Inference Providers

·

Metrics for top trending models

GLM-5
novita
cheapest
$1.00 $3.20 202,800 2.01 33 Yes No
GLM-5
together
fastest
$1.00 $3.20 202,752 0.51 35 Yes Yes
GLM-5
- - - 3.44 32 Yes No
MiniMax-M2.5
$0.30 $1.20 204,800 3.52 27 No No
Qwen3.5-397B-A17B
$0.60 $3.60 262,144 1.01 109 Yes No
Kimi-K2.5
$0.60 $3.00 262,144 1.11 39 Yes Yes
Kimi-K2.5
together
cheapest
$0.50 $2.80 262,144 0.99 41 Yes Yes
Kimi-K2.5
fireworks-ai
fastest
- - 262,144 1.41 103 Yes No
Qwen3-Coder-Next
$0.20 $1.50 262,144 0.84 147 Yes Yes
GLM-4.7-Flash
novita
cheapest
$0.07 $0.40 200,000 0.75 53 No No
GLM-4.7-Flash
zai-org
fastest
- - - 2.32 54 No No
gpt-oss-20b
groq
fastest
$0.10 $0.50 131,072 0.13 854 Yes No
gpt-oss-20b
$0.04 $0.15 131,072 0.50 147 No Yes
gpt-oss-20b
$0.05 $0.20 131,072 0.76 129 Yes Yes
gpt-oss-20b
hyperbolic
cheapest
$0.10 $0.10 131,072 0.69 68 Yes No
gpt-oss-20b
$0.05 $0.20 131,072 0.24 110 Yes Yes
gpt-oss-20b
$0.05 $0.20 131,072 0.27 135 Yes No
gpt-oss-20b
$0.05 $0.18 131,072 0.42 105 Yes Yes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02 $0.05 16,384 0.68 68 No No
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10 $0.10 - 0.24 1,253 No No
Llama-3.1-8B-Instruct
$0.10 $0.20 16,384 0.44 688 Yes Yes
Llama-3.1-8B-Instruct
$0.06 $0.06 131,072 0.81 60 No Yes
Llama-3.1-8B-Instruct
- - - - - - -
Llama-3.1-8B-Instruct
- - - 0.36 98 Yes Yes
Llama-3.1-8B-Instruct
$0.11 $0.11 131,072 0.28 42 Yes Yes
gpt-oss-120b
$0.15 $0.75 131,072 0.10 449 Yes No
gpt-oss-120b
novita
cheapest
$0.05 $0.25 131,072 0.38 55 Yes No
gpt-oss-120b
cerebras
fastest
$0.25 $0.69 - 0.21 1,220 Yes No
gpt-oss-120b
$0.22 $0.59 131,072 1.12 491 Yes Yes
gpt-oss-120b
$0.10 $0.40 131,072 0.75 83 Yes Yes
gpt-oss-120b
$0.30 $0.30 131,072 0.72 270 Yes No
gpt-oss-120b
$0.15 $0.60 131,072 2.28 49 Yes Yes
gpt-oss-120b
$0.15 $0.60 131,072 0.54 63 Yes No
gpt-oss-120b
- - - 0.36 202 Yes No
gpt-oss-120b
$0.09 $0.47 131,072 0.54 44 Yes Yes
MiniMax-M2.1
$0.30 $1.20 204,800 1.23 48 No No
Qwen3-8B
$0.07 $0.18 40,960 0.77 56 Yes No
DeepSeek-V3.2
novita
cheapest
$0.27 $0.40 163,840 1.37 33 Yes Yes
DeepSeek-V3.2
fireworks-ai
fastest
- - 163,840 2.88 46 Yes No
MiniMax-M2
$0.30 $1.20 204,800 3.28 35 Yes No
Qwen3-4B-Instruct-2507
$0.01 $0.03 262,144 0.79 60 Yes No
GLM-4.7
novita
cheapest fastest
$0.60 $2.20 204,800 0.89 72 No Yes
GLM-4.7
- - - - - - -
GLM-4.7
- - - 1.84 70 Yes No
Qwen3-Coder-Next-FP8
$0.50 $1.20 262,144 0.85 125 Yes Yes
gemma-3-27b-it
- - - 0.50 48 Yes Yes
Qwen2.5-Coder-7B-Instruct
$0.01 $0.03 131,072 0.81 62 No Yes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08 $0.50 131,072 0.76 46 Yes Yes
Qwen3-VL-8B-Instruct
together
fastest
$0.18 $0.68 262,144 0.35 128 Yes Yes
DeepSeek-R1
$0.70 $2.50 64,000 1.04 29 Yes No
DeepSeek-R1
sambanova
fastest
- - - 0.87 132 Yes Yes
DeepSeek-R1
hyperbolic
cheapest
$2.00 $2.00 163,840 0.72 64 No No
DeepSeek-R1
$3.00 $7.00 163,840 0.47 58 No Yes
