Hugging Face's logo

Inference Providers

·

Metrics for top trending models

Browse all models Learn more
MiMo-V2-Flash
novita
$0.10 $0.29 262,144 2.22 64 No Yes
GLM-4.6V-Flash
novita
cheapest
$0.30 $0.90 131,072 0.87 69 Yes Yes
GLM-4.6V-Flash
zai-org
fastest
- - - 1.90 112 Yes No
DeepSeek-V3.2
novita
cheapest
$0.27 $0.40 163,840 1.31 26 No No
DeepSeek-V3.2
fireworks-ai
fastest
- - 163,840 1.33 46 Yes No
AutoGLM-Phone-9B-Multilingual
novita
$0.04 $0.14 65,536 0.77 64 No No
Apriel-1.6-15b-Thinker
together
$0.00 $0.00 131,072 0.31 151 No No
GLM-4.6V
novita
- - - - - - -
GLM-4.6V
zai-org
- - - 2.36 72 Yes No
rnj-1-instruct
together
$0.15 $0.15 32,768 0.69 108 Yes Yes
Olmo-3.1-32B-Think
publicai
$0.00 $0.00 - 2.69 63 No No
gpt-oss-20b
groq
fastest
$0.10 $0.50 131,072 0.24 780 Yes No
gpt-oss-20b
novita
$0.03 $0.12 131,072 0.97 198 No Yes
gpt-oss-20b
nebius
$0.05 $0.20 131,072 0.40 170 Yes Yes
gpt-oss-20b
nscale
$0.05 $0.20 131,072 0.84 112 Yes Yes
gpt-oss-20b
hyperbolic
cheapest
$0.10 $0.10 131,072 1.20 94 No No
gpt-oss-20b
together
$0.05 $0.20 131,072 0.30 128 Yes No
gpt-oss-20b
fireworks-ai
$0.05 $0.20 131,072 0.49 129 Yes No
gpt-oss-20b
ovhcloud
$0.05 $0.18 131,072 0.59 16 No Yes
Olmo-3.1-32B-Instruct
publicai
$0.00 $0.00 - 4.48 29 No Yes
EuroLLM-22B-Instruct-2512
publicai
$0.00 $0.00 - - - No No
Llama-3.1-8B-Instruct
novita
cheapest
$0.02 $0.05 16,384 0.74 81 No No
Llama-3.1-8B-Instruct
nebius
$0.03 $0.09 131,072 0.46 152 No Yes
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10 $0.10 - 0.35 1,078 No No
Llama-3.1-8B-Instruct
sambanova
$0.10 $0.20 16,384 0.84 473 Yes Yes
Llama-3.1-8B-Instruct
nscale
$0.06 $0.06 131,072 0.94 58 No Yes
Llama-3.1-8B-Instruct
fireworks-ai
- - - - - - -
Llama-3.1-8B-Instruct
scaleway
- - - 0.39 113 Yes Yes
Llama-3.1-8B-Instruct
ovhcloud
$0.11 $0.11 131,072 0.50 43 Yes Yes
DeepSeek-OCR
novita
$0.02 $0.02 8,192 0.89 215 No Yes
gpt-oss-120b
groq
$0.15 $0.75 131,072 0.20 426 Yes No
gpt-oss-120b
novita
cheapest
$0.04 $0.20 131,072 1.33 117 No Yes
gpt-oss-120b
nebius
$0.15 $0.60 131,072 0.70 181 Yes No
gpt-oss-120b
cerebras
fastest
$0.25 $0.69 - 0.38 764 Yes No
gpt-oss-120b
sambanova
$0.22 $0.59 131,072 0.50 488 Yes Yes
gpt-oss-120b
nscale
$0.10 $0.40 131,072 0.85 86 Yes Yes
gpt-oss-120b
hyperbolic
$0.30 $0.30 131,072 0.79 264 Yes No
gpt-oss-120b
together
$0.15 $0.60 131,072 0.41 67 Yes Yes
gpt-oss-120b
fireworks-ai
$0.15 $0.60 131,072 0.54 104 Yes No
gpt-oss-120b
scaleway
- - - 0.63 99 Yes Yes
gpt-oss-120b
ovhcloud
$0.09 $0.47 131,072 0.46 142 Yes Yes
