Inference Providers

·

Metrics for top trending models

GLM-5.1
together
cheapest
$1.40$4.40202,7520.7930YesYes
GLM-5.1
--202,7521.3415YesNo
GLM-5.1
zai-org
fastest
---3.5036YesNo
gemma-4-31B-it
novita
cheapest
$0.14$0.40262,1441.2115YesYes
gemma-4-31B-it
together
fastest
$0.20$0.50262,1440.3218YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8002.6331YesNo
MiniMax-M2.7
$0.30$1.20196,6080.83132YesYes
MiniMax-M2.7
fireworks-ai
fastest
---1.03157YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1442.4244NoYes
GLM-5.1-FP8
---3.9236NoNo
Qwen3.5-9B
$0.10$0.15262,1440.3774YesYes
Qwen3.5-27B
$0.30$2.40262,1440.7058YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.2439YesNo
GLM-5
$1.00$3.20202,7520.6537YesYes
GLM-5
fireworks-ai
fastest
--202,7520.9672YesNo
GLM-5
---3.8637YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.90132YesNo
gpt-oss-120b
$0.15$0.75131,0720.16437YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4151YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.251,061YesNo
gpt-oss-120b
$0.22$0.59131,0720.56592YesYes
gpt-oss-120b
$0.10$0.40131,0720.77111YesYes
gpt-oss-120b
$0.15$0.60131,0720.30134YesYes
gpt-oss-120b
$0.15$0.60131,0720.51122YesNo
gpt-oss-120b
---0.44162YesYes
gpt-oss-120b
$0.09$0.47131,0720.32117YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.61132YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.74173YesNo
Qwen3-Coder-Next
$0.20$1.50262,1441.43109YesNo
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.0457YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.4054YesYes
Kimi-K2.5
--262,1440.5026NoNo
DeepSeek-R1
$0.70$2.5064,0001.7130YesYes
DeepSeek-R1
sambanova
fastest
---0.72130YesYes
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.7799NoNo
DeepSeek-R1
$3.00$7.00163,8400.42103NoYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.8853YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.8875YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.37109YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.16837YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.6852NoYes
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.20131,0720.19168YesYes
gpt-oss-20b
$0.05$0.20131,0720.4281YesNo
gpt-oss-20b
$0.05$0.18131,0720.42112YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.8073NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.251,183NoNo
Llama-3.1-8B-Instruct
$0.10$0.2016,3840.60613YesYes
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7960NoYes
Llama-3.1-8B-Instruct
---0.3171YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.20136YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.4135YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.7456YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1441.2999YesNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.7858YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.2699YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.5186NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.23284YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4747YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0721.05227YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9217NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.85107YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.6299YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.44132NoNo
Llama-3.3-70B-Instruct
---0.4282YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3939YesYes
MiMo-V2-Flash
$0.10$0.30262,1441.1091YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8185YesNo
Llama-3.2-1B-Instruct
--131,0000.79184NoNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.3394YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4770YesYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.50128YesYes
DeepSeek-V3
$0.40$1.3064,0001.1133YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.7952NoYes
QwQ-32B
$0.18$0.20131,0720.9828YesYes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.8862YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.2576NoYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8362NoYes
Kimi-K2-Instruct
$0.57$2.30131,0720.8429YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9327NoYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.18387YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3254NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7333YesYes
gemma-3-27b-it
---0.4048YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.6956YesNo
GLM-4.7
cerebras
fastest
---0.22426YesNo
GLM-4.7
--202,7520.96160YesNo
GLM-4.7
---2.1753YesNo
gemma-3n-E4B-it
$0.02$0.0432,7680.2415NoYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.1732YesNo
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0720.42204YesYes
DeepSeek-V3-0324
$1.25$1.25163,8400.8525YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.5954YesYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8402.3023YesNo
DeepSeek-R1-0528
$5.00$7.00131,0724.1491YesYes
DeepSeek-R1-0528
hyperbolic
fastest
$3.00$3.00163,8400.6294NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.4390NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.88139NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8466NoNo
gpt-oss-safeguard-20b
--131,0720.38694YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.82118YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.34139YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.7176YesNo
GLM-4.5-Air
zai-org
fastest
---1.7577YesNo
DeepSeek-R1-Distill-Llama-70B
novita
fastest
$0.80$0.808,1920.3948NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.0117NoNo
DeepSeek-R1-Distill-Llama-70B
---0.6538NoYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.7221NoNo
Kimi-K2-Thinking
novita
cheapest
$0.60$2.50262,1441.0139YesNo
Kimi-K2-Thinking
fireworks-ai
fastest
---1.1270YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2830YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0721.17112YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.44136YesNo
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.16165YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1441.6416YesYes
Kimi-K2-Instruct-0905
--262,1440.8218YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.7222YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.9675NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7556NoYes
Llama-3.1-70B-Instruct
---0.4783YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.22275YesNo
Qwen3-32B
$0.10$0.4540,9600.8151NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.8727YesYes
Qwen3-32B
$0.09$0.2532,7680.4439YesYes
Qwen3-14B
$0.07$0.2040,9600.9251YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.7649NoNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8000.6768YesNo
GLM-4.6
---2.4562YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.79117NoYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7924YesYes
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.8346YesNo
GLM-4.5
zai-org
fastest
---2.6947YesNo
GLM-4.6V
---4.9323NoNo
rnj-1-instruct
$0.15$0.1532,7680.17121YesYes
tiny-aya-global
---0.18122NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3836NoYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8728NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.4382YesNo
command-a-translate-08-2025
---0.3366YesNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0720.85378YesYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.2542YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.24500YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9524YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.5246YesYes
Qwen3-235B-A22B-Instruct-2507
---0.35101YesYes
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.8426NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2467NoNo
command-a-reasoning-08-2025
---0.2980YesNo
c4ai-command-r7b-arabic-02-2025
---0.17110YesNo
aya-expanse-32b
---0.1944NoNo
c4ai-command-r-08-2024
---0.2514YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.0450YesNo
GLM-4.5V
zai-org
fastest
---1.9563YesNo
GLM-4.6-FP8
---2.0345YesNo
GLM-4.5V-FP8
---1.9562YesNo
GLM-4.6V-FP8
---3.9322NoNo
GLM-4.7-FP8
---1.9967YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.0241NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.3511NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0323YesYes
Qwen3-30B-A3B
$0.09$0.4540,9600.8374NoNo
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0000.9567NoNo
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0001.0281NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1844NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0721.07157YesNo
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8001.8747YesNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8000.68151YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5236YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6366NoNo
Arch-Router-1.5B
---0.1171NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.5746NoYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4836NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8496YesNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5619NoYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9845YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.4680YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.1884YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.8282NoYes
tiny-aya-earth
---0.22122NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.9459NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.4445YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9951YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0721.1545YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.7218NoYes
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.4430YesYes
DeepSeek-V3.1
together
fastest
$0.60$1.70131,0720.4852YesYes
DeepSeek-V3.1
--163,8400.4552NoNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.6170YesNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.3362YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5530YesYes
c4ai-command-a-03-2025
---0.5529YesNo
tiny-aya-fire
---0.19122NoNo
c4ai-command-r7b-12-2024
---0.2199YesNo
MiniMax-M2
$0.30$1.20204,8001.0351YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.2011NoNo
aya-vision-32b
---0.2937NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.7245NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.8338NoNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.71104NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.979NoNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.2874NoNo
cogito-671b-v2.1
--163,8400.5334YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.1875NoNo
tiny-aya-water
---0.17123NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2283YesYes