DeepSeek-R1
- - - - - - -
DeepSeek-OCR
$0.03 $0.03 8,192 0.65 144 No No
GLM-4.6V-Flash
novita
cheapest
$0.30 $0.90 131,072 1.11 40 Yes No
GLM-4.6V-Flash
zai-org
fastest
- - - 1.31 78 Yes No
Llama-3.2-3B-Instruct
- - - - - - -
Llama-3.2-3B-Instruct
- - - - - - -
Llama-3.2-3B-Instruct
$0.10 $0.10 131,072 0.66 134 Yes No
Llama-3.2-3B-Instruct
together
cheapest fastest
$0.06 $0.06 131,072 0.30 146 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
- - - 0.37 71 Yes No
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07 $0.26 262,144 0.37 71 Yes Yes
Qwen2.5-7B-Instruct
$0.30 $0.30 32,768 0.35 114 Yes Yes
Llama-3.3-70B-Instruct
$0.59 $0.79 131,072 0.11 262 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
$0.14 $0.40 131,072 0.72 31 Yes No
Llama-3.3-70B-Instruct
cerebras
fastest
$0.85 $1.20 - 0.24 1,029 Yes No
Llama-3.3-70B-Instruct
$0.60 $1.20 131,072 0.37 307 Yes Yes
Llama-3.3-70B-Instruct
$0.40 $0.40 131,072 1.08 16 No Yes
Llama-3.3-70B-Instruct
$0.40 $0.40 131,072 0.73 128 Yes No
Llama-3.3-70B-Instruct
$0.88 $0.88 131,072 0.98 64 Yes Yes
Llama-3.3-70B-Instruct
- - - - - - -
Llama-3.3-70B-Instruct
- - - 0.31 81 Yes Yes
Llama-3.3-70B-Instruct
$0.74 $0.74 131,072 0.45 37 Yes Yes
Kimi-K2-Thinking
novita
cheapest
$0.60 $2.50 262,144 0.90 47 Yes No
Kimi-K2-Thinking
together
fastest
$1.20 $4.00 262,144 1.03 109 Yes Yes
Qwen3-VL-30B-A3B-Instruct
$0.20 $0.70 131,072 0.78 114 Yes Yes
Qwen3-32B
$0.29 $0.59 131,072 0.24 254 Yes No
Qwen3-32B
$0.10 $0.45 40,960 0.54 45 No No
Qwen3-32B
cerebras
fastest
$0.40 $0.80 - 0.26 1,139 Yes No
Qwen3-32B
$0.40 $0.80 32,768 2.35 208 Yes Yes
Qwen3-32B
nscale
cheapest
$0.08 $0.25 40,960 0.78 28 Yes Yes
Qwen3-32B
$0.09 $0.25 32,768 0.34 41 Yes Yes
MiMo-V2-Flash
$0.10 $0.30 262,144 1.34 45 Yes No
Qwen3-14B
$0.07 $0.20 40,960 0.79 51 Yes Yes
Qwen3-4B-Thinking-2507
$0.01 $0.03 262,144 0.83 96 Yes No
Llama-3.2-1B-Instruct
- - 131,000 0.63 189 No No
Llama-3.2-1B-Instruct
- - - - - - -
Llama-3.2-1B-Instruct
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30 $1.30 262,144 1.04 47 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
$2.00 $2.00 262,144 0.72 52 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00 $2.00 262,144 0.50 64 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
- - - - - - -
Qwen3-30B-A3B
$0.09 $0.45 40,960 0.97 70 Yes No
Qwen3-30B-A3B
- - - - - - -
Qwen3-Next-80B-A3B-Instruct
$0.15 $1.50 131,072 0.90 108 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
$0.30 $0.30 262,144 0.51 174 No No
Qwen3-Next-80B-A3B-Instruct
$0.15 $1.50 262,144 0.55 117 Yes Yes
Apriel-1.6-15b-Thinker
$0.00 $0.00 131,072 0.16 150 No No
DeepSeek-R1-Distill-Qwen-32B
- - - - - - -
DeepSeek-R1-Distill-Qwen-32B
$0.30 $0.30 131,072 0.96 28 No Yes
Qwen2.5-VL-7B-Instruct
$0.20 $0.20 32,768 0.49 93 No No
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09 $0.58 131,072 0.94 22 Yes Yes
