Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.74$3.481,048,5761.0356YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.6325YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5761.4576YesYes
DeepSeek-V4-Pro
---0.6228YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.7173YesNo
DeepSeek-V4-Flash
---0.3852YesNo
Qwen3.6-35B-A3B
---1.1190YesYes
Kimi-K2.6
novita
cheapest
$0.95$4.00262,1441.4848YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.3856YesYes
Kimi-K2.6
-------
Kimi-K2.6
---0.9817YesNo
Ling-2.6-1T
$0.00$0.00262,1440.7882YesYes
gemma-4-31B-it
novita
cheapest
$0.14$0.40262,1440.6025YesYes
gemma-4-31B-it
$0.20$0.50262,1440.3413YesYes
gemma-4-31B-it
deepinfra
fastest
---0.2330YesYes
GLM-5.1
together
cheapest fastest
$1.40$4.40202,7520.8181YesYes
GLM-5.1
--202,7521.2944YesNo
GLM-5.1
---3.5634YesNo
GLM-5.1
---0.7637YesYes
gemma-4-26B-A4B-it
novita
cheapest fastest
$0.13$0.40262,1440.5748YesNo
gemma-4-26B-A4B-it
---0.4638YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.3245YesNo
MiniMax-M2.7
$0.30$1.20196,6080.4615YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.51129YesNo
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.5550YesYes
Qwen3.5-9B
$0.12$0.18262,1440.3341YesYes
gpt-oss-120b
$0.15$0.75131,0720.14438YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.3835YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.151,200YesNo
gpt-oss-120b
$0.22$0.59131,0721.02457YesYes
gpt-oss-120b
$0.10$0.40131,0720.99104YesYes
gpt-oss-120b
-------
gpt-oss-120b
$0.15$0.60131,0720.34153YesNo
gpt-oss-120b
---0.37129YesYes
gpt-oss-120b
$0.09$0.47131,0720.26145YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4962NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.571,131NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7959NoYes
Llama-3.1-8B-Instruct
---0.30150YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.11844YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.6466NoYes
gpt-oss-20b
$0.05$0.20131,0720.98155NoYes
gpt-oss-20b
$0.05$0.20131,0720.31145YesNo
gpt-oss-20b
$0.05$0.20131,0720.5887YesNo
gpt-oss-20b
$0.05$0.18131,0720.5255YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21121YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.34112YesNo
Kimi-K2.5
$0.60$3.00262,1441.3941YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.4317YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.2858YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.28115YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3078YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.20263YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.6629YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0720.68261YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9316NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.76114NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.5452YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.55115NoNo
Llama-3.3-70B-Instruct
---0.2986YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.5623YesYes
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.2958YesNo
GLM-4.7-Flash
zai-org
fastest
---2.0259NoNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.80105YesNo
Qwen3.5-27B
$0.30$2.40262,1440.7537YesNo
Qwen3.5-122B-A10B
novita
cheapest
$0.40$3.20262,1440.6583YesNo
Qwen3.5-122B-A10B
deepinfra
fastest
---0.2996YesYes
Arch-Router-1.5B
---0.1173NoYes
Llama-3.2-1B-Instruct
--131,0000.41199NoNo
DeepSeek-R1
$0.70$2.5064,0002.0121YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.6698NoNo
DeepSeek-R1
$3.00$7.00163,8400.4885NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8686YesNo
MiniMax-M2.5
novita
cheapest fastest
$0.30$1.20204,8000.9862YesNo
MiniMax-M2.5
---0.6558YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.9058NoYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4985NoYes
MiMo-V2-Flash
$0.10$0.30262,1441.3394YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.2938YesNo
GLM-5
$1.00$3.20202,7520.7133YesYes
GLM-5
fireworks-ai
fastest
--202,7521.0672YesNo
GLM-5
---3.7336NoNo
c4ai-command-r7b-12-2024
---0.2371YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0721.0028NoYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9601.2053YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.37144YesNo
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.2133YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8402.9139YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8428NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3789YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.9123YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8000.9860YesNo
GLM-4.6
---2.0357YesNo
DeepSeek-V3
$0.40$1.3064,0001.0932YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.4542YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.7830YesNo
GLM-4.7
cerebras
fastest
---0.16448YesNo
GLM-4.7
--202,7521.58126YesNo
GLM-4.7
---2.4021YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.50365YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3765NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8432YesYes
gpt-oss-safeguard-20b
--131,0720.12792YesNo
gemma-3-27b-it
---0.3548YesYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.96137NoNo
gemma-3n-E4B-it
$0.06$0.1232,7680.4220NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7886NoYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7520.9347YesNo
GLM-5.1-FP8
---3.5135YesNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.42142YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.0049YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.4493YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.33108YesNo