Qwen3-4B-Instruct-2507
nscale
$0.01 $0.03 262,144 0.93 87 Yes No
Qwen3-VL-8B-Instruct
novita
$0.06 $0.40 131,072 0.86 72 Yes Yes
GLM-4.6
novita
cheapest
$0.44 $1.76 204,800 0.70 50 Yes No
GLM-4.6
cerebras
fastest
- - - 0.33 291 Yes No
GLM-4.6
zai-org
- - - 2.21 61 Yes No
Kimi-K2-Thinking
novita
cheapest
$0.48 $2.00 262,144 0.88 25 Yes No
Kimi-K2-Thinking
nebius
$0.60 $2.50 262,144 0.75 79 Yes Yes
Kimi-K2-Thinking
together
fastest
$1.20 $4.00 262,144 0.54 94 Yes Yes
gemma-3-27b-it
nebius
cheapest fastest
$0.20 $0.60 110,000 0.44 59 No Yes
gemma-3-27b-it
scaleway
- - - 0.66 43 Yes No
Qwen3-8B
nscale
$0.07 $0.18 40,960 0.82 58 No No
Qwen3-VL-30B-A3B-Instruct
novita
$0.16 $0.56 131,072 0.82 69 Yes Yes
Qwen2.5-7B-Instruct
together
$0.30 $0.30 32,768 0.38 147 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
nebius
fastest
$0.10 $0.30 262,144 0.43 143 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
fireworks-ai
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
scaleway
- - - 0.47 100 Yes No
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07 $0.26 262,144 0.48 40 Yes Yes
Qwen3-30B-A3B-Instruct-2507
nebius
$0.10 $0.30 262,144 0.53 85 Yes Yes
Llama-3.2-3B-Instruct
novita
cheapest
$0.02 $0.04 32,768 0.74 121 Yes No
Llama-3.2-3B-Instruct
sambanova
- - - - - - -
Llama-3.2-3B-Instruct
hyperbolic
$0.10 $0.10 131,072 0.69 140 No No
Llama-3.2-3B-Instruct
together
fastest
$0.06 $0.06 131,072 0.36 150 Yes Yes
Llama-3.2-1B-Instruct
novita
- - 131,000 0.74 185 No No
Llama-3.2-1B-Instruct
sambanova
- - - - - - -
Meta-Llama-3-8B-Instruct
groq
- - - - - - -
Meta-Llama-3-8B-Instruct
novita
$0.03 $0.03 8,192 0.81 86 No No
Meta-Llama-3-8B-Instruct
together
- - - - - - -
Qwen3-4B-Thinking-2507
nscale
$0.01 $0.03 262,144 0.93 89 Yes No
MiniMax-M2
novita
$0.30 $1.20 204,800 1.27 59 No No
Llama-3.3-70B-Instruct
groq
$0.59 $0.79 131,072 0.23 261 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
$0.11 $0.32 131,072 1.30 45 Yes No
Llama-3.3-70B-Instruct
nebius
$0.25 $0.75 131,072 0.40 131 Yes Yes
Llama-3.3-70B-Instruct
cerebras
fastest
$0.85 $1.20 - 0.34 988 Yes No
Llama-3.3-70B-Instruct
sambanova
$0.60 $1.20 131,072 0.43 323 Yes Yes
Llama-3.3-70B-Instruct
nscale
$0.40 $0.40 131,072 0.96 17 No Yes
Llama-3.3-70B-Instruct
hyperbolic
$0.40 $0.40 131,072 1.20 113 No No
Llama-3.3-70B-Instruct
together
$0.88 $0.88 131,072 0.39 120 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai
$0.90 $0.90 131,072 0.47 119 No No
Llama-3.3-70B-Instruct
scaleway
- - - 0.49 61 Yes Yes
Llama-3.3-70B-Instruct
