Inference Providers

·

Metrics for top trending models

GLM-5.2
$1.40$4.401,048,5761.7537YesYes
GLM-5.2
together
fastest
$1.40$4.40262,1440.46127YesYes
GLM-5.2
---0.7846YesNo
GLM-5.2
---4.7325NoNo
GLM-5.2
deepinfra
cheapest
$0.95$3.001,048,5760.5845YesYes
MiniMax-M3
novita
cheapest
$0.30$1.201,000,0002.1137YesNo
MiniMax-M3
$0.30$1.20524,2880.5560YesYes
MiniMax-M3
fireworks-ai
fastest
---0.71117YesNo
Kimi-K2.7-Code
$0.95$4.00262,1441.0482YesNo
Kimi-K2.7-Code
together
fastest
$0.95$4.00262,1440.49109YesYes
Kimi-K2.7-Code
---1.9291YesNo
Kimi-K2.7-Code
deepinfra
cheapest
$0.74$3.50262,1440.5938YesNo
GLM-5.2-FP8
---4.7435NoNo
DeepSeek-V4-Pro
$1.60$3.201,048,5760.6246YesNo
DeepSeek-V4-Pro
together
fastest
$1.74$3.48512,0000.9475YesYes
DeepSeek-V4-Pro
--1,048,5760.9345YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.6330YesYes
Qwen3.6-27B
ovhcloud
cheapest
$0.47$3.19262,1440.7127YesYes
Qwen3.6-27B
deepinfra
fastest
$0.32$3.20262,1440.6574YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.3148YesYes
DeepSeek-V4-Flash
$0.14$0.281,048,5761.5258YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.6590YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.10$0.201,048,5760.6318YesYes
gemma-4-31B-it
$0.14$0.40262,1441.0031YesYes
gemma-4-31B-it
together
fastest
$0.39$0.97262,1440.3273YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.4521YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1440.83106YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1440.5939YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.5317YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.3171YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4541YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1441.1727YesYes
MiMo-V2.5-Pro
$1.00$3.001,048,5760.4025NoNo
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.8929YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.5675YesYes
Kimi-K2.6
--262,1440.4767YesNo
Kimi-K2.6
$0.75$3.50262,1440.8734YesNo
GLM-5.1
$1.40$4.40202,7521.8918YesYes
GLM-5.1
fireworks-ai
fastest
--202,7521.1565YesNo
GLM-5.1
---4.3522NoNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7521.3119YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.05120YesNo
gpt-oss-120b
$0.15$0.75131,0720.20434YesNo
gpt-oss-120b
$0.05$0.25131,0720.47115YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.26967YesNo
gpt-oss-120b
$0.22$0.59131,0721.32430YesYes
gpt-oss-120b
$0.10$0.40131,0720.55116YesYes
gpt-oss-120b
$0.15$0.60131,0720.2379YesYes
gpt-oss-120b
$0.15$0.60131,0720.54193YesNo
gpt-oss-120b
---0.36161YesYes
gpt-oss-120b
$0.09$0.47131,0720.6535YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.19131,0720.3435YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
together
cheapest
$0.60$3.60512,2880.41100YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
fastest
---0.43165YesNo
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.63156NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.58147NoYes
Llama-3.1-8B-Instruct
---0.33136YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.17129YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.41276YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4146YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.5428NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.8083YesYes
Llama-3.3-70B-Instruct
---0.3684YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.8015YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1921.19105NoYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.22647YesNo
gpt-oss-20b
$0.04$0.15131,0720.68102NoYes
gpt-oss-20b
$0.05$0.20131,0720.68150YesYes
gpt-oss-20b
$0.05$0.20131,0720.29110YesYes
gpt-oss-20b
$0.05$0.20131,0720.8170YesNo
gpt-oss-20b
$0.05$0.18131,0720.4274YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.43100YesYes
DeepSeek-R1
$0.70$2.5064,0001.6025YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
GLM-5
novita
cheapest
$1.00$3.20202,8002.0816NoNo
GLM-5
together
fastest
$1.00$3.20202,7520.54106YesYes
GLM-5
---4.0534YesNo
GLM-5
-------
Step-3.7-Flash
$0.20$1.15262,1440.7817NoNo
Qwen3-8B
$0.07$0.1840,9600.65123YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1441.2589YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1441.0522YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.38101YesYes
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.7172YesYes
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1441.4847YesNo
Qwen3.5-27B
$0.26$2.60262,1440.5713YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.8647NoYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.60148NoYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.9149YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.49172YesYes
Qwen3.5-397B-A17B
---0.8153YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.5287YesYes
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.4336YesYes
Qwen3-14B
$0.07$0.2040,9600.7393YesNo
MiniMax-M2.7
$0.30$1.20204,8001.4323YesNo
MiniMax-M2.7
together
fastest
$0.30$1.20196,6080.41139YesYes
MiniMax-M2.7
--196,6080.61138YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.8731YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.4280NoNo
GLM-4.7-Flash
zai-org
fastest
---2.3584NoNo
GLM-4.7-Flash
$0.06$0.40202,7520.4815YesNo
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.6772YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6395NoNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.69123YesYes
gemma-3-4b-it
$0.05$0.10131,0720.4059YesYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7520.9962YesNo
GLM-5.1-FP8
