Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.67$3.381,048,5761.0226YesNo
DeepSeek-V4-Pro
together
fastest
$2.10$4.40512,0001.7353NoYes
DeepSeek-V4-Pro
--1,048,5761.0639YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.6822YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5761.2295YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.5535YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.24130YesYes
gemma-4-31B-it
$0.14$0.40262,1440.5611YesYes
gemma-4-31B-it
$0.20$0.50262,1440.4613YesYes
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.5915YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.9443YesNo
Kimi-K2.6
$1.20$4.50262,1440.5655YesNo
Kimi-K2.6
fireworks-ai
fastest
--262,1440.4658YesNo
Kimi-K2.6
$0.75$3.50262,1440.5245YesNo
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.2774YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4234YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7521.8035YesYes
GLM-5.1
--202,7521.7128YesNo
GLM-5.1
---4.0128YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7523.2922YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.6345YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.4351YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4248NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.181,444NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8361NoYes
Llama-3.1-8B-Instruct
---0.36129YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.25854YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.3967NoYes
gpt-oss-20b
$0.05$0.20131,0721.01146YesYes
gpt-oss-20b
$0.05$0.20131,0720.28120YesYes
gpt-oss-20b
$0.05$0.20131,0720.7560YesNo
gpt-oss-20b
$0.05$0.18131,0720.3883YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.4131YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3846YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.41159YesNo
gpt-oss-120b
$0.15$0.75131,0720.17439YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.3766YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.161,191YesNo
gpt-oss-120b
$0.22$0.59131,0720.68563NoYes
gpt-oss-120b
$0.10$0.40131,0720.8799YesYes
gpt-oss-120b
$0.15$0.60131,0720.29124YesYes
gpt-oss-120b
$0.15$0.60131,0720.39121YesNo
gpt-oss-120b
---0.3994YesYes
gpt-oss-120b
$0.09$0.47131,0721.6843YesNo
Ling-2.6-1T
$0.30$2.50262,1441.0680YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.22123YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4869YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4853YesYes
Kimi-K2.5
$0.60$3.00262,1441.1737YesYes
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.4445YesYes
Kimi-K2.5
-------
DeepSeek-R1
$0.70$2.5064,0001.8622YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-OCR
$0.03$0.038,1920.68151NoNo
Qwen3-Coder-Next
$0.20$1.50262,1441.25118YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.5546YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
Step-3.5-Flash
$0.10$0.30262,1440.2856YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9873YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.42118YesNo
Llama-3.2-1B-Instruct
--131,0000.56189NoNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.7289YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5132NoYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4374NoNo
Qwen3-8B
$0.07$0.1840,9600.9257YesNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.8151YesYes
DeepSeek-V3.2
$0.27$0.40163,8401.4626YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1442.0148YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.80191YesYes
Qwen3.5-397B-A17B
---0.4836YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2391YesYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.8972YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.4450YesYes
Qwen3.5-27B
$0.30$2.40262,1441.1364YesNo
QwQ-32B
$0.18$0.20131,0721.0128YesYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.95140NoNo
Qwen3-14B
$0.07$0.2040,9600.7850YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8254YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.1345YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.5476NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.1763YesYes
GLM-5.1-FP8
--202,7521.2522YesNo
GLM-5.1-FP8
zai-org
fastest
---4.2029NoNo
gemma-3-27b-it
---0.4747YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8959NoYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8328NoYes
DeepSeek-V3-0324
$0.27$1.12163,8401.0435YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3
$0.40$1.3064,0000.9535YesNo
DeepSeek-V3
-------
Kimi-K2-Instruct-0905
$0.60$2.50262,1442.6934YesNo
gpt-oss-safeguard-20b
--131,0720.18814YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8459NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.58125NoYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.32371YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4344NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8433YesYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.83302YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.8348YesNo
GLM-4.7
cerebras
fastest
---0.17451YesNo
GLM-4.7
-------
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0721.1962NoNo
Arch-Router-1.5B
---0.1279NoYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7026YesYes
Llama-3.1-70B-Instruct
---0.3280YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7980YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.23257YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4545YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0720.93251YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9617NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.3438NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0721.6045YesYes
Llama-3.3-70B-Instruct
---0.2578YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4025YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.3060NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.455NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.1124YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8128NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.2976YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.18280YesNo
Qwen3-32B
$0.10$0.4540,9600.5546NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9524YesYes
Qwen3-32B
$0.09$0.2532,7680.3339YesYes
GLM-5
novita
cheapest
$1.00$3.20202,8002.8022YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.5663YesYes
GLM-5
---4.2431NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8895YesNo
WizardLM-2-8x22B
$0.62$0.6265,5350.8011NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6483NoNo
tiny-aya-earth
---0.24121NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0752YesNo
GLM-4.6
$0.55$2.20204,8001.7230YesNo
GLM-4.6
-------
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5923YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.86168YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.1051YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6418NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.3623YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.7720YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.9437NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7871NoYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.1713NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.6031YesNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.7648YesNo
GLM-4.5V
---2.5642YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6668YesNo
GLM-4.5-Air
---2.0448YesNo
GLM-4.5V-FP8
---2.4242YesNo
GLM-4.6V
---2.7045YesNo
tiny-aya-fire
---0.19122NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.4256YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.1063NoNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.2749YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.31596YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.1419YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.4537YesYes
Qwen3-235B-A22B-Instruct-2507
---0.3690YesYes
GLM-4.6V-FP8
---1.6577YesNo
c4ai-command-r-08-2024
---0.2054YesNo
GLM-4.7-FP8
---1.9961YesNo
command-a-vision-07-2025
---0.2446NoNo
aya-vision-32b
---0.2736NoNo
aya-expanse-32b
---0.1841NoNo
c4ai-command-r7b-12-2024
---0.2378YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.9343YesNo
GLM-4.5
zai-org
fastest
---2.0854YesNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.1967YesYes
c4ai-command-a-03-2025
---3.8715NoNo
tiny-aya-global
---0.18120NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2752NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.3052NoNo
cogito-671b-v2.1
-------
rnj-1-instruct
$0.15$0.1532,7680.21123YesYes
tiny-aya-water
---0.24120NoNo
Gemma-4-31B-it-pearl
$0.28$0.8632,0000.1954YesNo
command-a-translate-08-2025
---0.4165YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.1439NoNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7146YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.5213NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.0945YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5920NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3844NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.5439YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.8029NoYes
DeepSeek-V3.1
$0.27$1.00131,0721.7124YesYes
DeepSeek-V3.1
-------
MiniMax-M2.1
$0.30$1.20204,8001.3764YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.5194YesNo
MiniMax-M2
$0.30$1.20204,8000.8364YesNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.01100YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.4223YesYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6753NoYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3548NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9517NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3674YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-0.8765YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2648YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.1952NoYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5222NoYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.45109NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6126NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1921.0034NoNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.9425NoYes