ovhcloud
$0.74 $0.74 131,072 0.58 23 Yes Yes
Qwen3-Next-80B-A3B-Instruct
novita
$0.12 $1.20 131,072 0.97 95 Yes Yes
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
$0.30 $0.30 262,144 0.63 159 Yes No
Qwen3-Next-80B-A3B-Instruct
together
$0.15 $1.50 262,144 0.54 146 Yes Yes
Olmo-3-7B-Instruct
publicai
$0.00 $0.00 - 2.24 37 No Yes
Qwen2.5-VL-7B-Instruct
hyperbolic
$0.20 $0.20 32,768 0.66 112 No No
DeepSeek-V3.2-Exp
novita
$0.22 $0.33 163,840 1.03 31 Yes Yes
DeepSeek-R1
novita
cheapest
$0.56 $2.00 64,000 1.33 28 Yes No
DeepSeek-R1
sambanova
fastest
- - - 2.40 153 Yes No
DeepSeek-R1
hyperbolic
$2.00 $2.00 163,840 0.85 47 No No
DeepSeek-R1
together
$3.00 $7.00 163,840 0.63 43 No Yes
DeepSeek-R1
fireworks-ai
- - - - - - -
GLM-4.5-Air
novita
cheapest fastest
$0.10 $0.68 131,072 1.01 94 Yes No
GLM-4.5-Air
nebius
$0.20 $1.20 131,072 0.44 63 Yes Yes
GLM-4.5-Air
fireworks-ai
- - - - - - -
GLM-4.5-Air
zai-org
- - - 2.26 75 Yes No
Kimi-K2-Instruct
novita
cheapest
$0.46 $1.84 131,072 0.91 30 Yes Yes
Kimi-K2-Instruct
nebius
fastest
$0.50 $2.40 131,072 0.56 71 Yes Yes
Kimi-K2-Instruct
together
$1.00 $3.00 131,072 0.60 46 Yes No
Kimi-K2-Instruct
fireworks-ai
- - - - - - -
Kimi-K2-Instruct-0905
groq
fastest
- - 262,144 0.31 178 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
$0.48 $2.00 262,144 1.24 45 Yes Yes
Kimi-K2-Instruct-0905
together
$1.00 $3.00 262,144 0.63 45 Yes Yes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11 $0.34 131,072 0.40 352 Yes No
Llama-4-Scout-17B-16E-Instruct
novita
$0.08 $0.40 131,072 0.84 38 No No
Llama-4-Scout-17B-16E-Instruct
sambanova
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09 $0.29 890,000 1.00 26 Yes Yes
Llama-4-Scout-17B-16E-Instruct
together
$0.18 $0.59 1,048,576 0.47 109 Yes Yes
Llama-4-Scout-17B-16E-Instruct
fireworks-ai
- - - - - - -
Qwen3-30B-A3B-Thinking-2507
nebius
$0.10 $0.30 262,144 0.45 107 Yes Yes
DeepSeek-R1-0528-Qwen3-8B
novita
$0.05 $0.07 128,000 1.09 67 No No
gemma-2-2b-it
nebius
$0.02 $0.06 8,192 0.51 171 No No
DeepSeek-R1-Distill-Qwen-32B
novita
cheapest fastest
$0.24 $0.24 64,000 0.83 60 No Yes
DeepSeek-R1-Distill-Qwen-32B
nscale
$0.30 $0.30 131,072 1.14 25 No No
Olmo-3-7B-Think
publicai
$0.00 $0.00 - 3.59 98 No Yes
Qwen2.5-72B-Instruct
novita
cheapest
$0.30 $0.32 32,000 1.66 19 Yes No
Qwen2.5-72B-Instruct
hyperbolic
$0.40 $0.40 131,072 0.95 46 Yes No
Qwen2.5-72B-Instruct
together
fastest
$1.20 $1.20 131,072 0.48 80 Yes Yes
Qwen2.5-72B-Instruct
fireworks-ai
- - - - - - -
Qwen3-14B
nscale
