 131072 0.14 13 No No
Apertus-70B-Instruct-2509
publicai
- - - 0.95 52 No Yes
Qwen2.5-VL-32B-Instruct
fireworks-ai
0.22 0.88 128000 0.33 51 No No
command-a-vision-07-2025
cohere
- - - 0.21 43 No No
aya-expanse-32b
cohere
- - - 0.19 43 No No
c4ai-command-r7b-12-2024
cohere
- - - 0.18 113 Yes No
c4ai-command-a-03-2025
cohere
- - - 0.26 58 Yes No
DeepSeek-R1-0528-Qwen3-8B
novita
0.06 0.09 128000 0.63 75 No No
ERNIE-4.5-VL-28B-A3B-PT
novita
0.14 0.56 30000 0.64 71 No No
ERNIE-4.5-0.3B-PT
novita
- - 120000 0.63 113 No No
GLM-4.1V-9B-Thinking
novita
0.035 0.138 65536 0.62 70 No No
GLM-4-32B-0414
novita
0.55 1.66 32000 1.02 37 No No
Qwen2.5-Coder-3B-Instruct
nscale
0.01 0.03 32768 0.81 85 No Yes
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
1.2 1.2 65536 0.83 25 No Yes
Mixtral-8x22B-Instruct-v0.1
together
- - - - - - -
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
1.2 1.2 65536 0.38 68 No No
DeepSeek-R1-0528
novita
0.7 2.5 163840 0.69 28 Yes No
DeepSeek-R1-0528
nebius
cheapest
0.8 2.4 163840 0.52 17 Yes Yes
DeepSeek-R1-0528
sambanova
fastest
5 7 131072 2.05 121 Yes Yes
DeepSeek-R1-0528
hyperbolic
3 3 163840 0.73 55 No No
DeepSeek-R1-0528
together
3 7 163840 0.59 55 No Yes
DeepSeek-R1-0528
fireworks-ai
3 8 163840 1.00 33 Yes No
ERNIE-4.5-21B-A3B-PT
novita
0.07 0.28 120000 1.15 80 No No
ERNIE-4.5-VL-424B-A47B-Base-PT
novita
0.42 1.25 123000 1.22 42 No No
Dobby-Unhinged-Llama-3.3-70B
fireworks-ai
0.9 0.9 131072 0.30 52 No No
Gemma-SEA-LION-v4-27B-IT
publicai
- - - 1.84 48 No Yes
cogito-v2-preview-llama-405B
together
3.5 3.5 32768 0.82 24 Yes Yes
cogito-v2-preview-llama-109B-MoE
together
0.18 0.59 32767 0.70 83 Yes Yes
cogito-v2-preview-llama-70B
together
0.88 0.88 32768 0.93 51 Yes Yes
command-a-translate-08-2025
cohere
- - - 0.20 64 Yes No
command-a-reasoning-08-2025
cohere
- - - 0.18 90 Yes No
c4ai-command-r-08-2024
cohere
- - - 0.26 57 Yes No
aya-vision-32b
cohere
- - - 0.32 57 No No
L3-8B-Lunaris-v1
novita
0.05 0.05 8192 0.66 73 No No
DeepSeek-Prover-V2-671B
novita
0.7 2.5 160000 0.66 38 No No
Meta-Llama-3-70B-Instruct
groq
- - - - - - -
Meta-Llama-3-70B-Instruct
novita
0.51 0.74 8192 0.78 28 No Yes
Meta-Llama-3-70B-Instruct
hyperbolic
cheapest fastest
0.4 0.4 8192 0.98 95 No No
Meta-Llama-3-70B-Instruct
together
0.88 0.88 8192 0.29 70 No Yes
WizardLM-2-8x22B
novita
0.62 0.62 65535 0.39 44 No No
Hermes-4-70B
nebius
0.13 0.4 131072 0.35 88 No No
Qwen3-235B-A22B-FP8
together
0.2 0.6 40960 0.44 33 Yes Yes
Llama-3_1-Nemotron-Ultra-253B-v1
nebius
0.6 1.8 131072 0.24 40 No Yes
gemma-2-9b-it
groq
- - - - - - -
gemma-2-9b-it
nebius
0.03 0.09 8192 0.24 137 No Yes
MiniMax-M1-80k
novita
0.55 2.2 1000000 1.23 58 Yes No
ERNIE-4.5-300B-A47B-Base-PT
novita
0.28 1.1 123000 1.16 25 No Yes
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova
0.6 1.2 131072 3.03 133 No Yes