Inference Providers

·

Metrics for top trending models

MiniMax-M2
novita live 0.3 1.2 204800 0.93 51 No No
gpt-oss-safeguard-20b
groq live - - 131072 0.15 865 Yes No
GLM-4.6
novita live 0.6 2.2 204800 0.80 40 Yes No
GLM-4.6
zai-org live - - - 1.03 49 Yes No
gpt-oss-20b
groq live 0.1 0.5 131072 0.10 865 Yes No
gpt-oss-20b
novita live 0.04 0.15 131072 1.07 178 No Yes
gpt-oss-20b
nebius live 0.05 0.2 131072 0.41 176 Yes Yes
gpt-oss-20b
nscale live 0.05 0.2 131072 0.91 88 Yes Yes
gpt-oss-20b
hyperbolic live 0.1 0.1 131072 0.52 127 No No
gpt-oss-20b
together live 0.05 0.2 131072 0.23 129 Yes Yes
gpt-oss-20b
fireworks-ai live 0.05 0.2 131072 0.54 221 Yes No
Qwen3-VL-8B-Instruct
novita live 0.08 0.5 131072 0.60 75 Yes Yes
Llama-3.1-8B-Instruct
novita live 0.02 0.05 16384 0.83 73 No No
Llama-3.1-8B-Instruct
nebius live 0.03 0.09 131072 0.31 165 Yes Yes
Llama-3.1-8B-Instruct
cerebras live 0.1 0.1 - 0.44 997 No No
Llama-3.1-8B-Instruct
sambanova live 0.1 0.2 16384 0.61 610 Yes Yes
Llama-3.1-8B-Instruct
nscale live 0.06 0.06 131072 0.96 59 No Yes
Llama-3.1-8B-Instruct
fireworks-ai live 0.2 0.2 131072 0.42 242 No No
Llama-3.1-8B-Instruct
scaleway live - - - 0.46 71 Yes Yes
gpt-oss-120b
groq live 0.15 0.75 131072 0.14 432 Yes No
gpt-oss-120b
novita live 0.05 0.25 131072 0.63 247 Yes Yes
gpt-oss-120b
nebius live 0.15 0.6 131072 0.50 19 Yes No
gpt-oss-120b
cerebras live 0.25 0.69 - 0.26 985 Yes No
gpt-oss-120b
sambanova live 0.22 0.59 131072 1.02 448 Yes Yes
gpt-oss-120b
nscale live 0.1 0.4 131072 0.98 109 Yes Yes
gpt-oss-120b
hyperbolic live 0.3 0.3 131072 0.76 245 Yes No
gpt-oss-120b
together live 0.15 0.6 131072 0.31 113 Yes Yes
gpt-oss-120b
fireworks-ai live 0.15 0.6 131072 0.71 124 Yes No
gpt-oss-120b
scaleway live - - - 0.52 68 Yes Yes
DeepSeek-V3.2-Exp
novita live 0.27 0.41 163840 0.98 30 Yes Yes
Kimi-K2-Instruct-0905
groq live - - 262144 0.21 186 Yes No
Kimi-K2-Instruct-0905
novita live 0.6 2.5 262144 1.05 38 Yes Yes
Kimi-K2-Instruct-0905
together live 1 3 262144 0.52 37 Yes Yes
Mistral-7B-Instruct-v0.3
novita offline 0.029 0.059 32768 0.83 118 No No
Mistral-7B-Instruct-v0.3
together live 0.2 0.2 32768 0.20 189 No Yes
Qwen3-VL-30B-A3B-Instruct
novita live 0.2 0.7 131072 0.73 85 Yes Yes
SmolLM3-3B
hf-inference live - - - 0.16 87 Yes Yes
DeepSeek-R1
novita live 0.7 2.5 64000 0.75 28 Yes No
DeepSeek-R1
sambanova live - - - 1.61 150 Yes Yes
DeepSeek-R1
hyperbolic live 2 2 163840 0.93 42 No No
DeepSeek-R1
together live 3 7 163840 0.58 42 No Yes
DeepSeek-R1
fireworks-ai offline 3 8 163840 0.83 70 No No
Qwen2.5-7B-Instruct
together live 0.3 0.3 32768 0.56 74 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
nebius live 0.1 0.3 262144 0.38 130 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
fireworks-ai offline 0.15 0.6 262144 0.90 102 Yes No
Qwen3-Coder-30B-A3B-Instruct