$0.07 $0.20 40,960 1.00 48 No No
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest fastest
$0.20 $0.60 131,072 0.36 436 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova
$0.63 $1.80 131,072 1.49 333 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
fireworks-ai
$0.22 $0.88 1,048,576 0.40 96 Yes No
DeepSeek-R1-Distill-Qwen-1.5B
nscale
$0.10 $0.10 131,072 1.01 136 No No
SmolLM3-3B
hf-inference
- - - 0.22 85 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30 $1.30 262,144 1.31 33 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
nebius
$0.40 $1.80 262,144 0.36 68 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
cerebras
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00 $2.00 262,144 1.28 75 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
$2.00 $2.00 262,144 0.76 45 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
fireworks-ai
$0.45 $1.80 262,144 4.45 22 No No
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.07 $0.46 131,072 1.09 21 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nebius
$0.20 $0.60 262,144 0.55 70 Yes Yes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60 $1.20 - 0.33 397 Yes No
Qwen3-235B-A22B-Instruct-2507
nscale
$0.20 $0.60 32,768 1.18 24 Yes Yes
Qwen3-235B-A22B-Instruct-2507
hyperbolic
$2.00 $2.00 262,144 1.36 32 Yes No
Qwen3-235B-A22B-Instruct-2507
together
$0.20 $0.60 262,144 0.84 27 Yes Yes
Qwen3-235B-A22B-Instruct-2507
fireworks-ai
$0.22 $0.88 262,144 0.75 55 Yes No
Qwen3-235B-A22B-Instruct-2507
scaleway
- - - 0.57 43 Yes Yes
DeepSeek-V3
novita
cheapest fastest
$0.32 $1.04 64,000 1.25 31 Yes No
DeepSeek-V3
together
$1.25 $1.25 131,072 1.83 11 Yes Yes
DeepSeek-V3
fireworks-ai
- - - - - - -
NVIDIA-Nemotron-Nano-12B-v2
nebius
$0.07 $0.20 131,072 0.49 120 No Yes
Qwen3-VL-235B-A22B-Instruct
novita
$0.24 $1.20 131,072 0.75 45 Yes Yes
Qwen3-VL-235B-A22B-Thinking
novita
$0.78 $3.16 131,072 0.99 49 No No
Qwen3-VL-30B-A3B-Thinking
novita
$0.16 $0.80 131,072 1.20 76 Yes No
Qwen3-235B-A22B
novita
$0.16 $0.64 40,960 1.17 32 No No
Qwen3-235B-A22B
nscale
cheapest
$0.20 $0.60 32,000 1.10 23 Yes Yes
Qwen3-235B-A22B
together
$0.20 $0.60 40,960 0.60 46 Yes Yes
Qwen3-235B-A22B
fireworks-ai
fastest
$0.22 $0.88 131,072 0.53 81 Yes No
Qwen3-32B
groq
$0.29 $0.59 131,072 0.30 250 Yes No
Qwen3-32B
novita
$0.08 $0.36 40,960 0.87 57 No No
Qwen3-32B
nebius
$0.10 $0.30 40,960 0.49 49 Yes Yes
Qwen3-32B
cerebras
fastest
$0.40 $0.80 - 0.34 1,137 Yes No
Qwen3-32B
sambanova
$0.40 $0.80 32,768 2.86 187 Yes Yes
Qwen3-32B
nscale
cheapest
