Inference Providers

·

Metrics for top trending models

Qwen3.5-9B
$0.10$0.15262,1440.38112YesNo
Qwen3.5-27B
$0.30$2.40262,1441.9553YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1441.26111YesNo
Kimi-K2.5
$0.60$3.00262,1440.9142YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.5282YesNo
Kimi-K2.5
fireworks-ai
fastest
--262,1440.5991YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6271NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.251,339NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8760NoYes
Llama-3.1-8B-Instruct
---0.34150YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.3440YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.74136YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8002.5725YesNo
GLM-5
$1.00$3.20202,7520.5367NoNo
GLM-5
fireworks-ai
fastest
--202,7521.1070YesNo
GLM-5
---3.8632NoNo
Qwen3-Coder-Next
$0.20$1.50262,1440.7475YesNo
gpt-oss-120b
groq
fastest
$0.15$0.75131,0720.43397YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.3951YesYes
gpt-oss-120b
$0.22$0.59131,0721.21376YesYes
gpt-oss-120b
$0.10$0.40131,0720.8099YesYes
gpt-oss-120b
$0.30$0.30131,0720.97105YesNo
gpt-oss-120b
$0.15$0.60131,0720.3981YesYes
gpt-oss-120b
$0.15$0.60131,0720.3397YesNo
gpt-oss-120b
---0.39163YesYes
gpt-oss-120b
$0.09$0.47131,0720.4680YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.1529YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.5173YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4695NoYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.8550YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.3685YesNo
Qwen3.5-397B-A17B
---0.4657YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.19139YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.10857YesNo
gpt-oss-20b
$0.04$0.15131,0720.4997NoYes
gpt-oss-20b
$0.05$0.20131,0720.91140YesYes
gpt-oss-20b
hyperbolic
cheapest
$0.10$0.10131,0720.52185YesNo
gpt-oss-20b
$0.05$0.20131,0720.20147YesYes
gpt-oss-20b
$0.05$0.20131,0721.3872YesNo
gpt-oss-20b
$0.05$0.18131,0720.2697YesNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.7659YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.26140YesNo
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.24259YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4642YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0720.50267YesNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8716NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.72101YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.7150YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.26136NoNo
Llama-3.3-70B-Instruct
---0.3779YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3537YesYes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.9851YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.2894NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7187YesNo
DeepSeek-R1
$0.70$2.5064,0001.5823YesYes
DeepSeek-R1
sambanova
fastest
---1.59170YesYes
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.6126NoNo
DeepSeek-R1
$3.00$7.00163,8400.5767NoNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.8972YesNo
gemma-3-27b-it
---0.4148YesYes
MiMo-V2-Flash
$0.10$0.30262,1441.9476YesNo
Llama-3.2-1B-Instruct
--131,0000.62184NoNo
Qwen2.5-VL-7B-Instruct
$0.20$0.2032,7680.39118NoNo
DeepSeek-OCR
$0.03$0.038,1921.40182NoNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.29100YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.2978YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.28347YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3351NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8133YesYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.82141NoNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7561NoYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.23254YesNo
Qwen3-32B
$0.10$0.4540,9600.7236NoNo
Qwen3-32B
$0.40$0.8032,7680.91237YesYes
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.8428YesYes
Qwen3-32B
$0.09$0.2532,7680.4241YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8265NoYes
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7838NoNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1441.0343YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.5048YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.1951YesYes
DeepSeek-V3
$0.40$1.3064,0001.3032YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.5038YesYes
Llama-3.1-70B-Instruct
---0.3179YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.7889YesNo
gpt-oss-safeguard-20b
--131,0720.15818YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.0429YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0324YesYes
Qwen3-235B-A22B-Instruct-2507
$2.00$2.00262,1442.8220YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.8615YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.3398YesYes
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.16186YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1441.1832YesYes
Kimi-K2-Instruct-0905
-------
Kimi-K2-Instruct-0905
--262,1440.6524YesNo
Kimi-K2-Thinking
novita
cheapest
$0.60$2.50262,1440.9143NoNo
Kimi-K2-Thinking
-------
Kimi-K2-Thinking
fireworks-ai
fastest
---0.5352YesNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.0932YesNo
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0722.42144YesYes
DeepSeek-V3-0324
$1.25$1.25163,8400.7862YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.5663YesYes
Qwen3-30B-A3B
$0.09$0.4540,9600.9280YesNo
Olmo-3.1-32B-Think
$0.15$0.50-1.2972NoNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6867YesNo
GLM-4.5-Air
---2.0550YesNo
tiny-aya-global
---0.26121NoNo
rnj-1-instruct