Qwen3.5-397B-A17B
---0.2395YesYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0720.84393YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5036NoYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.27285YesNo
Qwen3-32B
$0.10$0.4540,9600.5646NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9601.0427YesYes
Qwen3-32B
$0.09$0.2532,7680.3533YesYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.7915NoNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.64101YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.30137YesNo
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.8662YesNo
Qwen3-VL-8B-Instruct
-------
Qwen3-30B-A3B
$0.09$0.4540,9600.8376YesNo
Step-3.5-Flash
---0.3423YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1414NoNo
Qwen3-14B
$0.07$0.2040,9601.0249YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.6161NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.8654NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5049NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.667NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.2430YesYes
command-a-reasoning-08-2025
---0.2686YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1047YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.27544YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0019YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2652YesYes
Qwen3-235B-A22B-Instruct-2507
---0.3263YesYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.7832YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.7959NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.4958YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1921.7032NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.6220NoYes
rnj-1-instruct
$0.15$0.1532,7680.19118YesYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2078YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0721.0294YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.39127YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0926YesYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.9650YesNo
GLM-4.6V-Flash
zai-org
fastest
---4.0365NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.9220YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5124YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.9256NoNo
aya-expanse-32b
---0.2440NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.9766NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0145YesNo
DeepSeek-OCR
$0.03$0.038,1920.79148NoNo
Kimi-K2-Thinking
$0.60$2.50262,1441.1439YesNo
QwQ-32B
$0.18$0.20131,0720.8028NoYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9955YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.4976NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2076YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.2468YesNo
GLM-4.5V-FP8
---2.3750YesNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.56108NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.5759YesNo
GLM-4.5V
---2.1050YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.70102YesNo
GLM-4.5-Air
---1.8194YesNo
c4ai-command-a-03-2025
---0.8225YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0721.2154YesNo
GLM-4.5
zai-org
fastest
---2.2258YesNo
command-a-vision-07-2025
---0.2646NoNo
c4ai-command-r-08-2024
---0.4314YesNo
command-a-translate-08-2025
---0.5067YesNo
c4ai-command-r7b-arabic-02-2025
---0.1995YesNo
GLM-4.6-FP8
---1.9843YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.5424YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.4846YesNo
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.4356NoNo
tiny-aya-fire
---0.17123NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2363NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.2663NoNo
cogito-671b-v2.1
-------
GLM-4.6V
---2.3444YesNo
GLM-4.7-FP8
---3.0733YesNo
tiny-aya-water
---0.37120NoNo
tiny-aya-global
---0.39118NoNo
tiny-aya-earth
---0.29120NoNo
aya-vision-32b
---0.4037NoNo
GLM-4.6V-FP8
---3.5041YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.6447NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.0516NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3085YesYes
MiniMax-M1-80k
$0.55$2.201,000,0001.1562YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0002.0218NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9391YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2143NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.0029YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7745YesNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.9537NoNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.6321YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.7657NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.4897NoYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.9620NoYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.88163YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.9537YesYes
MiniMax-M2
$0.30$1.20204,8001.1462YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6452NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.7812NoNo
Llama-3.1-70B-Instruct
---0.2887YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6295NoNo
MiniMax-M2.1
$0.30$1.20204,8001.3563YesNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5832NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2060YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.1245YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2347NoYes