$0.08 $0.25 40,960 0.95 25 Yes Yes
Qwen3-32B
ovhcloud
$0.09 $0.25 32,768 0.47 33 Yes Yes
DeepSeek-R1-Distill-Llama-8B
novita
- - - - - - -
DeepSeek-R1-Distill-Llama-8B
nscale
$0.05 $0.05 131,072 0.89 56 No Yes
QwQ-32B
groq
- - - - - - -
QwQ-32B
nebius
- - - - - - -
QwQ-32B
sambanova
- - - - - - -
QwQ-32B
nscale
$0.18 $0.20 131,072 1.06 27 Yes Yes
QwQ-32B
hyperbolic
- - - - - - -
QwQ-32B
fireworks-ai
- - - - - - -
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06 $0.20 131,072 1.12 26 No Yes
Qwen2.5-Coder-32B-Instruct
hyperbolic
$0.20 $0.20 32,768 1.97 45 No No
Qwen2.5-Coder-32B-Instruct
together
- - - - - - -
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
- - - 0.57 102 Yes No
DeepSeek-R1-Distill-Qwen-14B
novita
cheapest fastest
$0.12 $0.12 32,768 1.02 55 No No
DeepSeek-R1-Distill-Qwen-14B
nscale
$0.20 $0.20 131,072 1.02 37 No Yes
Qwen2.5-Coder-7B-Instruct
nscale
$0.01 $0.03 131,072 0.82 62 No Yes
Arch-Router-1.5B
hf-inference
- - - 0.23 77 No Yes
gpt-oss-safeguard-20b
groq
- - 131,072 0.29 756 Yes No
Qwen3-30B-A3B
novita
cheapest
$0.07 $0.36 40,960 0.99 91 No No
Qwen3-30B-A3B
fireworks-ai
fastest
$0.15 $0.60 131,072 0.73 163 Yes No
Qwen3-Coder-480B-A35B-Instruct-FP8
together
$2.00 $2.00 262,144 0.65 46 Yes Yes
Apertus-8B-Instruct-2509
publicai
$0.00 $0.00 - 1.77 46 No Yes
L3-8B-Stheno-v3.2
novita
$0.05 $0.05 8,192 0.79 86 No No
gemma-2-9b-it
groq
- - - - - - -
gemma-2-9b-it
nebius
$0.03 $0.09 8,192 0.29 135 No Yes
Qwen3-235B-A22B-Thinking-2507
novita
$0.24 $2.40 131,072 0.84 40 Yes No
Qwen3-235B-A22B-Thinking-2507
nebius
cheapest
$0.20 $0.80 262,144 0.53 31 Yes Yes
Qwen3-235B-A22B-Thinking-2507
cerebras
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
fireworks-ai
fastest
$0.22 $0.88 262,144 0.68 66 Yes No
Qwen3-VL-32B-Instruct
together
$0.50 $1.50 262,144 0.34 50 No Yes
GLM-4.6-FP8
zai-org
- - - 2.80 49 Yes No
DeepSeek-R1-Distill-Llama-70B
groq
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
novita
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
$0.70 $1.40 131,072 0.92 199 No No
DeepSeek-R1-Distill-Llama-70B
nscale
$0.75 $0.75 131,072 0.94 16 No Yes
DeepSeek-R1-Distill-Llama-70B
scaleway
- - - 0.79 24 No Yes
DeepSeek-R1-Distill-Llama-70B
ovhcloud
cheapest
$0.74 $0.74 131,072 0.47 30 No Yes
GLM-4.5-Air-FP8
together
$0.20 $1.10 131,072 0.40 99 Yes Yes
DeepSeek-R1-0528
novita
cheapest
$0.56 $2.00 163,840 1.47 33 Yes No
DeepSeek-R1-0528
nebius
$0.80 $2.40 163,840 0.90 23 No Yes
DeepSeek-R1-0528
sambanova
fastest
$5.00 $7.00 131,072 2.93 117 Yes No