Qwen3-235B-A22B-Instruct-2507
- - - - - - -
Qwen3-235B-A22B-Instruct-2507
$0.20 $0.60 32,768 1.11 23 Yes Yes
Qwen3-235B-A22B-Instruct-2507
$2.00 $2.00 262,144 0.82 69 Yes No
Qwen3-235B-A22B-Instruct-2507
$0.20 $0.60 262,144 0.39 44 Yes Yes
Qwen3-235B-A22B-Instruct-2507
- - - - - - -
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
- - - 0.41 81 Yes Yes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06 $0.20 131,072 0.81 28 No Yes
Qwen2.5-Coder-32B-Instruct
$0.20 $0.20 32,768 0.51 40 No No
Qwen2.5-Coder-32B-Instruct
- - - - - - -
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
- - - 0.42 90 Yes No
Qwen2.5-72B-Instruct
$0.38 $0.40 32,000 0.93 34 Yes No
Qwen2.5-72B-Instruct
- - - - - - -
Qwen2.5-72B-Instruct
- - - - - - -
Qwen2.5-72B-Instruct
- - - - - - -
DeepSeek-R1-Distill-Qwen-7B
$0.15 $0.15 131,072 0.81 66 No No
Qwen3-VL-235B-A22B-Instruct
$0.30 $1.50 131,072 0.81 25 Yes Yes
Qwen3-VL-235B-A22B-Thinking
$0.98 $3.95 131,072 1.01 47 No No
Mistral-7B-Instruct-v0.2
$0.20 $0.20 32,768 0.23 90 No Yes
GLM-4.6V
- - - - - - -
GLM-4.6V
- - - 3.65 37 Yes No
Meta-Llama-3-8B-Instruct
- - - - - - -
Meta-Llama-3-8B-Instruct
$0.04 $0.04 8,192 0.76 75 No No
Meta-Llama-3-8B-Instruct
- - - - - - -
DeepSeek-V3
$0.40 $1.30 64,000 1.71 28 Yes No
DeepSeek-V3
together
cheapest fastest
$1.25 $1.25 131,072 1.52 81 Yes Yes
DeepSeek-V3
- - - - - - -
Kimi-K2-Instruct
novita
cheapest
$0.57 $2.30 131,072 1.09 29 Yes Yes
Kimi-K2-Instruct
together
fastest
$1.00 $3.00 131,072 0.66 44 Yes Yes
Kimi-K2-Instruct
- - - - - - -
Qwen3-VL-30B-A3B-Thinking
$0.20 $1.00 131,072 0.83 93 Yes No
gemma-3n-E4B-it
$0.02 $0.04 32,768 0.31 33 No Yes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11 $0.34 131,072 0.12 370 Yes No
Llama-4-Scout-17B-16E-Instruct
$0.18 $0.59 131,072 0.40 91 No No
Llama-4-Scout-17B-16E-Instruct
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09 $0.29 890,000 0.82 33 Yes Yes
Llama-4-Scout-17B-16E-Instruct
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
- - - - - - -
Qwen3-235B-A22B
$0.20 $0.80 40,960 2.86 7 No No
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20 $0.60 32,000 0.93 22 Yes Yes
Qwen3-235B-A22B
- - - - - - -
Qwen3-235B-A22B
- - - - - - -
Llama-3.1-70B-Instruct
- - - - - - -
Llama-3.1-70B-Instruct
- - - 0.49 77 Yes Yes
EuroLLM-22B-Instruct-2512
$0.10 $0.20 - - - No No
GLM-4.5-Air
novita
cheapest
$0.13 $0.85 131,072 0.63 53 Yes No
GLM-4.5-Air
- - - - - - -
GLM-4.5-Air
zai-org
fastest
- - - 2.06 69 Yes No
DeepSeek-V3.2-Exp
$0.27 $0.41 163,840 0.84 36 Yes Yes
Qwen3-VL-32B-Instruct
$0.50 $1.50 262,144 1.34 94 Yes Yes
DeepSeek-V3.1
novita
cheapest
$0.27 $1.00 131,072 1.21 39 Yes Yes
DeepSeek-V3.1
together
fastest
$0.60 $1.70 131,072 0.87 87 Yes Yes
DeepSeek-V3.1
- - 163,840 0.53 83 Yes No
GLM-4.5V
novita
cheapest fastest
$0.60 $1.80 65,536 0.67 65 Yes No
GLM-4.5V
- - - - - - -
GLM-4.5V
- - - 2.14 51 Yes No
