Inference Providers

·

Metrics for top trending models

GLM-5.1
together
cheapest fastest
$1.40$4.40202,7520.7864YesYes
GLM-5.1
--202,7520.6958YesNo
GLM-5.1
---3.4136YesNo
gemma-4-31B-it
novita
cheapest
$0.14$0.40262,1440.977YesYes
gemma-4-31B-it
together
fastest
$0.20$0.50262,1440.2723YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1441.1322YesNo
Qwen3.5-9B
$0.10$0.15262,1441.3887YesYes
GLM-5.1-FP8
---4.0929NoNo
Qwen3.5-27B
$0.30$2.40262,1440.6650YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.4533YesNo
GLM-5
$1.00$3.20202,7520.8748YesYes
GLM-5
fireworks-ai
fastest
--202,7521.5360YesNo
GLM-5
---3.3439YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.91128YesNo
gpt-oss-120b
$0.15$0.75131,0720.16446YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4046YesNo
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.25753YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.80108YesYes
gpt-oss-120b
$0.15$0.60131,0720.38111YesYes
gpt-oss-120b
$0.15$0.60131,0720.46140YesNo
gpt-oss-120b
---0.40111YesYes
gpt-oss-120b
$0.09$0.47131,0720.41127YesYes
Kimi-K2.5
$0.60$3.00262,1441.4258YesYes
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.4272YesNo
Kimi-K2.5
--262,1440.2659YesNo
MiniMax-M2.5
novita
cheapest fastest
$0.30$1.20204,8000.72167YesNo
MiniMax-M2.5
---0.75164YesNo
DeepSeek-R1
$0.70$2.5064,0001.4829YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.6998NoNo
DeepSeek-R1
$3.00$7.00163,8400.9892NoYes
Qwen3-Coder-Next
$0.20$1.50262,1440.90109YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.8655YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.4280YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.3894YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.22754YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.9746NoYes
gpt-oss-20b
$0.05$0.20131,0721.06155YesYes
gpt-oss-20b
$0.05$0.20131,0720.5798YesYes
gpt-oss-20b
$0.05$0.20131,0720.47115YesNo
gpt-oss-20b
$0.05$0.18131,0720.2899YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.7181NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.241,446NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7659NoNo
Llama-3.1-8B-Instruct
---0.31101YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.2135YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.0269YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.74105YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.19126YesYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4886NoYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.8954YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.22150YesNo
MiMo-V2-Flash
$0.10$0.30262,1442.8776YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8187YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.16244YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4748YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9216NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.84101YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.58116YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.25130NoNo
Llama-3.3-70B-Instruct
---0.3585YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.8034YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4281YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3178YesYes
Llama-3.2-1B-Instruct
--131,0000.73182NoNo
DeepSeek-V3
$0.40$1.3064,0001.1529YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.5582YesYes
QwQ-32B
$0.18$0.20131,0720.9928YesYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.49139YesYes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.7367YesNo
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.3368NoYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.8626NoNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8401.2785NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.40106NoYes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.97114YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.30150YesNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.1030YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.8762YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.6557YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.21370YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.2963NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8433YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.7666NoNo
gemma-3-27b-it
---0.3448YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8362NoYes
Kimi-K2-Instruct
$0.57$2.30131,0720.9028YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.8947YesNo
GLM-4.7
cerebras
fastest
---0.21444YesNo
GLM-4.7
--202,7520.90168YesNo
GLM-4.7
---1.7766YesNo
gemma-3n-E4B-it
$0.02$0.0432,7680.2417NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.69138NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8828NoYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.16252YesNo
Qwen3-32B
$0.10$0.4540,9600.7035NoNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9528YesYes
Qwen3-32B
$0.09$0.2532,7680.3837YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.3331YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.89112YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.45126YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1441.0033YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.4458YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.1668YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3832NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9716NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4238NoYes
Kimi-K2-Thinking
novita
cheapest
$0.60$2.50262,1440.7055YesNo
Kimi-K2-Thinking
fireworks-ai
fastest
---1.3461YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.908NoNo
gpt-oss-safeguard-20b
--131,0720.30684YesNo
rnj-1-instruct
$0.15$0.1532,7680.16122YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3931NoYes
tiny-aya-global
---0.28119NoNo
Apertus-8B-Instruct-2509
$0.10$0.20-1.01114NoYes
command-a-translate-08-2025
---0.3066YesNo
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.14187YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1441.2229YesYes
Kimi-K2-Instruct-0905
--262,1442.0514YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.0239NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.7790YesNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5118NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1037YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.25567YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9024YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.7221YesYes
Qwen3-235B-A22B-Instruct-2507
---0.35103YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7270NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.8443NoNo
aya-expanse-32b
---0.2044NoNo
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8002.6751YesNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8000.64152YesNo
Llama-3.1-70B-Instruct
---0.3584YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.8773YesNo
GLM-4.5-Air
zai-org
fastest
---1.6287YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8000.6648YesNo
GLM-4.6
---2.5146YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7938YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.80164YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7380YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.8548YesNo
GLM-4.5
zai-org
fastest
---2.4851YesNo
GLM-4.6V
---4.2619YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8956NoYes
Qwen3-14B
$0.07$0.2040,9600.8445YesYes
c4ai-command-r-08-2024
---0.2227YesNo
aya-vision-32b
---0.3937NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.1863YesYes
c4ai-command-r7b-arabic-02-2025
---0.2093YesNo
c4ai-command-a-03-2025
---1.9521YesNo
command-a-vision-07-2025
---0.2143NoNo
GLM-4.7-FP8
---3.6451YesNo
command-a-reasoning-08-2025
---0.4285YesNo
c4ai-command-r7b-12-2024
---0.23116YesNo
GLM-4.6V-FP8
---4.3322YesNo
tiny-aya-earth
---0.23121NoNo
GLM-4.5V-FP8
---2.0855YesNo
GLM-4.6-FP8
---2.0553YesNo
GLM-4.5V
-------
GLM-4.5V
---2.0058NoNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.8126NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2266NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3537NoYes
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7432NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.5316NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.9322YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.5147NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen3-30B-A3B
$0.09$0.4540,9600.9765YesNo
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0001.0867NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1442NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8328NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.4183YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0721.0548YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9752YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.9831YesNo
Arch-Router-1.5B
---0.1468NoYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.1023YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.4273YesNo
tiny-aya-fire
---0.17103NoNo
MiniMax-M2
$0.30$1.20204,8003.5040YesNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.2269NoNo
cogito-671b-v2.1
--163,8400.5137YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4830YesYes
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.3330YesYes
DeepSeek-V3.1
together
fastest
$0.60$1.70131,0720.5958YesYes
DeepSeek-V3.1
--163,8400.6343NoNo
WizardLM-2-8x22B
$0.62$0.6265,5351.1510NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.6063YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7182NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3844YesYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.65102NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.7822NoYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2668NoNo
MiniMax-M1-80k
$0.55$2.201,000,0002.3345YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.1059NoYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.2210NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.6642NoNo
tiny-aya-water
---0.83112NoNo