Inference Providers

·

Metrics for top trending models

Qwen3.5-9B
$0.10$0.15262,1440.34130YesNo
Qwen3.5-27B
$0.30$2.40262,1440.7554YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.89142YesNo
Kimi-K2.5
$0.60$3.00262,1441.0576YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.9011YesNo
Kimi-K2.5
fireworks-ai
fastest
--262,1440.5382YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6668NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.261,262NoNo
Llama-3.1-8B-Instruct
$0.10$0.2016,3841.25540YesYes
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7860NoNo
Llama-3.1-8B-Instruct
---0.34128YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8002.4330YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.63163YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8002.0532YesNo
GLM-5
$1.00$3.20202,7520.7259YesYes
GLM-5
fireworks-ai
fastest
--202,7521.1164YesNo
GLM-5
---4.1827NoNo
Qwen3-Coder-Next
$0.20$1.50262,1441.04138YesYes
gpt-oss-120b
$0.15$0.75131,0720.17443YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4671YesYes
gpt-oss-120b
sambanova
fastest
$0.22$0.59131,0720.40607YesYes
gpt-oss-120b
$0.10$0.40131,0720.9097YesYes
gpt-oss-120b
$0.30$0.30131,0720.68105YesNo
gpt-oss-120b
$0.15$0.60131,0720.39115YesYes
gpt-oss-120b
$0.15$0.60131,0720.50121YesNo
gpt-oss-120b
---0.41152YesYes
gpt-oss-120b
$0.09$0.47131,0720.30130YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.23139YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.2545YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1441.4474YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4978NoYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.3330YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.3770YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0002.7655NoNo
GLM-4.7-Flash
zai-org
fastest
---2.2267NoNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.09850YesNo
gpt-oss-20b
$0.04$0.15131,0720.4594NoYes
gpt-oss-20b
$0.05$0.20131,0720.82145YesYes
gpt-oss-20b
hyperbolic
cheapest
$0.10$0.10131,0720.46136YesNo
gpt-oss-20b
$0.05$0.20131,0720.27132YesYes
gpt-oss-20b
$0.05$0.20131,0720.36116YesNo
gpt-oss-20b
$0.05$0.18131,0720.35116YesYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.9054YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.2689YesNo
DeepSeek-R1
$0.70$2.5064,0001.4628YesYes
DeepSeek-R1
sambanova
fastest
---0.80191NoYes
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.6575NoNo
DeepSeek-R1
$3.00$7.00163,8400.4353NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.23295YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0722.5120NoNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0722.94168YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.0116NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.3726YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.6084YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.44135NoNo
Llama-3.3-70B-Instruct
---0.3080YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4139YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8373YesNo
gemma-3-27b-it
---0.4548YesYes
Qwen3.5-122B-A10B
$0.40$3.20262,1440.7182YesNo
Llama-3.2-1B-Instruct
--131,0000.64186NoNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.8556YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.23122NoYes
Qwen2.5-VL-7B-Instruct
$0.20$0.2032,7680.41116NoNo
MiMo-V2-Flash
$0.10$0.30262,1442.6272YesNo
DeepSeek-OCR
$0.03$0.038,1920.88231NoNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.79141NoNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.20383YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3883NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7533YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.6967NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6938NoNo
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.1136YesNo
DeepSeek-V3
together
cheapest
$1.25$1.25131,0721.4932YesYes
gpt-oss-safeguard-20b
--131,0720.11858YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.82165YesNo
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30$0.30262,1440.49187YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.38107YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3379YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6981YesNo
GLM-4.5-Air
---1.8679YesNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.65133YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8261NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9093YesNo
Llama-3.1-70B-Instruct
---0.3382YesYes
Kimi-K2-Thinking
novita
cheapest fastest
$0.60$2.50262,1440.7857YesNo
Kimi-K2-Thinking
-------
Kimi-K2-Thinking
---0.8922YesNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0721.1497YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.30138YesNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.1037YesNo
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0721.30149YesYes
DeepSeek-V3-0324
$1.25$1.25163,8401.1538YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.4162YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.20272YesNo
Qwen3-32B
$0.10$0.4540,9600.6358NoNo
Qwen3-32B
$0.40$0.8032,7682.73189YesYes
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.8827YesNo
Qwen3-32B
$0.09$0.2532,7680.3642YesYes
Olmo-3.1-32B-Think
$0.15$0.50-1.3470NoNo
Apriel-1.6-15b-Thinker
$0.00$0.00131,0720.1680NoNo
gemma-3n-E4B-it
$0.02$0.0432,7680.2938NoYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0722.2074YesNo
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
$0.30$0.30262,1440.51172YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50262,1440.34123YesYes
tiny-aya-fire
---0.20124NoNo
rnj-1-instruct