---4.1532NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.53241YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.5738YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.99276YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4444NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7253YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.3150YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.73161NoNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.87100YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest fastest
$0.14$1.00262,1440.21146YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.5948NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3893YesYes
Kimi-K2.5
$0.60$3.00262,1441.3235YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.4255YesNo
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.4848YesNo
DeepSeek-OCR
$0.03$0.038,1920.54157NoNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.75109YesYes
gemma-3-12b-it
$0.05$0.15131,0720.7737YesYes
Step-3.5-Flash
$0.10$0.30262,1440.2546YesNo
tiny-aya-global
---0.21133NoNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.4846YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6413YesYes
Qwen3-235B-A22B-Instruct-2507
together
fastest
$0.20$0.60262,1440.3749YesYes
Qwen3-235B-A22B-Instruct-2507
---0.5147NoYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.2510NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.62159NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.3351NoYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8536YesYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.2955YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.3271NoNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.2258YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.9174YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.2828YesYes
aya-expanse-32b
---0.2640NoNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.6960NoYes
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.7933YesNo
GLM-4.6
---3.7520YesNo
c4ai-command-r7b-12-2024
---0.2079YesNo
gpt-oss-safeguard-20b
--131,0720.22762YesNo
aya-vision-32b
---0.2042NoNo
GLM-4.6V
---2.4962YesNo
Llama-3.1-70B-Instruct
---0.4138YesYes
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.7236YesNo
GLM-4.5V
zai-org
fastest
---3.4949YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.6259YesNo
GLM-4.5-Air
zai-org
fastest
---2.0466YesNo
GLM-4.5
---2.7348YesNo
gemma-3-27b-it
scaleway
fastest
---0.5447YesYes
gemma-3-27b-it
deepinfra
cheapest
$0.08$0.16131,0720.3615YesYes
command-a-translate-08-2025
---0.5868YesNo
MiniMax-M2.5
$0.30$1.20204,8000.8965YesNo
MiniMax-M2.5
deepinfra
cheapest fastest
$0.15$1.15196,6080.6696YesNo
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.8539YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.6812YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.3151NoYes
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0720.8886YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.8125YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
Ling-2.6-1T
$0.30$2.50262,1441.2878YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.9572NoNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.9425NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0001.1316YesYes
WizardLM-2-8x22B
$0.62$0.6265,5351.2811NoNo
DeepSeek-V3-0324
$0.27$1.12163,8400.8736YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3
$0.40$1.3064,0001.2936YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5822YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.8223YesNo
tiny-aya-water
---0.21133NoNo
tiny-aya-earth
---0.39131NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2865NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.1237YesNo
tiny-aya-fire
---0.27131NoNo
command-a-reasoning-08-2025
---0.3678YesNo
command-a-vision-07-2025
---0.2146NoNo
c4ai-command-a-03-2025
---0.2062YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.9936YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.5730YesYes
GLM-4.5V-FP8
---2.5344NoNo
GLM-4.7
$0.60$2.20204,8001.8541YesNo
GLM-4.7
cerebras
fastest
---0.16420YesNo
GLM-4.7
-------
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.4844YesNo
GLM-4.6-FP8
---3.4615YesNo
MiniMax-M2.1
$0.30$1.20204,8001.5459YesNo
GLM-4.6V-FP8
---3.4056NoNo
GLM-4.7-FP8
---1.63102YesNo
c4ai-command-r7b-arabic-02-2025
---0.2385YesNo
Kimi-K2-Thinking
$0.60$2.50262,1442.7754NoNo
MiniMax-M2
$0.30$1.20204,8001.2664YesNo
c4ai-command-r-08-2024
---0.2556YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.55188NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2846YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.4382NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2266YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4832NoYes
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
$0.80$0.808,1921.0642NoNo
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4078YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5534NoYes
GLM-4-32B-0414
$0.55$1.6632,0001.7934NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5791NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.59141NoYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.86168YesNo
MiniMax-M1-80k
$0.55$2.201,000,0000.9662YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.6339NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2640NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.4725YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.2866NoNo
cogito-671b-v2.1
-------
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7350YesNo
DeepSeek-V3.1
$0.27$1.00131,0721.5323YesYes