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
$0.60 $0.60 32,768 0.60 43 No No
Qwen2.5-VL-72B-Instruct
$1.01 $1.01 32,768 0.57 33 No Yes
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest fastest
$0.20 $0.60 131,072 0.24 467 Yes No
Llama-4-Maverick-17B-128E-Instruct
$0.63 $1.80 131,072 3.63 148 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
- - - - - - -
rnj-1-instruct
$0.15 $0.15 32,768 0.23 121 Yes Yes
Apertus-8B-Instruct-2509
$0.10 $0.20 - 1.66 85 No Yes
Kimi-K2-Instruct-0905
groq
fastest
- - 262,144 0.10 174 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
$0.60 $2.50 262,144 1.14 24 Yes Yes
Kimi-K2-Instruct-0905
$1.00 $3.00 262,144 0.59 46 Yes Yes
gpt-oss-safeguard-20b
- - 131,072 0.09 898 Yes No
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest fastest
$0.27 $0.85 1,048,576 0.54 68 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27 $0.85 1,048,576 0.29 48 Yes Yes
Olmo-3.1-32B-Think
$0.15 $0.50 - 1.72 88 No No
Olmo-3.1-32B-Instruct
$0.20 $0.60 - 2.06 51 Yes Yes
Molmo2-8B
- - - 2.00 133 No Yes
Arch-Router-1.5B
- - - 0.12 73 No Yes
SmolLM3-3B
- - - 0.10 91 Yes Yes
WizardLM-2-8x22B
$0.62 $0.62 65,535 0.65 62 No No
Qwen3-Next-80B-A3B-Thinking
$0.15 $1.50 131,072 0.75 155 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30 $0.30 262,144 0.63 187 Yes No
Qwen3-Next-80B-A3B-Thinking
$0.15 $1.50 262,144 0.82 160 Yes Yes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00 $2.00 262,144 0.44 63 Yes Yes
AutoGLM-Phone-9B-Multilingual
$0.04 $0.14 65,536 0.81 67 No No
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20 $1.20 65,536 0.92 19 No Yes
Mixtral-8x22B-Instruct-v0.1
- - - - - - -
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20 $1.20 65,536 0.41 70 No No
Qwen3-235B-A22B-Thinking-2507
$0.30 $3.00 131,072 0.59 71 Yes No
Qwen3-235B-A22B-Thinking-2507
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
- - - - - - -
L3-8B-Stheno-v3.2
$0.05 $0.05 8,192 0.69 40 No No
NVIDIA-Nemotron-Nano-9B-v2
$0.06 $0.25 131,072 0.67 105 Yes Yes
GLM-4.6
novita
cheapest
$0.55 $2.20 204,800 1.41 74 Yes No
GLM-4.6
- - - - - - -
GLM-4.6
$0.60 $2.20 202,752 0.77 66 Yes No
GLM-4.6
zai-org
fastest
- - - 1.78 86 Yes No
aya-expanse-32b
- - - 0.19 42 No No
DeepSeek-V3-0324
novita
cheapest
$0.27 $1.12 163,840 1.00 36 Yes Yes
DeepSeek-V3-0324
sambanova
fastest
$3.00 $4.50 131,072 0.65 159 Yes Yes
DeepSeek-V3-0324
$1.25 $1.25 163,840 1.01 67 Yes No
DeepSeek-V3-0324
$1.25 $1.25 131,072 0.69 88 Yes Yes
DeepSeek-V3-0324
- - - - - - -
GLM-4.5
novita
cheapest fastest
$0.60 $2.20 131,072 0.67 60 Yes No
GLM-4.5
- - - - - - -
GLM-4.5
- - - 2.06 49 Yes No
Trinity-Mini
$0.05 $0.15 128,000 0.17 171 Yes Yes
Gemma-SEA-LION-v4-27B-IT
$0.20 $0.40 - 1.97 46 No Yes
aya-vision-32b
- - - 0.30 37 No No
c4ai-command-a-03-2025
- - - 0.23 45 Yes No
DeepSeek-R1-Distill-Llama-8B
- - - - - - -
DeepSeek-R1-Distill-Llama-8B
$0.05 $0.05 131,072 0.73 57 No No