$0.15$0.1532,7680.20123YesNo
Apriel-1.6-15b-Thinker
$0.00$0.00131,0720.3260NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9234YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8257NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.86136YesNo
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30$0.30262,1440.55191YesNo
Qwen3-235B-A22B
$0.20$0.8040,9600.765NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0916YesYes
Llama-4-Maverick-17B-128E-Instruct
-------
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.36363YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.7518NoNo
GLM-4.7
fireworks-ai
fastest
--202,7521.8563YesNo
GLM-4.7
---2.7235YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.9423NoNo
GLM-4.6V-Flash
zai-org
fastest
---1.5480YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.84115YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.29136YesNo
tiny-aya-fire
---0.21124NoNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.9081YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.30137YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
$0.27$0.851,048,5760.5021NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
$0.27$0.851,048,5760.4152YesYes
MiniMax-M2
$0.30$1.20204,8002.3138YesNo
gemma-3n-E4B-it
$0.02$0.0432,7680.5919NoYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0923YesYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1441.10127NoYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.8719YesNo
command-a-reasoning-08-2025
---0.2779YesNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.8125NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2567NoNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8402.4123YesNo
DeepSeek-R1-0528
sambanova
fastest
$5.00$7.00131,0721.09181NoYes
DeepSeek-R1-0528
$3.00$3.00163,8400.6292NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.5167NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
$0.60$0.6032,7680.6841NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3037NoYes
aya-expanse-32b
---0.1843NoNo
command-a-translate-08-2025
---0.3166YesNo
GLM-4.5-Air-FP8
$0.20$1.10131,0720.2556YesYes
c4ai-command-r7b-arabic-02-2025
---0.20108YesNo
command-a-vision-07-2025
---0.2043NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9028NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.32106YesNo
tiny-aya-water
---0.26121NoNo
DeepSeek-R1-Distill-Llama-70B
novita
fastest
$0.80$0.808,1920.6051NoNo
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.8516NoYes
DeepSeek-R1-Distill-Llama-70B
---0.5338NoYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0722.0987YesNo
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
$0.30$0.30262,1440.66171YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50262,1440.33136YesYes
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.8429YesNo
GLM-4.6
together
fastest
$0.60$2.20202,7520.4871NoNo
GLM-4.6
---2.3131YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0352YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.1028YesNo
Kimi-K2-Instruct
-------
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.8819NoNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.6238YesNo
GLM-4.5
zai-org
fastest
---2.4649NoNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.60106NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.7021NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.9342NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.7928NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-1.26109NoYes
Qwen3-14B
$0.07$0.2040,9600.7338YesYes
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.8129YesNo
GLM-4.5V
zai-org
fastest
---2.4040YesNo
GLM-4.6V
---4.0221YesNo
GLM-4.5V-FP8
---2.5145YesNo
GLM-4.6V-FP8
---3.7219NoNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.2174NoNo
cogito-671b-v2.1
--163,8400.3534YesNo
GLM-4.7-FP8
together
cheapest fastest
$0.45$2.00202,7521.2069YesYes
GLM-4.7-FP8
---3.5334YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2276NoNo
GLM-4.6-FP8
---3.3232YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.5423YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.6817YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8401.2735YesNo
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8001.9240YesNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8001.14124NoNo
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0000.9479NoNo
c4ai-command-a-03-2025
---0.3134YesNo
c4ai-command-r7b-12-2024
---0.2284YesNo
c4ai-command-r-08-2024
---0.3322NoNo
aya-vision-32b
---0.3437NoNo
tiny-aya-earth
---0.26122NoNo
Arch-Router-1.5B
---0.1379NoYes
WizardLM-2-8x22B
$0.62$0.6265,5350.8310NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.6940NoNo
GLM-4-32B-0414
$0.55$1.6632,0000.9741NoNo
MiniMax-M1-80k
$0.55$2.201,000,0002.5536YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.8920NoYes
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0000.8556NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2242YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2642NoNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5123YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6235YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5948NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7589NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.7459NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.4947NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3045YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2364YesYes
Olmo-3.1-32B-Instruct
$0.20$0.60-0.9457YesYes
Llama-3.3-Swallow-70B-Instruct-v0.4
$0.60$1.20131,0723.45124NoYes