Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.69$3.381,048,5760.9238YesNo
DeepSeek-V4-Pro
together
fastest
$2.10$4.40512,0000.5642YesYes
DeepSeek-V4-Pro
--1,048,5763.7722YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.5331YesYes
DeepSeek-V4-Flash
$0.14$0.281,048,5760.70110YesNo
DeepSeek-V4-Flash
-------
Qwen3.6-35B-A3B
$0.15$0.95262,1440.32134YesYes
gemma-4-31B-it
$0.14$0.40262,1441.1913NoNo
gemma-4-31B-it
$0.20$0.50262,1440.3713YesYes
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.7216YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.9627YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.3886YesYes
Kimi-K2.6
--262,1440.5346YesNo
Kimi-K2.6
$0.75$3.50262,1440.7018YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1440.6837YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.3049YesYes
GLM-5.1
$1.40$4.40202,7520.9747YesYes
GLM-5.1
--202,7522.4929YesNo
GLM-5.1
---3.6931YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.7255YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3178YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4239YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.5264NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.221,229NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.9257NoNo
Llama-3.1-8B-Instruct
---0.23141YesYes
Ling-2.6-1T
$0.30$2.50262,1441.1475YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.2935YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3368YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.42170YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.22717YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.5366NoYes
gpt-oss-20b
$0.05$0.20131,0720.91148YesYes
gpt-oss-20b
$0.05$0.20131,0720.39124YesNo
gpt-oss-20b
$0.05$0.20131,0720.6062YesNo
gpt-oss-20b
$0.05$0.18131,0720.2989YesYes
gpt-oss-120b
$0.15$0.75131,0720.18433YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.3869YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.37966YesNo
gpt-oss-120b
$0.22$0.59131,0721.36425YesNo
gpt-oss-120b
$0.10$0.40131,0720.90112YesYes
gpt-oss-120b
$0.15$0.60131,0721.5886YesYes
gpt-oss-120b
$0.15$0.60131,0720.36152YesNo
gpt-oss-120b
---0.41110YesYes
gpt-oss-120b
$0.09$0.47131,0720.3875YesYes
DeepSeek-OCR
$0.03$0.038,1921.03170NoNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.20113YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.3999YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4295YesYes
DeepSeek-R1
$0.70$2.5064,0002.3121YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.5866YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.03121YesNo
Kimi-K2.5
$0.60$3.00262,1441.5736YesYes
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.4462YesYes
Kimi-K2.5
--262,1443.6732YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4192NoYes
Qwen3-8B
$0.07$0.1840,9600.8657YesNo
DeepSeek-V3.2
$0.27$0.40163,8401.6031YesYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0721.4962YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9969YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.46149YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1442.5974YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.45215YesYes
Qwen3.5-397B-A17B
---0.42107YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2858YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5136NoYes
Step-3.5-Flash
$0.10$0.30262,1440.3073YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1441.0787YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.4182YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.9064YesNo
Llama-3.2-1B-Instruct
--131,0000.43196NoNo
Qwen3-14B
$0.07$0.2040,9600.9151YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.80129NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9429NoYes
QwQ-32B
$0.18$0.20131,0720.8129NoYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.3777YesNo
GLM-5.1-FP8
--202,7521.0428YesNo
GLM-5.1-FP8
zai-org
fastest
---3.8430NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8554NoYes
Qwen3.5-27B
$0.30$2.40262,1440.6860YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.1264YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.5276NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.1666YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8261NoYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.4426YesNo
DeepSeek-V3
$0.40$1.3064,0001.2431YesNo
DeepSeek-V3
-------
DeepSeek-V3-0324
$0.27$1.12163,8400.9034YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.6432YesNo
GLM-4.6
---3.7520NoNo
Llama-3.1-70B-Instruct
---0.4851YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.12414YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3652NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.9133YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9927NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.31110YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.2425YesNo
gemma-3-27b-it
---0.5648YesNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0722.01278YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0721.0337NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8167NoNo
gpt-oss-safeguard-20b
--131,0720.24767YesNo
Arch-Router-1.5B
---0.1079NoYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.3750YesNo
GLM-4.7
cerebras
fastest
---0.14500YesNo
GLM-4.7
---3.7379YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.15324YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4848YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0723.22157YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.0117NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9863NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.7975YesYes
Llama-3.3-70B-Instruct
---0.3666YesYes
Llama-3.3-70B-Instruct
-------
Apertus-8B-Instruct-2509
$0.10$0.20-1.0753NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.6416NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0719YesYes
WizardLM-2-8x22B
$0.62$0.6265,5350.7913NoNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.8130YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.8372YesYes
GLM-5
-------
GLM-5
---3.2339YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2655NoYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5428YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6388NoNo
tiny-aya-global
---0.28122NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.89166YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5926YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7834YesYes
MiniMax-M2
$0.30$1.20204,8000.8173YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.1056YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.7036NoNo
MiMo-V2-Flash
$0.10$0.30262,1441.3298YesNo
MiniMax-M2.1
$0.30$1.20204,8001.3459YesNo
DeepSeek-R1-0528
$0.70$2.50163,8402.3122YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
tiny-aya-earth
---0.23121NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.8089NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9194YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1513NoNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.0648YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.15581YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0124YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.3247YesYes
Qwen3-235B-A22B-Instruct-2507
---0.36103YesYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.1966YesYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6461NoYes
tiny-aya-fire
---0.25121NoNo
c4ai-command-a-03-2025
---0.3223YesNo
GLM-4.7-FP8
---2.22118YesNo
GLM-4.6V-FP8
---2.6341YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.2932YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.6067NoNo
GLM-4.6V
---2.9242YesNo
GLM-4.5V-FP8
---2.3053YesNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.7454YesNo
GLM-4.5V
---2.2850YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0721.2469YesNo
GLM-4.5-Air
---1.7463YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0721.0646YesNo
GLM-4.5
zai-org
fastest
---2.3856YesNo
Gemma-4-31B-it-pearl
$0.28$0.8632,0000.1950YesNo
tiny-aya-water
---0.18122NoNo
c4ai-command-r7b-12-2024
---0.2979YesNo
c4ai-command-r-08-2024
---0.1656YesNo
aya-expanse-32b
---0.1941NoNo
aya-vision-32b
---0.2336NoNo
c4ai-command-r7b-arabic-02-2025
---0.2880YesNo
command-a-vision-07-2025
---0.1747NoNo
command-a-reasoning-08-2025
---0.5149YesNo
command-a-translate-08-2025
---0.4367YesNo
rnj-1-instruct
$0.15$0.1532,7680.18122YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.3135NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2443NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5761.2311NoYes
GLM-4-32B-0414
$0.55$1.6632,0000.9543NoNo
Qwen3-30B-A3B
$0.09$0.4540,9600.6961YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.17312YesNo
Qwen3-32B
$0.10$0.4540,9600.6348NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9603.1213YesYes
Qwen3-32B
$0.09$0.2532,7680.3437YesYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.5720NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.1853YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5219NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1641NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1921.6532NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9334YesNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0720.93110YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0727YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9246YesNo
DeepSeek-V3.1
$0.27$1.00131,0721.7525YesYes
DeepSeek-V3.1
-------
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3744NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9517NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3967YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.7660YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2247YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2652NoYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5121NoYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.44111NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7334NoNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5361.1225NoNo