scaleway live - - - 0.52 108 Yes No
Qwen3-4B-Instruct-2507
nscale live 0.01 0.03 262144 0.94 91 Yes No
Meta-Llama-3-8B-Instruct
groq offline 0.05 0.08 8192 0.19 1056 Yes No
Meta-Llama-3-8B-Instruct
novita live 0.04 0.04 8192 0.85 67 No No
Meta-Llama-3-8B-Instruct
together offline - - - - - - -
Qwen3-8B
nscale live 0.07 0.18 40960 1.06 51 Yes No
Arch-Router-1.5B
hf-inference live - - - 0.13 67 No Yes
NVIDIA-Nemotron-Nano-12B-v2
nebius live 0.07 0.2 131072 0.34 124 No Yes
Qwen3-30B-A3B-Instruct-2507
nebius live 0.1 0.3 262144 0.37 95 Yes Yes
gemma-3-27b-it
nebius live 0.2 0.6 110000 0.42 77 No Yes
gemma-3-27b-it
scaleway live - - - 0.61 43 Yes No
Qwen3-Next-80B-A3B-Instruct
novita live 0.15 1.5 131072 0.80 111 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic live 0.3 0.3 262144 0.65 159 Yes No
Qwen3-Next-80B-A3B-Instruct
together live 0.15 1.5 262144 0.58 166 Yes Yes
Llama-3.2-3B-Instruct
novita live 0.03 0.05 32768 0.83 122 Yes No
Llama-3.2-3B-Instruct
sambanova offline - - - 0.38 - - -
Llama-3.2-3B-Instruct
hyperbolic live 0.1 0.1 131072 1.52 91 No No
Llama-3.2-3B-Instruct
together live 0.06 0.06 131072 0.69 121 Yes Yes
MiniMax-M1-80k
novita live 0.55 2.2 1000000 1.23 47 No No
Llama-3.3-70B-Instruct
groq live 0.59 0.79 131072 0.13 406 Yes No
Llama-3.3-70B-Instruct
novita live 0.13 0.39 131072 0.71 29 Yes No
Llama-3.3-70B-Instruct
nebius live 0.25 0.75 131072 0.35 106 Yes Yes
Llama-3.3-70B-Instruct
cerebras live 0.85 1.2 - 0.26 1138 Yes No
Llama-3.3-70B-Instruct
sambanova live 0.6 1.2 131072 0.46 315 Yes Yes
Llama-3.3-70B-Instruct
nscale live 0.4 0.4 131072 1.15 17 No Yes
Llama-3.3-70B-Instruct
hyperbolic live 0.4 0.4 131072 0.70 111 No No
Llama-3.3-70B-Instruct
together live 0.88 0.88 131072 0.44 105 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai live 0.9 0.9 131072 0.51 133 No No
Llama-3.3-70B-Instruct
scaleway live - - - 0.64 25 Yes Yes
Llama-3.2-1B-Instruct
novita live - - 131000 1.07 184 No No
Llama-3.2-1B-Instruct
sambanova offline - - - 0.44 - - -
Kimi-K2-Instruct
novita live 0.57 2.3 131072 0.77 39 Yes No
Kimi-K2-Instruct
nebius live 0.5 2.4 131072 0.41 43 Yes Yes
Kimi-K2-Instruct
together live 1 3 131072 0.65 47 Yes Yes
Kimi-K2-Instruct
fireworks-ai live 0.6 2.5 131072 0.81 36 Yes No
GLM-4.5-Air
novita live 0.13 0.85 131072 0.65 53 Yes No
GLM-4.5-Air
nebius live 0.2 1.2 131072 0.32 72 Yes Yes
GLM-4.5-Air
fireworks-ai offline 0.22 0.88 131072 0.76 106 Yes No
GLM-4.5-Air
zai-org live - - - 1.08 38 Yes No
Mixtral-8x7B-Instruct-v0.1
together live 0.6 0.6 32768 0.24 58 No Yes
Llama-4-Scout-17B-16E-Instruct
groq live 0.11 0.34 131072 0.27 349 Yes No
Llama-4-Scout-17B-16E-Instruct
novita live 0.1 0.5 131072 0.54 53 No No
Llama-4-Scout-17B-16E-Instruct
cerebras live 0.65 0.85 - 0.28 1138 Yes No
Llama-4-Scout-17B-16E-Instruct
sambanova offline - - - 0.86 - - -
