Inference Providers

·

Metrics for top trending models

gemma-4-31B-it
novita
cheapest fastest
$0.14$0.40262,1441.0021YesYes
gemma-4-31B-it
$0.20$0.50262,1440.5114NoNo
GLM-5.1
together
cheapest fastest
$1.40$4.40202,7520.4837YesYes
GLM-5.1
--202,7520.7413YesNo
GLM-5.1
---3.9036NoNo
gemma-4-26B-A4B-it
$0.13$0.40262,1442.5723NoNo
Qwen3.5-9B
$0.10$0.15262,1440.3576YesYes
GLM-5.1-FP8
---3.4837NoNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.3435YesNo
GLM-5
$1.00$3.20202,7520.7250YesYes
GLM-5
fireworks-ai
fastest
--202,7522.2361YesNo
GLM-5
---2.9541NoNo
Qwen3.5-27B
$0.30$2.40262,1440.6148YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1441.12131YesNo
MiniMax-M2.5
novita
cheapest fastest
$0.30$1.20204,8000.63108NoNo
MiniMax-M2.5
---3.2385YesNo
gpt-oss-120b
$0.15$0.75131,0720.15445YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.5143YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.24854YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.99106NoYes
gpt-oss-120b
$0.15$0.60131,0720.3675YesYes
gpt-oss-120b
$0.15$0.60131,0720.42109YesNo
gpt-oss-120b
---0.31122YesYes
gpt-oss-120b
$0.09$0.47131,0720.3343YesYes
DeepSeek-R1
$0.70$2.5064,0001.5729YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.6142NoNo
DeepSeek-R1
together
fastest
$3.00$7.00163,8400.6046NoYes
Kimi-K2.5
$0.60$3.00262,1441.0851YesNo
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.7657YesYes
Kimi-K2.5
--262,1440.7237NoNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.8549YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.5368YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.4076YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.77116YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.16788YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.7856NoYes
gpt-oss-20b
$0.05$0.20131,0720.82158YesYes
gpt-oss-20b
$0.05$0.20131,0720.22127YesYes
gpt-oss-20b
$0.05$0.20131,0720.54113YesNo
gpt-oss-20b
$0.05$0.18131,0720.30103YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6864NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.241,280NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8259NoYes
Llama-3.1-8B-Instruct
---0.3191YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.3230YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8402.9442YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1441.74114YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.23122YesYes
GLM-4.7-Flash
-------
GLM-4.7-Flash
---2.7666NoNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9601.0354YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.24138YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.5978NoYes
MiMo-V2-Flash
$0.10$0.30262,1441.7479YesNo
Llama-3.2-1B-Instruct
--131,0000.72182NoNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8986YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4479YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4061YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.17280YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4745YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8617NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.1793YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.74102YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.4196NoNo
Llama-3.3-70B-Instruct
---0.3677YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4734YesYes
DeepSeek-V3
$0.40$1.3064,0001.0834YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.6157YesYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.52138YesYes
QwQ-32B
$0.18$0.20131,0720.7828YesYes
gemma-3-27b-it
---0.5544YesYes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.7358YesNo
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.3382YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.17373YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4536NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8333YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9151YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.5553YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.2375YesYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.8024YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
hyperbolic
fastest
$3.00$3.00163,8401.5655NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.4745NoYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.9536YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
$1.25$1.25163,8401.0880YesNo
DeepSeek-V3-0324
together
fastest
$1.25$1.25131,0720.5490YesYes
gemma-3n-E4B-it
$0.02$0.0432,7680.2835NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6782NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.21291YesNo
Qwen3-32B
$0.10$0.4540,9600.6258NoNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9727YesYes
Qwen3-32B
$0.09$0.2532,7680.4340YesYes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.61122YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.31149YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8161NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8266NoNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.70142NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9925NoYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.7958YesNo
GLM-4.7
cerebras
fastest
---0.30291YesNo
GLM-4.7
--202,7521.04118YesNo
GLM-4.7
---2.3561YesNo
Llama-3.1-70B-Instruct
---0.3778YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0721.10116YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.44135YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.1829YesNo
Kimi-K2-Thinking
novita
cheapest fastest
$0.60$2.50262,1440.9736YesNo
Kimi-K2-Thinking
---4.6721YesNo
gpt-oss-safeguard-20b
--131,0720.37730YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0930YesYes
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.18176YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1441.4618YesYes
Kimi-K2-Instruct-0905
--262,1441.5517YesNo
DeepSeek-R1-Distill-Llama-70B
novita
fastest
$0.80$0.808,1920.3843NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9717NoYes
DeepSeek-R1-Distill-Llama-70B
---0.5138NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9788YesNo
command-a-translate-08-2025
---0.3165YesNo
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0001.1076NoNo
tiny-aya-global
---0.23121NoNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.354NoNo
rnj-1-instruct
$0.15$0.1532,7680.24121YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.7197NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.5346YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.24534YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.1624YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1441.3924YesYes
Qwen3-235B-A22B-Instruct-2507
---0.4161YesYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5318NoNo
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8002.2453YesNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8001.26125YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3844NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.9414YesNo
Qwen3-14B
$0.07$0.2040,9600.8850YesNo
c4ai-command-r7b-12-2024
---0.2590YesNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.9449YesNo
GLM-4.6
zai-org
fastest
---1.8062YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8234YesYes
c4ai-command-r-08-2024
---0.408YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.92166YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.6066YesNo
aya-expanse-32b
---0.1943NoNo
command-a-vision-07-2025
---0.2440NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7630NoNo
c4ai-command-a-03-2025
---1.3922NoNo
Arch-Router-1.5B
---0.1172NoYes
command-a-reasoning-08-2025
---0.3152YesNo
GLM-4.7-FP8
---2.5054YesNo
tiny-aya-water
---0.26120NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.3054YesYes
GLM-4.6V
---4.1021YesNo
tiny-aya-earth
---0.26121NoNo
c4ai-command-r7b-arabic-02-2025
---0.2085YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.7378YesNo
GLM-4.5-Air
---1.9875YesNo
aya-vision-32b
---0.3237NoNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.6353YesNo
GLM-4.5
zai-org
fastest
---2.7053YesNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.8325NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2268NoNo
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0001.0771NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.7443NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9344YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8328NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3850YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8657NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.4014NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.1721YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8742YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2937NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3436NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.9746NoYes
GLM-4-32B-0414
$0.55$1.6632,0000.8943NoNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7961YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.1926YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.2231NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.7441YesNo
GLM-4.5V
---2.4238YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.6875NoYes
GLM-4.6-FP8
---2.4257YesNo
GLM-4.5V-FP8
---3.1040YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.4930YesYes
DeepSeek-V3.1
together
fastest
$0.60$1.70131,0720.5391YesYes
DeepSeek-V3.1
--163,8400.5945NoNo
GLM-4.6V-FP8
---3.5527YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4729YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.7035NoNo
WizardLM-2-8x22B
$0.62$0.6265,5351.197NoNo
MiniMax-M2
$0.30$1.20204,8002.8947YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1811NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.5460YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.6244YesYes
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.2071NoNo
cogito-671b-v2.1
--163,8400.3635YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.6922NoYes
MiniMax-M1-80k
$0.55$2.201,000,0001.5947YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2372NoNo
tiny-aya-fire
---0.31120NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.0959NoYes