DeepSeek-R1-Distill-Qwen-1.5B
$0.10 $0.10 131,072 0.98 138 No No
DeepSeek-Prover-V2-671B
$0.70 $2.50 160,000 1.94 9 No No
Apertus-70B-Instruct-2509
$0.82 $2.92 - 1.86 57 No Yes
Olmo-3-7B-Instruct
$0.10 $0.20 - - - Yes No
cogito-671b-v2.1
together
cheapest fastest
$1.25 $1.25 163,840 0.24 59 No Yes
cogito-671b-v2.1
- - 163,840 0.34 40 Yes No
cogito-671b-v2.1-FP8
$1.25 $1.25 163,840 0.23 59 No Yes
DeepSeek-V3.1-Terminus
$0.27 $1.00 131,072 1.12 39 Yes Yes
L3-8B-Lunaris-v1
$0.05 $0.05 8,192 3.07 25 No No
L3-70B-Euryale-v2.1
$1.48 $1.48 8,192 0.72 35 No No
Hermes-2-Pro-Llama-3-8B
$0.14 $0.14 8,192 0.69 101 No No
Meta-Llama-3-70B-Instruct
- - - - - - -
Meta-Llama-3-70B-Instruct
$0.51 $0.74 8,192 0.70 22 No Yes
Meta-Llama-3-70B-Instruct
- - - - - - -
Meta-Llama-3-70B-Instruct
- - - - - - -
GLM-4.5V-FP8
- - - 2.38 48 Yes No
GLM-4-32B-0414
$0.55 $1.66 32,000 0.86 40 No No
GLM-4.7-FP8
together
cheapest
$0.45 $2.00 202,752 0.55 63 Yes No
GLM-4.7-FP8
zai-org
fastest
- - - 2.37 80 Yes No
DeepSeek-R1-Distill-Llama-70B
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
$0.80 $0.80 8,192 0.67 57 No No
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
$0.70 $1.40 131,072 0.76 123 No No
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75 $0.75 131,072 1.06 16 No Yes
DeepSeek-R1-Distill-Llama-70B
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
- - - 0.63 25 No Yes
DeepSeek-R1-Distill-Llama-70B
- - - - - - -
GLM-4.6V-FP8
- - - 2.93 57 Yes No
Llama-3.3-Swallow-70B-Instruct-v0.4
$0.60 $1.20 131,072 2.63 130 No No
DeepSeek-R1-0528
$0.70 $2.50 163,840 1.38 32 Yes No
DeepSeek-R1-0528
sambanova
fastest
$5.00 $7.00 131,072 0.63 159 Yes Yes
DeepSeek-R1-0528
$3.00 $3.00 163,840 0.86 48 No No
DeepSeek-R1-0528
together
cheapest
$0.00 $0.00 163,840 0.65 48 No Yes
DeepSeek-R1-0528
- - - - - - -
GLM-4.6-FP8
- - - 1.51 90 Yes No
MiniMax-M1-80k
$0.55 $2.20 1,000,000 2.58 41 Yes No
ERNIE-4.5-300B-A47B-Base-PT
$0.28 $1.10 123,000 1.60 21 No Yes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42 $1.25 123,000 1.09 41 No No
ERNIE-4.5-VL-28B-A3B-PT
$0.14 $0.56 30,000 0.98 75 No No
ERNIE-4.5-21B-A3B-PT
$0.07 $0.28 120,000 0.87 73 No No
command-a-reasoning-08-2025
- - - 0.18 76 Yes No
command-a-vision-07-2025
- - - 0.16 42 No No
Llama-Guard-4-12B
$0.20 $0.20 131,072 0.26 8 No No
c4ai-command-r7b-arabic-02-2025
- - - 0.27 104 Yes No
Qwen-SEA-LION-v4-32B-IT
$0.25 $0.50 - 2.02 44 Yes Yes
DictaLM-3.0-24B-Thinking
$0.20 $0.40 - 1.70 62 Yes Yes
c4ai-command-r7b-12-2024
- - - 0.17 138 Yes No
GLM-4.5-Air-FP8
$0.20 $1.10 131,072 0.23 135 Yes Yes
marin-8b-instruct
$0.18 $0.18 4,096 0.22 171 No Yes
Qwen2.5-Coder-3B-Instruct
$0.01 $0.03 32,768 0.81 82 No Yes
c4ai-command-r-08-2024
- - - 0.19 39 Yes No
QwQ-32B
- - - - - - -
QwQ-32B
- - - - - - -
QwQ-32B
$0.18 $0.20 131,072 0.93 29 Yes Yes
QwQ-32B
- - - - - - -
QwQ-32B
- - - - - - -
command-a-translate-08-2025
- - - 0.22 65 Yes No