Llama-4-Scout-17B-16E-Instruct
nscale live 0.09 0.29 890000 0.96 33 Yes Yes
Llama-4-Scout-17B-16E-Instruct
together offline 0.18 0.59 1048576 0.31 83 Yes Yes
Llama-4-Scout-17B-16E-Instruct
fireworks-ai live 0.15 0.6 1048576 0.60 81 Yes No
Qwen3-30B-A3B
novita live 0.09 0.45 40960 0.84 104 No No
Qwen3-30B-A3B
nebius live 0.1 0.3 40960 0.34 83 Yes Yes
Qwen3-30B-A3B
fireworks-ai live 0.15 0.6 131072 0.70 143 Yes No
Qwen3-30B-A3B-Thinking-2507
nebius live 0.1 0.3 262144 0.24 109 Yes Yes
Qwen3-VL-30B-A3B-Thinking
novita live 0.2 1 131072 0.79 111 Yes Yes
QwQ-32B
groq offline - - - - - - -
QwQ-32B
nebius live 0.5 1.5 131072 0.37 84 No Yes
QwQ-32B
sambanova offline - - - 0.41 - - -
QwQ-32B
nscale live 0.18 0.2 131072 1.15 24 Yes Yes
QwQ-32B
hyperbolic live 0.4 0.4 131072 0.72 87 No No
QwQ-32B
fireworks-ai offline - - - 0.56 - No No
Qwen3-32B
groq live 0.29 0.59 131072 0.21 231 Yes No
Qwen3-32B
novita live 0.1 0.45 40960 0.94 62 No No
Qwen3-32B
nebius live 0.1 0.3 40960 0.34 47 Yes Yes
Qwen3-32B
cerebras live 0.4 0.8 - 0.26 181 No No
Qwen3-32B
sambanova live 0.4 0.8 32768 2.13 203 Yes Yes
Qwen3-32B
nscale live 0.08 0.25 40960 0.94 25 Yes Yes
Qwen3-14B
nebius live 0.08 0.24 40960 0.31 84 Yes Yes
Qwen3-14B
nscale live 0.07 0.2 40960 0.95 35 Yes Yes
Qwen3-Next-80B-A3B-Thinking
novita live 0.15 1.5 131072 0.86 140 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic live 0.3 0.3 262144 0.73 144 Yes No
Qwen3-Next-80B-A3B-Thinking
together live 0.15 1.5 262144 1.00 172 Yes Yes
Qwen2.5-VL-7B-Instruct
hyperbolic live 0.2 0.2 32768 0.72 106 No No
Qwen3-VL-235B-A22B-Instruct
novita live 0.3 1.5 131072 1.02 36 Yes Yes
GLM-4.5
novita live 0.6 2.2 131072 0.74 28 Yes No
GLM-4.5
nebius live 0.6 2.2 131072 0.37 34 Yes Yes
GLM-4.5
fireworks-ai live 0.55 2.19 131072 0.82 85 Yes No
GLM-4.5
zai-org live - - - 1.05 31 Yes No
DeepSeek-R1-Distill-Qwen-7B
nscale live 0.15 0.15 131072 0.87 66 No No
DeepSeek-V3.1
novita live 0.27 1 131072 0.94 39 Yes Yes
DeepSeek-V3.1
together live 0.6 1.7 131072 0.46 109 Yes No
DeepSeek-V3.1
fireworks-ai live - - 163840 1.04 71 Yes No
GLM-4.5V
novita live 0.6 1.8 65536 1.92 44 Yes No
GLM-4.5V
zai-org live - - - 1.36 48 Yes No
GLM-4.6-FP8
zai-org live - - - 1.48 61 Yes No
Apertus-8B-Instruct-2509
publicai live - - - 1.27 105 No Yes
Qwen3-4B-Thinking-2507
nscale live 0.01 0.03 262144 0.97 57 Yes No
Qwen3-235B-A22B-Thinking-2507
novita live 0.3 3 131072 0.58 50 Yes No
Qwen3-235B-A22B-Thinking-2507
cerebras live 0.6 1.2 - 0.31 541 No No
Qwen3-235B-A22B-Thinking-2507
fireworks-ai live 0.22 0.88 262144 1.04 57 Yes No
Apertus-70B-Instruct-2509
publicai live - - - 1.22 39 Yes Yes
DeepSeek-R1-0528-Qwen3-8B
novita live 0.06 0.09 128000 0.99 77 No No
DeepSeek-R1-Distill-Qwen-32B
novita live 0.3 0.3 64000 0.79 35 No Yes
DeepSeek-R1-Distill-Qwen-32B
nscale live 0.3 0.3 131072 1.05 26 No Yes
