Inference Providers

·

Metrics for top trending models

gemma-4-31B-it
$0.14$0.40262,1440.852YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.7811YesNo
Qwen3.5-9B
$0.10$0.15262,1440.2770YesYes
GLM-5
novita
cheapest
$1.00$3.20202,8002.4134YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.5863YesYes
GLM-5
--202,7521.8150YesNo
GLM-5
-------
Qwen3.5-27B
$0.30$2.40262,1440.9958YesNo
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.6537YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.7925YesNo
Kimi-K2.5
--262,1441.5719YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.83107YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.58110YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.80144YesNo
DeepSeek-R1
$0.70$2.5064,0001.6327YesYes
DeepSeek-R1
sambanova
fastest
---1.51102NoYes
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.7088NoNo
DeepSeek-R1
$3.00$7.00163,8400.4872NoYes
Qwen3-Coder-Next
$0.20$1.50262,1441.0499YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.9042YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.4846YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.4892YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6578NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.221,194NoNo
Llama-3.1-8B-Instruct
$0.10$0.2016,3840.31780YesYes
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8959NoYes
Llama-3.1-8B-Instruct
---0.30129YesYes
gpt-oss-120b
$0.15$0.75131,0720.13442YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4068YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.27892YesNo
gpt-oss-120b
$0.22$0.59131,0720.59542YesYes
gpt-oss-120b
$0.10$0.40131,0720.93105YesYes
gpt-oss-120b
$0.15$0.60131,0720.63179YesYes
gpt-oss-120b
$0.15$0.60131,0720.36145YesNo
gpt-oss-120b
---0.31161YesYes
gpt-oss-120b
$0.09$0.47131,0720.2781YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.3928YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.5450YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.09794YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.6594NoYes
gpt-oss-20b
$0.05$0.20131,0720.86149YesYes
gpt-oss-20b
$0.05$0.20131,0720.22111YesYes
gpt-oss-20b
$0.05$0.20131,0720.5966YesNo
gpt-oss-20b
$0.05$0.18131,0720.2939YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.18119YesYes
MiMo-V2-Flash
$0.10$0.30262,1441.6983YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4479NoYes
GLM-4.7-Flash
-------
GLM-4.7-Flash
---2.1663YesNo
Llama-3.2-1B-Instruct
--131,0000.64181NoNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.6885YesNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.7358YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.30131YesNo
gemma-3-27b-it
---0.5448YesYes
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.27259YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4141YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0720.52286YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8117NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.1599YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.4999YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.43118NoNo
Llama-3.3-70B-Instruct
---0.3279YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.6836YesYes
Qwen3-Coder-30B-A3B-Instruct
---0.3656NoNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest fastest
$0.07$0.26262,1440.3573YesYes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.7050YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.2862NoNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7887YesNo
QwQ-32B
$0.18$0.20131,0720.7729YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.32356YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3744NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.9232YesYes
gemma-3n-E4B-it
$0.02$0.0432,7680.2713NoYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.39145YesYes
DeepSeek-V3
$0.40$1.3064,0001.2035YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.4168YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2226YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.6376YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9447YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.1663YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6935YesYes
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8000.8032YesNo
GLM-4.6
---3.5527NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8528NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.72139NoYes
DeepSeek-R1-Distill-Llama-70B
novita
fastest
$0.80$0.808,1920.3440NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.8416NoYes
DeepSeek-R1-Distill-Llama-70B
---0.4838NoYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8402.0824YesNo
DeepSeek-R1-0528
sambanova
fastest
$5.00$7.00131,0720.60134YesYes
DeepSeek-R1-0528
$3.00$3.00163,8401.0965NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.4379NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7661NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.33268YesNo
Qwen3-32B
$0.10$0.4540,9600.7038NoNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9601.0427YesNo
Qwen3-32B
$0.09$0.2532,7680.3838YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8028NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3955YesNo
Qwen3-235B-A22B
$0.20$0.8040,9600.4622NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.9823YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.9162NoNo
Llama-3.1-70B-Instruct
---0.3277YesYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.95292YesYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.0335YesYes
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0720.88137YesYes
DeepSeek-V3-0324
$1.25$1.25163,8400.7654YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.4172YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0721.145NoYes
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.5938YesNo
GLM-4.5V
zai-org
fastest
---2.9243YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7681.2620NoYes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.86117YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.33149YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.1729YesNo
tiny-aya-water
---0.19122NoNo
tiny-aya-global
---0.18121NoNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0721.3256YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.44136YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0721.04158YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.1354YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.7790YesNo
Qwen3-14B
$0.07$0.2040,9600.9151YesNo
aya-expanse-32b
---0.1944NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4918NoYes
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0000.9970NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8002.5215YesNo
GLM-4.7
cerebras
fastest
---0.27471YesNo
GLM-4.7
--202,7521.5938YesNo
GLM-4.7
---3.3720NoNo
c4ai-command-r7b-12-2024
---0.2588YesNo
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8001.9239YesNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8001.35139YesNo
MiniMax-M1-80k
$0.55$2.201,000,0002.2834YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.1035NoNo
command-a-translate-08-2025
---0.3164YesNo
GLM-4.6V
---4.3018YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1739YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.23572YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9124YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.5933YesYes
Qwen3-235B-A22B-Instruct-2507
---0.4098YesYes
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0000.8966NoNo
tiny-aya-earth
---0.17123NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.8033NoNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.65106NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.8071YesYes
c4ai-command-r7b-arabic-02-2025
---0.1982YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.8815YesNo
aya-vision-32b
---0.3837NoNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.7965YesNo
GLM-4.5-Air
---2.0361YesNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.1669NoNo
cogito-671b-v2.1
--163,8400.3629YesNo
rnj-1-instruct
$0.15$0.1532,7680.18119NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.3110NoNo
c4ai-command-a-03-2025
---0.5445YesNo
c4ai-command-r-08-2024
---0.2629NoNo
Kimi-K2-Thinking
novita
cheapest
$0.60$2.50262,1441.3532YesNo
Kimi-K2-Thinking
fireworks-ai
fastest
---1.0540YesNo
MiniMax-M2
$0.30$1.20204,8002.1940YesNo
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.21190YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1441.4521YesNo
Kimi-K2-Instruct-0905
--262,1440.9820YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7257NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.8191NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-2.0955NoYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8538YesNo
gpt-oss-safeguard-20b
--131,0720.22779YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.4820YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.5454YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.4825YesYes
DeepSeek-V3.1
together
fastest
$0.60$1.70131,0720.4763YesYes
DeepSeek-V3.1
--163,8400.5149NoNo
GLM-4.7-FP8
---3.9619NoNo
WizardLM-2-8x22B
$0.62$0.6265,5351.1112NoNo
GLM-4.6V-FP8
---4.6220YesNo
Arch-Router-1.5B
---0.1179NoYes
GLM-4.5V-FP8
---2.4245YesNo
GLM-4.6-FP8
---2.8328YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6662NoNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.9848YesNo
GLM-4.5
---2.3242YesNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.9925NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2666NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7686NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
tiny-aya-fire
---0.18122NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.6219NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Olmo-3.1-32B-Instruct
$0.20$0.60-1.4542YesYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.7519NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2664YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.4645YesYes
command-a-reasoning-08-2025
---0.4269YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.5047NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4319NoYes
command-a-vision-07-2025
---0.2243NoNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5626YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2542NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.1676NoNo