Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.74$3.481,048,5761.0233YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0002.2935NoYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.5378YesYes
DeepSeek-V4-Pro
$1.74$3.4865,5360.3630YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.6187YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5762.1526YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.38113YesYes
gemma-4-31B-it
-------
gemma-4-31B-it
together
fastest
$0.20$0.50262,1440.2843YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.2933YesYes
Kimi-K2.6
$0.95$4.00262,1441.6534YesNo
Kimi-K2.6
$1.20$4.50262,1441.3928YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.2290YesNo
Kimi-K2.6
deepinfra
cheapest
$0.75$3.50262,1440.719YesYes
Ling-2.6-1T
$0.00$0.00262,1440.7770YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7520.5471YesYes
GLM-5.1
--202,7521.1429YesNo
GLM-5.1
---3.5833YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.7860YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1442.7626YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.1952YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.1031YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3848YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6082.2285YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4069NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.161,123NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8659NoYes
Llama-3.1-8B-Instruct
---0.32127YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.6041YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4541YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.10799YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.4583NoYes
gpt-oss-20b
$0.05$0.20131,0721.03155YesNo
gpt-oss-20b
$0.05$0.20131,0720.28135YesYes
gpt-oss-20b
$0.05$0.20131,0720.4999YesNo
gpt-oss-20b
$0.05$0.18131,0720.3468YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.25114YesYes
gpt-oss-120b
$0.15$0.75131,0720.16439YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4849YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.19957YesNo
gpt-oss-120b
$0.22$0.59131,0720.38639YesYes
gpt-oss-120b
$0.10$0.40131,0720.91112YesYes
gpt-oss-120b
$0.15$0.60131,0720.2567YesYes
gpt-oss-120b
$0.15$0.60131,0720.78138YesNo
gpt-oss-120b
---0.34164YesYes
gpt-oss-120b
$0.09$0.47131,0720.2551YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.97124YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.5396YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.20278YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5943YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0720.84263YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9917NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.71105NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.7476YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.36170NoNo
Llama-3.3-70B-Instruct
---0.3264YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3529YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.5172YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3762YesYes
GLM-4.7-Flash
-------
GLM-4.7-Flash
---2.1082NoNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.0559YesNo
MiniMax-M2.5
fireworks-ai
fastest
---1.61121YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.3593YesNo
Qwen3.5-27B
$0.30$2.40262,1440.6540YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8683YesNo
Kimi-K2.5
$0.60$3.00262,1441.1942YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.4716YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.3578YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4391NoYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9601.1257YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.3073YesNo
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.3624YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.6638YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.97100YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.3993YesYes
gemma-3-27b-it
---0.4746YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7361NoYes
GLM-5
novita
cheapest
$1.00$3.20202,8001.6732YesNo
GLM-5
$1.00$3.20202,7521.2246YesYes
GLM-5
fireworks-ai
fastest
--202,7521.0773YesNo
GLM-5
---3.7039NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9027NoYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9128NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3980YesNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.7453YesNo
GLM-4.6
zai-org
fastest
---2.0355YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.9054YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
Llama-3.2-1B-Instruct
--131,0000.41199NoNo
gpt-oss-safeguard-20b
--131,0720.21779YesNo
Arch-Router-1.5B
---0.1377NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.2647YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0620YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.3928YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.4568NoYes
Step-3.5-Flash
$0.10$0.30262,1440.2732YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2239NoNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0721.15268YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3552NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.9133YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5736NoYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.9437NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.9166NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.6132YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.81140NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6080NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.8986NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7657NoYes
DeepSeek-V3
$0.40$1.3064,0001.0833YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.4934YesYes
Qwen3.5-397B-A17B
$0.60$3.60262,1440.9346YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.4667YesYes
Qwen3.5-397B-A17B
---1.4751YesNo
Qwen3.5-397B-A17B
deepinfra
cheapest fastest
$0.54$3.40262,1440.2592YesYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.1612NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.8343YesNo
GLM-4.7
cerebras
fastest
---0.15425YesNo
GLM-4.7
--202,7524.0734YesNo
GLM-4.7
---2.4139YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.24257YesNo
Qwen3-32B
$0.10$0.4540,9600.7732NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9601.0527YesNo
Qwen3-32B
$0.09$0.2532,7680.4227YesYes
GLM-5.1-FP8
--202,7520.8625YesNo
GLM-5.1-FP8
zai-org
fastest
---3.6333YesNo
c4ai-command-r7b-12-2024
---0.2570YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3137NoYes
Qwen3-30B-A3B
$0.09$0.4540,9600.7243YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.6625NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.2919YesNo
rnj-1-instruct
$0.15$0.1532,7680.14121YesYes
Qwen3-235B-A22B
$0.20$0.8040,9600.887NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0329YesYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.9232YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.6559NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.4550YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.9892YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.36131YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.7697NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6761NoYes
DeepSeek-R1
$0.70$2.5064,0001.7524YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8401.0998NoNo
DeepSeek-R1
$3.00$7.00163,8400.4892NoYes
GLM-4.6V-Flash
$0.30$0.90131,0720.6447YesNo
GLM-4.6V-Flash
-------
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4422NoYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.49140YesYes
command-a-reasoning-08-2025
---0.4372YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.7024YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1441.0538YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.6076NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.1941YesYes
DeepSeek-OCR
$0.03$0.038,1920.67203NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.3150YesYes
aya-expanse-32b
---0.1841NoNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.9621NoYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2425YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9849YesNo
QwQ-32B
$0.18$0.20131,0720.7929NoYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.34330YesYes
Qwen3-14B
$0.07$0.2040,9600.7949YesYes
GLM-4.7-FP8
---3.0445YesNo
GLM-4.5V-FP8
---3.1332YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.2325YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.4738NoYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.5248NoNo
c4ai-command-r-08-2024
---0.982NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2857NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.2856NoNo
cogito-671b-v2.1
-------
GLM-4.6V-FP8
---2.8937YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6243NoNo
GLM-4.6V
---2.5248YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.86115YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.27130YesNo
c4ai-command-a-03-2025
---1.5035YesNo
MiniMax-M2.1
$0.30$1.20204,8001.3964YesNo
Kimi-K2-Thinking
$0.60$2.50262,1440.9847YesNo
GLM-4.6-FP8
---2.6655YesNo
tiny-aya-fire
---0.56118NoNo
aya-vision-32b
---0.4936NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.9528YesNo
GLM-4.5V
---3.5227YesNo
tiny-aya-earth
---1.23107NoNo
tiny-aya-global
---1.30104NoNo
tiny-aya-water
---0.51117NoNo
command-a-translate-08-2025
---0.3868YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6987YesNo
GLM-4.5-Air
---2.1278YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.7256NoNo
GLM-4.5
---2.4755YesNo
command-a-vision-07-2025
---0.1747NoNo
c4ai-command-r7b-arabic-02-2025
---0.2098YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7940YesNo
GLM-4-32B-0414
$0.55$1.6632,0000.8840NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8095YesNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.3118YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.6957NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.5191NoYes
MiniMax-M1-80k
$0.55$2.201,000,0001.1153YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.9018NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2443NoNo
Kimi-K2-Instruct
$0.57$2.30131,0720.9329YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3546NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.0716NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3165YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8231YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.8763YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.96165YesNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5535NoNo
Llama-3.1-70B-Instruct
---0.4365YesYes
WizardLM-2-8x22B
$0.62$0.6265,5351.1912NoNo
MiniMax-M2
$0.30$1.20204,8000.8359YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.6941NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2565YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2745YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2548NoYes