DeepSeek-R1-Distill-Qwen-14B
novita live 0.15 0.15 32768 1.21 55 No No
DeepSeek-R1-Distill-Qwen-14B
nscale live 0.2 0.2 131072 1.01 35 No No
L3-8B-Stheno-v3.2
novita live 0.05 0.05 8192 0.71 93 No No
Qwen3-Coder-480B-A35B-Instruct
novita live 0.29 1.2 262144 1.50 36 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
nebius live 0.4 1.8 262144 0.50 63 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
cerebras live 2 2 - 0.29 695 Yes No
Qwen3-Coder-480B-A35B-Instruct
hyperbolic live 2 2 262144 1.84 61 Yes No
Qwen3-Coder-480B-A35B-Instruct
together live 2 2 262144 0.58 29 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
fireworks-ai live 0.45 1.8 262144 0.83 32 Yes No
DeepSeek-R1-Distill-Qwen-1.5B
nscale live 0.1 0.1 131072 0.80 128 No No
Mixtral-8x22B-Instruct-v0.1
nscale live 1.2 1.2 65536 0.99 20 No Yes
Mixtral-8x22B-Instruct-v0.1
together offline - - - - - - -
Mixtral-8x22B-Instruct-v0.1
fireworks-ai live 1.2 1.2 65536 0.36 69 No No
Qwen3-VL-235B-A22B-Thinking
novita live 0.98 3.95 131072 0.86 35 No No
Baichuan-M2-32B
novita live 0.07 0.07 131072 1.83 35 No Yes
Qwen2.5-VL-32B-Instruct
fireworks-ai live 0.22 0.88 128000 0.53 43 No No
Hermes-4-70B
nebius live 0.13 0.4 131072 0.36 90 No No
Qwen3-235B-A22B-Instruct-2507
novita live 0.09 0.58 131072 0.87 31 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nebius live 0.2 0.6 262144 0.37 59 Yes Yes
Qwen3-235B-A22B-Instruct-2507
cerebras live 0.6 1.2 - 0.26 458 Yes No
Qwen3-235B-A22B-Instruct-2507
nscale live 0.2 0.6 32768 1.12 24 Yes Yes
Qwen3-235B-A22B-Instruct-2507
hyperbolic live 2 2 262144 0.76 59 Yes No
Qwen3-235B-A22B-Instruct-2507
together live 0.2 0.6 262144 0.47 42 Yes Yes
Qwen3-235B-A22B-Instruct-2507
fireworks-ai live 0.22 0.88 262144 1.04 39 Yes No
Qwen3-235B-A22B-Instruct-2507
scaleway live - - - 0.52 82 Yes Yes
Llama-3.1-405B-Instruct
nebius live 1 3 131072 0.30 35 Yes Yes
Llama-3.1-405B-Instruct
sambanova offline - - - 0.47 112 Yes Yes
Llama-3.1-405B-Instruct
fireworks-ai live 3 3 131072 0.51 65 Yes No
Llama-Guard-4-12B
groq live 0.2 0.2 131072 0.21 9 No No
DeepSeek-R1-0528
novita live 0.7 2.5 163840 0.99 28 Yes No
DeepSeek-R1-0528
nebius live 0.8 2.4 163840 0.36 38 Yes Yes
DeepSeek-R1-0528
sambanova live 5 7 131072 0.39 221 Yes Yes
DeepSeek-R1-0528
hyperbolic live 3 3 163840 0.86 47 No No
DeepSeek-R1-0528
together live 3 7 163840 0.62 40 No Yes
DeepSeek-R1-0528
fireworks-ai live 3 8 163840 1.05 36 Yes No
Qwen2.5-Coder-32B-Instruct
nscale live 0.06 0.2 131072 0.91 28 No Yes
Qwen2.5-Coder-32B-Instruct
hyperbolic live 0.2 0.2 32768 1.56 55 No No
Qwen2.5-Coder-32B-Instruct
together live 0.8 0.8 16384 0.30 95 Yes Yes
Qwen2.5-Coder-32B-Instruct
scaleway live - - - 0.54 40 Yes No
Llama-4-Maverick-17B-128E-Instruct-FP8