$0.15$0.1532,7680.55120YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9856YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.7765YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.6472YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.6237YesNo
GLM-4.7
fireworks-ai
fastest
--202,7521.1562YesNo
GLM-4.7
---2.4439YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.3338YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9224YesYes
Qwen3-235B-A22B-Instruct-2507
$2.00$2.00262,1440.8528YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.5029YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.37103YesYes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
$0.60$0.6032,7680.4344NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3536NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.887NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0623YesYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.7421YesNo
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.17184YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1440.6951YesYes
Kimi-K2-Instruct-0905
-------
Kimi-K2-Instruct-0905
--262,1440.9655YesNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.4722YesNo
DeepSeek-R1-0528
sambanova
fastest
$5.00$7.00131,0721.29180YesYes
DeepSeek-R1-0528
$3.00$3.00163,8400.6577NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.4753NoNo
tiny-aya-global
---0.31120NoNo
tiny-aya-water
---0.30120NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
$0.27$0.851,048,5760.3940NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
$0.27$0.851,048,5760.3144YesYes
command-a-reasoning-08-2025
---0.4237YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8157NoYes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.89117YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.30149YesNo
GLM-4.6V-Flash
$0.30$0.90131,0720.7731YesNo
GLM-4.6V-Flash
-------
MiniMax-M2
$0.30$1.20204,8003.3929YesNo
QwQ-32B
$0.18$0.20131,0720.8729YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.8017NoNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.7957NoNo
GLM-4.5
---2.2354YesNo
MiniMax-M1-80k
$0.55$2.201,000,0003.2225NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.7828NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.35110YesNo
command-a-translate-08-2025
---0.4637YesNo
aya-expanse-32b
---0.1844NoNo
DeepSeek-R1-Distill-Llama-70B
novita
fastest
$0.80$0.808,1920.6762NoNo
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9016NoYes
DeepSeek-R1-Distill-Llama-70B
---0.3838NoYes
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.7926YesNo
GLM-4.6
together
fastest
$0.60$2.20202,7521.2272YesNo
GLM-4.6
-------
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2428YesYes
c4ai-command-r7b-arabic-02-2025
---0.2086YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7335YesYes
aya-vision-32b
---0.3937NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.6921NoYes
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0001.0050NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9934YesNo
command-a-vision-07-2025
---0.2642NoNo
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0001.0080NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.0728YesNo
Kimi-K2-Instruct
-------
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.0343NoNo
Llama-4-Maverick-17B-128E-Instruct
-------
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.25343YesYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.63107NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4127NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7569YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.70119NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8928NoYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.3564YesYes
Qwen3-14B
$0.07$0.2040,9600.9552YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7384NoYes
L3-8B-Lunaris-v1
$0.05$0.058,1921.2341NoNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5361.0225NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2568NoNo
GLM-4.7-FP8
together
cheapest fastest
$0.45$2.00202,7520.3981YesNo
GLM-4.7-FP8
---2.7937YesNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.1865NoNo
cogito-671b-v2.1
--163,8400.6541YesNo
c4ai-command-r-08-2024
---0.2937YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6748NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.7513NoNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.9951YesNo
GLM-4.5V
zai-org
fastest
---2.7152YesNo
GLM-4.6-FP8
---3.1828YesNo
GLM-4.5V-FP8
---2.3448YesNo
GLM-4.6V
---3.2732YesNo
GLM-4.6V-FP8
---3.8019NoNo
c4ai-command-r7b-12-2024
---0.25118YesNo
c4ai-command-a-03-2025
---0.2744YesNo
Arch-Router-1.5B
---0.1078NoYes
Llama-3.3-Swallow-70B-Instruct-v0.4
$0.60$1.20131,0720.82206NoYes
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8002.4829YesNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8000.99150YesNo
GLM-4-32B-0414
$0.55$1.6632,0000.8141NoNo
tiny-aya-earth
---0.28120NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8248YesNo
Olmo-3.1-32B-Instruct
$0.20$0.60-1.2952YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.3729YesYes
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.4229YesYes
DeepSeek-V3.1
$0.60$1.70131,0721.4138YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.4267YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.4845YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.1848NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.6958NoYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.5965YesYes
GLM-4.5-Air-FP8
$0.20$1.10131,0720.94131YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5763NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2274NoNo