Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.69$3.381,048,5761.7863YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.5452YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.6678YesYes
DeepSeek-V4-Pro
$1.74$3.4865,5360.5126YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.23138YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5761.2625YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.8011YesYes
gemma-4-31B-it
$0.14$0.40262,1440.7716YesYes
gemma-4-31B-it
$0.20$0.50262,1440.3813YesYes
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.5317YesYes
Kimi-K2.6
$0.95$4.00262,1442.0933YesNo
Kimi-K2.6
$1.20$4.50262,1440.4030YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.2775YesNo
Kimi-K2.6
deepinfra
cheapest
$0.75$3.50262,1440.6849YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1440.3956YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.5545NoYes
GLM-5.1
together
fastest
$1.40$4.40202,7520.3844YesYes
GLM-5.1
--202,7521.2127YesNo
GLM-5.1
---3.6633YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.9026YesYes
Ling-2.6-1T
$0.30$2.50262,1441.3476YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3295YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4939YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.22745YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.5473NoNo
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.20131,0720.38179YesYes
gpt-oss-20b
$0.05$0.20131,0720.7150YesNo
gpt-oss-20b
$0.05$0.18131,0720.4991YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.3948NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.121,842NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
---0.32147YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8000.9940YesNo
MiniMax-M2.7
$0.30$1.20196,6080.4247YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.3490YesNo
Qwen3-Coder-Next
$0.20$1.50262,1440.92120YesNo
gpt-oss-120b
$0.15$0.75131,0720.17442YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.3758YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.141,087YesNo
gpt-oss-120b
$0.22$0.59131,0720.98488YesYes
gpt-oss-120b
-------
gpt-oss-120b
$0.15$0.60131,0720.2742YesYes
gpt-oss-120b
$0.15$0.60131,0720.37161YesNo
gpt-oss-120b
---0.41178YesYes
gpt-oss-120b
$0.09$0.47131,0720.3069YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4195YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.6864YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21116YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.70114YesNo
Qwen3-8B
-------
Qwen3-8B
--40,9600.30111YesNo
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.6937YesYes
Qwen3-VL-8B-Instruct
-------
MiMo-V2-Flash
$0.10$0.30262,1441.7688YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.5685YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.2396YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.21254YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4541YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0723.68146YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0722.0621NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.60105YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.3891NoNo
Llama-3.3-70B-Instruct
---0.3277YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.5136YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.8967YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.47147YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.3890NoYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.4732YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.0955YesNo
Qwen3.5-27B
$0.30$2.40262,1440.5266YesNo
Qwen2.5-Coder-32B-Instruct
-------
Qwen2.5-Coder-32B-Instruct
---0.34117YesNo
GLM-4.7-Flash
$0.07$0.40200,0001.0960NoNo
GLM-4.7-Flash
-------
gemma-3-27b-it
---0.4048YesYes
Step-3.5-Flash
$0.10$0.30262,1440.4582YesNo
Kimi-K2.5
$0.60$3.00262,1441.0837YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.6216YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.32101YesNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.8540YesNo
GLM-4.6
zai-org
fastest
---1.8472YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7792YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7692NoNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.6938YesNo
GLM-5
$1.00$3.20202,7520.6057YesYes
GLM-5
fireworks-ai
fastest
--202,7521.1068YesNo
GLM-5
---3.0541YesNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.56126YesYes
GLM-5.1-FP8
--202,7521.6023YesNo
GLM-5.1-FP8
zai-org
fastest
---3.3136YesNo
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.2236YesNo
DeepSeek-V3
together
cheapest
$1.25$1.25131,0721.2625YesYes
Arch-Router-1.5B
---0.1073NoYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.7038YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
together
fastest
$1.25$1.25131,0720.5147YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8233YesYes
DeepSeek-R1
$0.70$2.5064,0001.4821YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.8098NoNo
DeepSeek-R1
-------
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.3241YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.6230YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.7649YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.0754YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.62159YesYes
Qwen3.5-397B-A17B
---0.5098YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2691YesYes
tiny-aya-global
---0.19122NoNo
gemma-3n-E4B-it
$0.06$0.1232,7680.4327NoYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.2711NoNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2032YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0745YesNo
Llama-3.2-1B-Instruct
--131,0000.45193NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.8141YesNo
GLM-4.6V-Flash
zai-org
fastest
---2.5770NoNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9257YesNo
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.4876NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1441.1023YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6836NoNo
gpt-oss-safeguard-20b
--131,0720.17795YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.6242YesNo
GLM-4.5
zai-org
fastest
---2.2555YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.80108YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.20117YesNo
c4ai-command-r7b-12-2024
---0.2277YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4536NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.8577NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2848NoYes
DeepSeek-OCR
$0.03$0.038,1920.70183NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.7533YesNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.22359YesYes
c4ai-command-a-03-2025
---0.3228YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4424NoYes
rnj-1-instruct
$0.15$0.1532,7680.23121YesYes
command-a-translate-08-2025
---0.3169YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.2265NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2468NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.7753YesNo
GLM-4.7
cerebras
fastest
---0.14441YesNo
GLM-4.7
--202,7522.2850YesNo
GLM-4.7
---2.2455YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.4531YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.4545YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.3157NoNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.9423YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.7757NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.5696NoYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.92121YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.29138YesNo
tiny-aya-fire
---0.18123NoNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.5798YesNo
GLM-4.5-Air
---1.6193YesNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.1848YesYes
c4ai-command-r-08-2024
---0.2243YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4331YesYes
GLM-4.7-FP8
---2.8047NoNo
GLM-4.6V-FP8
---2.3743YesNo
GLM-4.6V
---2.7242YesNo
GLM-4.5V-FP8
---2.1354YesNo
GLM-4.6-FP8
---2.5652YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.5534YesNo
GLM-4.5V
zai-org
fastest
---2.0645YesNo
tiny-aya-earth
---0.16122NoNo
aya-expanse-32b
---0.3243NoNo
aya-vision-32b
---0.2737NoNo
c4ai-command-r7b-arabic-02-2025
---0.1899YesNo
command-a-vision-07-2025
---0.1747NoNo
command-a-reasoning-08-2025
---0.2684YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.16273YesNo
Qwen3-32B
$0.10$0.4540,9600.5937NoNo
Qwen3-32B
-------
Qwen3-32B
ovhcloud
cheapest
$0.09$0.2532,7680.7626YesYes
tiny-aya-water
---0.18122NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.84165YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.2030YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.0843NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8254YesNo
WizardLM-2-8x22B
$0.62$0.6265,5350.9512NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5624NoYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.34114NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5233NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.0429YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.4936NoNo
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
$0.80$0.808,1920.4348NoNo
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3275YesYes
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.4722NoYes
MiniMax-M1-80k
$0.55$2.201,000,0001.0363YesNo
Llama-4-Scout-17B-16E-Instruct
groq
cheapest fastest
$0.11$0.34131,0720.24391YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3257NoNo
Llama-4-Scout-17B-16E-Instruct
-------
GLM-4-32B-0414
$0.55$1.6632,0000.8547NoNo
Qwen3-235B-A22B
$0.20$0.8040,9601.528NoNo
Qwen3-235B-A22B
-------
Qwen3-30B-A3B
$0.09$0.4540,9600.9372YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.7013NoNo
MiniMax-M2.1
$0.30$1.20204,8001.2865YesNo
Llama-3.1-70B-Instruct
---0.4477YesYes
Kimi-K2-Thinking
$0.60$2.50262,1440.8023YesNo
MiniMax-M2
$0.30$1.20204,8000.9861YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.1766YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3545YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.6760NoYes