novita live 0.17 0.85 1048576 0.88 66 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together live 0.27 0.85 1048576 0.36 56 Yes Yes
Qwen3-Coder-480B-A35B-Instruct-FP8
together live 2 2 262144 0.52 41 Yes Yes
DeepSeek-V3
novita live 0.4 1.3 64000 1.54 30 Yes No
DeepSeek-V3
nebius offline 0.5 1.5 163840 0.96 31 No Yes
DeepSeek-V3
together live 1.25 1.25 131072 1.02 33 Yes Yes
DeepSeek-V3
fireworks-ai offline 0.9 0.9 131072 0.82 85 Yes No
GLM-4.5-Air-FP8
together live 0.2 1.1 131072 0.80 125 Yes Yes
AFM-4.5B
together live 0.048 0.15 65536 0.75 180 No Yes
aya-expanse-32b
cohere live - - - 0.35 36 No No
GLM-4.1V-9B-Thinking
novita live 0.035 0.138 65536 0.70 70 No No
Qwen2.5-VL-72B-Instruct
nebius live 0.25 0.75 32000 0.38 34 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic live 0.6 0.6 32768 0.59 40 No No
DeepSeek-V3.1-Terminus
novita live 0.27 1 131072 1.20 31 Yes Yes
gemma-2-9b-it
groq offline 0.2 0.2 8192 0.34 435 Yes No
gemma-2-9b-it
nebius live 0.03 0.09 8192 0.37 144 No Yes
Qwen2.5-72B-Instruct
novita live 0.38 0.4 32000 0.82 45 Yes No
Qwen2.5-72B-Instruct
nebius live 0.13 0.4 131072 0.36 37 Yes No
Qwen2.5-72B-Instruct
hyperbolic live 0.4 0.4 131072 1.11 60 Yes No
Qwen2.5-72B-Instruct
together live 1.2 1.2 131072 0.36 25 Yes Yes
Qwen2.5-72B-Instruct
fireworks-ai offline - - - 0.40 - Yes No
GLM-4.5V-FP8
zai-org live - - - 1.52 41 Yes No
Meta-Llama-3-70B-Instruct
groq offline 0.59 0.79 8192 0.17 296 Yes No
Meta-Llama-3-70B-Instruct
novita live 0.51 0.74 8192 0.81 20 No Yes
Meta-Llama-3-70B-Instruct
hyperbolic live 0.4 0.4 8192 0.74 99 No No
Meta-Llama-3-70B-Instruct
together live 0.88 0.88 8192 0.30 115 No Yes
DeepSeek-V3-0324
novita live 0.27 1.12 163840 1.10 29 Yes Yes
DeepSeek-V3-0324
nebius live 0.75 2.25 32768 0.92 125 No No
DeepSeek-V3-0324
sambanova live 3 4.5 131072 0.62 197 Yes Yes
DeepSeek-V3-0324
hyperbolic live 1.25 1.25 163840 1.02 65 No No
DeepSeek-V3-0324
together live 1.25 1.25 131072 1.19 39 Yes Yes
DeepSeek-V3-0324
fireworks-ai live 0.9 0.9 163840 0.94 74 Yes No
Llama-4-Maverick-17B-128E-Instruct
groq live 0.2 0.6 131072 0.17 507 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova live 0.63 1.8 131072 2.25 288 Yes No
Llama-4-Maverick-17B-128E-Instruct
fireworks-ai live 0.22 0.88 1048576 0.47 113 Yes No
marin-8b-instruct
together live 0.18 0.18 4096 0.22 172 No Yes
Qwen2.5-Coder-7B
nebius live 0.03 0.09 32768 0.30 217 No Yes
Hermes-2-Pro-Llama-3-8B
novita live 0.14 0.14 8192 0.91 106 No No
Hermes-4-405B
nebius live 1 3 131072 0.36 38 No No
gemma-2-2b-it
nebius live 0.02 0.06 8192 0.37 138 No Yes
Llama-3_1-Nemotron-Ultra-253B-v1
nebius live 0.6 1.8 131072 0.42 40 No Yes
DeepSeek-R1-Distill-Llama-8B
novita offline 0.04 0.04 32000 0.63 52 No Yes
DeepSeek-R1-Distill-Llama-8B
nscale live 0.05 0.05 131072 0.78 54 No Yes
Llama-3.1-70B-Instruct
fireworks-ai live 0.9 0.9 131072 0.41 131 No No