DeepSeek-R1-0528
hyperbolic
$3.00 $3.00 163,840 0.78 42 No No
DeepSeek-R1-0528
together
$3.00 $7.00 163,840 0.59 42 No Yes
DeepSeek-R1-0528
fireworks-ai
$3.00 $8.00 163,840 0.61 66 No No
Qwen2.5-Coder-7B
nebius
$0.03 $0.09 32,768 0.48 155 No Yes
command-a-reasoning-08-2025
cohere
- - - 0.32 91 Yes No
Hermes-4-405B
nebius
$1.00 $3.00 131,072 0.49 36 No No
DeepSeek-R1-Distill-Qwen-7B
nscale
$0.15 $0.15 131,072 0.93 66 No No
GLM-4.5
novita
cheapest
$0.48 $1.76 131,072 0.71 23 Yes No
GLM-4.5
nebius
$0.60 $2.20 131,072 0.49 38 Yes Yes
GLM-4.5
fireworks-ai
fastest
$0.55 $2.19 131,072 0.74 95 Yes No
GLM-4.5
zai-org
- - - 3.48 39 Yes No
Llama-3_1-Nemotron-Ultra-253B-v1
nebius
$0.60 $1.80 131,072 0.57 39 No Yes
Qwen2.5-VL-72B-Instruct
nebius
$0.25 $0.75 32,000 0.58 27 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest
$0.60 $0.60 32,768 0.68 9 No No
Qwen2.5-VL-72B-Instruct
ovhcloud
fastest
$1.01 $1.01 32,768 0.69 27 No Yes
Qwen3-Next-80B-A3B-Thinking
novita
$0.12 $1.20 131,072 1.19 82 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30 $0.30 262,144 0.69 185 Yes No
Qwen3-Next-80B-A3B-Thinking
together
$0.15 $1.50 262,144 0.58 140 Yes Yes
GLM-4.6V-FP8
zai-org
- - - 2.20 79 Yes No
Meta-Llama-3-70B-Instruct
groq
- - - - - - -
Meta-Llama-3-70B-Instruct
novita
$0.51 $0.74 8,192 1.04 29 No Yes
Meta-Llama-3-70B-Instruct
hyperbolic
cheapest fastest
$0.40 $0.40 8,192 0.76 70 No No
Meta-Llama-3-70B-Instruct
together
$0.88 $0.88 8,192 0.57 42 No Yes
Llama-Guard-4-12B
groq
$0.20 $0.20 131,072 0.27 7 No No
Qwen2.5-VL-32B-Instruct
fireworks-ai
$0.22 $0.88 128,000 0.46 67 No No
GLM-4.5V
novita
cheapest fastest
$0.48 $1.44 65,536 1.48 29 Yes No
GLM-4.5V
zai-org
- - - 3.80 27 No No
c4ai-command-r7b-12-2024
cohere
- - - 0.32 129 Yes No
GLM-4.5V-FP8
zai-org
- - - 3.04 39 Yes No
c4ai-command-a-03-2025
cohere
- - - 0.33 86 Yes No
ERNIE-4.5-VL-28B-A3B-PT
novita
$0.11 $0.45 30,000 0.95 80 No No
GLM-4.1V-9B-Thinking
novita
$0.03 $0.11 65,536 0.77 68 No No
Qwen-SEA-LION-v4-32B-IT
publicai
$0.00 $0.00 - 2.03 43 Yes Yes
L3-70B-Euryale-v2.1
novita
$1.48 $1.48 8,192 1.42 35 No No
DictaLM-3.0-24B-Thinking
publicai
$0.00 $0.00 - 1.93 62 Yes Yes
Baichuan-M2-32B
novita
$0.06 $0.06 131,072 1.62 41 No Yes
WizardLM-2-8x22B
novita
$0.50 $0.50 65,535 0.61 43 No No
Qwen2.5-Coder-3B-Instruct
nscale
$0.01 $0.03 32,768 0.99 84 No Yes
DeepSeek-V3-0324
novita
cheapest
$0.22 $0.90 163,840 0.92 33 Yes Yes
DeepSeek-V3-0324
nebius
$0.75 $2.25 32,768 1.08 115 No No
DeepSeek-V3-0324
sambanova
fastest
$3.00 $4.50 131,072 0.95 179 Yes Yes