Qwen2.5-Coder-3B-Instruct
nscale live 0.01 0.03 32768 0.86 73 No Yes
ERNIE-4.5-21B-A3B-PT
novita live 0.07 0.28 120000 0.95 77 No No
DeepSeek-Prover-V2-671B
novita live 0.7 2.5 160000 0.86 44 No No
Qwen3-235B-A22B
novita live 0.2 0.8 40960 1.07 31 No No
Qwen3-235B-A22B
nscale live 0.2 0.6 32000 1.11 23 Yes Yes
Qwen3-235B-A22B
together live 0.2 0.6 40960 0.48 47 Yes Yes
Qwen3-235B-A22B
fireworks-ai live 0.22 0.88 131072 0.95 72 Yes No
Qwen2.5-Coder-7B-Instruct
nscale live 0.01 0.03 131072 0.95 57 No Yes
Dobby-Unhinged-Llama-3.3-70B
fireworks-ai live 0.9 0.9 131072 0.37 52 No No
DeepSeek-R1-Distill-Llama-70B
groq offline 0.75 0.99 131072 0.65 200 Yes No
DeepSeek-R1-Distill-Llama-70B
novita live 0.8 0.8 8192 1.93 30 No Yes
DeepSeek-R1-Distill-Llama-70B
sambanova live 0.7 1.4 131072 0.77 187 No No
DeepSeek-R1-Distill-Llama-70B
nscale live 0.75 0.75 131072 0.98 16 No No
DeepSeek-R1-Distill-Llama-70B
scaleway live - - - 0.82 24 No Yes
KAT-Dev
novita live 0.15 0.4 65536 2.02 36 Yes Yes
command-a-translate-08-2025
cohere live - - - 0.27 62 Yes No
cogito-v2-preview-deepseek-671B-MoE
together live 1.25 1.25 163840 0.28 35 No Yes
cogito-v2-preview-llama-405B
together live 3.5 3.5 32768 0.94 26 Yes Yes
cogito-v2-preview-llama-109B-MoE
together live 0.18 0.59 32767 0.60 84 Yes Yes
cogito-v2-preview-llama-70B
together live 0.88 0.88 32768 0.81 53 Yes Yes
command-a-reasoning-08-2025
cohere live - - - 0.25 92 Yes No
command-a-vision-07-2025
cohere live - - - 0.26 47 No No
c4ai-command-r7b-arabic-02-2025
cohere live - - - 0.35 59 Yes No
aya-vision-32b
cohere live - - - 0.98 53 No No
c4ai-command-r-08-2024
cohere live - - - 0.22 48 Yes No
c4ai-command-r7b-12-2024
cohere live - - - 0.29 114 Yes No
c4ai-command-a-03-2025
cohere live - - - 0.43 62 Yes No
L3-8B-Lunaris-v1
novita live 0.05 0.05 8192 0.90 53 No No
WizardLM-2-8x22B
novita live 0.62 0.62 65535 0.70 35 No No
GLM-4-32B-0414
novita live 0.55 1.66 32000 1.12 36 No Yes
ERNIE-4.5-300B-A47B-Base-PT
novita live 0.28 1.1 123000 1.20 26 No Yes
ERNIE-4.5-VL-28B-A3B-PT
novita live 0.14 0.56 30000 1.15 75 No No
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova live 0.6 1.2 131072 2.68 146 No Yes
Hermes-3-Llama-3.1-405B
nebius live 1 3 131072 0.30 24 No Yes
ERNIE-4.5-VL-424B-A47B-Base-PT
novita live 0.42 1.25 123000 1.12 39 No No
ERNIE-4.5-0.3B-PT
novita live - - 120000 1.18 103 No No
QwQ-32B-Preview
sambanova offline - - - 0.35 - - -
QwQ-32B-Preview
hyperbolic offline - - - - - - -
QwQ-32B-Preview
together live - - - 0.85 87 Yes Yes
QwQ-32B-Preview
fireworks-ai offline - - - - - - -
Hermes-3-Llama-3.1-70B
hyperbolic live 0.4 0.4 12288 0.40 30 No No
Mistral-Small-24B-Instruct-2501
together live 0.8 0.8 32768 0.23 85 Yes Yes
L3-70B-Euryale-v2.1
novita live 1.48 1.48 8192 1.01 55 No No
Qwen3-235B-A22B-FP8
together live 0.2 0.6 40960 0.42 46 Yes Yes