DeepSeek-V3-0324
hyperbolic
$1.25 $1.25 163,840 1.81 16 No No
DeepSeek-V3-0324
together
$1.25 $1.25 131,072 1.93 11 Yes Yes
DeepSeek-V3-0324
fireworks-ai
$0.90 $0.90 163,840 0.59 35 Yes No
ERNIE-4.5-0.3B-PT
novita
- - 120,000 1.06 96 No No
ERNIE-4.5-VL-424B-A47B-Base-PT
novita
$0.34 $1.00 123,000 1.38 43 No No
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20 $1.20 65,536 1.01 25 No Yes
Mixtral-8x22B-Instruct-v0.1
together
- - - - - - -
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20 $1.20 65,536 0.54 69 No No
DeepSeek-V3.1-Terminus
novita
$0.22 $0.80 131,072 1.48 26 Yes Yes
ERNIE-4.5-21B-A3B-PT
novita
$0.06 $0.22 120,000 0.98 79 No No
marin-8b-instruct
together
$0.18 $0.18 4,096 0.30 175 No Yes
Qwen3-235B-A22B-FP8
together
$0.20 $0.60 40,960 0.64 47 Yes Yes
DeepSeek-V3.1
novita
cheapest
$0.22 $0.80 131,072 1.12 25 Yes Yes
DeepSeek-V3.1
together
$0.60 $1.70 131,072 1.55 56 Yes Yes
DeepSeek-V3.1
fireworks-ai
fastest
- - 163,840 0.60 83 Yes No
cogito-v2-preview-llama-405B
together
$3.50 $3.50 32,768 0.50 27 Yes Yes
cogito-v2-preview-llama-109B-MoE
together
$0.18 $0.59 32,767 0.29 73 Yes Yes
cogito-v2-preview-llama-70B
together
$0.88 $0.88 32,768 0.52 54 Yes Yes
command-a-translate-08-2025
cohere
- - - 0.26 93 Yes No
cogito-671b-v2.1-FP8
together
$1.25 $1.25 163,840 0.37 62 No Yes
cogito-671b-v2.1
together
cheapest fastest
$1.25 $1.25 163,840 0.37 58 No Yes
cogito-671b-v2.1
fireworks-ai
- - 163,840 0.76 44 Yes No
command-a-vision-07-2025
cohere
- - - 0.28 43 No No
c4ai-command-r7b-arabic-02-2025
cohere
- - - 0.39 87 Yes No
aya-vision-32b
cohere
- - - 1.55 27 No No
c4ai-command-r-08-2024
cohere
- - - 0.41 44 Yes No
aya-expanse-32b
cohere
- - - 0.29 42 No No
L3-8B-Lunaris-v1
novita
$0.05 $0.05 8,192 0.87 68 No No
Hermes-2-Pro-Llama-3-8B
novita
$0.14 $0.14 8,192 1.07 89 No No
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova
$0.60 $1.20 131,072 2.91 147 No Yes
Hermes-4-70B
nebius
$0.13 $0.40 131,072 0.39 81 No No
INTELLECT-3-FP8
nebius
$0.20 $1.10 131,072 0.69 58 Yes Yes
ERNIE-4.5-300B-A47B-Base-PT
novita
$0.22 $0.88 123,000 1.07 22 No Yes
MiniMax-M1-80k
novita
$0.44 $1.76 1,000,000 1.59 62 Yes No
DeepSeek-Prover-V2-671B
novita
$0.56 $2.00 160,000 1.52 9 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
$0.16 $0.72 1,048,576 0.50 36 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
$0.27 $0.85 1,048,576 0.53 116 Yes Yes
Apertus-70B-Instruct-2509
publicai
$0.00 $0.00 - 1.53 57 No Yes
Gemma-SEA-LION-v4-27B-IT
publicai
$0.00 $0.00 - 1.99 48 No Yes