Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.60$3.381,048,5760.9433YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.5735YesNo
DeepSeek-V4-Pro
--1,048,5760.9629YesNo
DeepSeek-V4-Pro
deepinfra
fastest
$1.74$3.4865,5360.6552YesYes
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5760.9267YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.8882YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.4422YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.65134YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.5723YesYes
gemma-4-31B-it
$0.39$0.97262,1440.5810YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.4517YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1442.2922YesNo
Kimi-K2.6
$1.20$4.50262,1440.3231YesYes
Kimi-K2.6
--262,1441.6428YesNo
Kimi-K2.6
deepinfra
fastest
$0.75$3.50262,1440.9141YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1441.1335YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.2751YesYes
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
nscale
cheapest
$0.06$0.06131,0720.8459NoYes
Llama-3.1-8B-Instruct
scaleway
fastest
---0.4772YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7520.5156YesYes
GLM-5.1
--202,7520.9344YesNo
GLM-5.1
---4.6727NoNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.7836YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.2248YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4041YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.0446YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3353YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.59121YesNo
gpt-oss-120b
$0.15$0.75131,0720.36420YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.38180YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.131,250YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0721.01108YesYes
gpt-oss-120b
$0.15$0.60131,0720.63115YesYes
gpt-oss-120b
$0.15$0.60131,0720.3990YesNo
gpt-oss-120b
---0.53174YesYes
gpt-oss-120b
$0.09$0.47131,0720.40120YesYes
Llama-3.2-1B-Instruct
--131,0000.4499NoNo
Qwen3-Coder-Next
$0.20$1.50262,1441.49116YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.7684YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.2198YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.20120YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.35123YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4137YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.26752YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.4970NoYes
gpt-oss-20b
$0.05$0.20131,0721.14153YesYes
gpt-oss-20b
$0.05$0.20131,0720.26128YesYes
gpt-oss-20b
$0.05$0.20131,0721.0974YesNo
gpt-oss-20b
$0.05$0.18131,0720.4050NoNo
Qwen3-8B
$0.07$0.1840,9601.0458YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.8487YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.13297YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.6032YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.0916NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.7280NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0721.0854YesYes
Llama-3.3-70B-Instruct
---0.2987YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3836YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.24398YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3952NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7533YesYes
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1441.2231YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.7143YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.1254YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1441.0596YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.36111YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.37111YesNo
Qwen3.5-397B-A17B
$0.49$3.60262,1440.5944YesYes
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.7445YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.9937NoYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.10$0.108,1920.59165NoYes
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.7562NoNo
GLM-4.7-Flash
zai-org
fastest
---3.0463YesNo
Qwen3-30B-A3B
$0.09$0.4540,9602.4748YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6494NoNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.8952YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.57153YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.94137NoNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.80109YesNo
DeepSeek-V3.2
$0.27$0.40163,8401.6727YesYes
DeepSeek-R1
$0.70$2.5064,0002.1621NoYes
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.42248YesNo
Qwen3-32B
$0.10$0.4540,9600.6555NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9826YesYes
Qwen3-32B
$0.09$0.2532,7680.2941YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5633NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.3445YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.1523YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.41102YesYes
MiMo-V2-Flash
$0.10$0.30262,1441.4696YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1441.0192YesNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0721.0166NoNo
Step-3.5-Flash
$0.10$0.30262,1440.2644YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.2831NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.5024YesNo
gemma-3-27b-it
---0.4848YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.2551NoYes
DeepSeek-OCR
$0.03$0.038,1920.81170NoNo
tiny-aya-earth
---0.67116NoNo
DeepSeek-V3
$0.40$1.3064,0001.1235YesNo
tiny-aya-water
---0.30120NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.6323YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8460NoYes
GLM-5
novita
cheapest
$1.00$3.20202,8002.3036YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.5556YesYes
GLM-5
---3.8335NoNo
c4ai-command-a-03-2025
---0.2546YesNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2082YesYes
MiniMax-M2
$0.30$1.20204,8001.1459YesNo
Qwen3.5-27B
$0.30$2.40262,1441.9433YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.3524YesYes
tiny-aya-fire
---0.22122NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.2111NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
GLM-4.6
$0.55$2.20204,8001.8540YesNo
GLM-4.6
-------
DeepSeek-V3-0324
$0.27$1.12163,8400.8635YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
Llama-3.1-70B-Instruct
---0.4485YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.66121NoYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.3547NoNo
GLM-5.1-FP8
---4.5826YesNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
GLM-4.7-FP8
---1.63102NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.0733YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.3752YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.6044YesNo
GLM-4.5-Air
zai-org
fastest
---2.6747YesNo
Gemma-4-31B-it-pearl
$0.28$0.8632,0000.3730YesNo
WizardLM-2-8x22B
$0.62$0.6265,5351.4710NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7037YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.6636YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.8268YesNo
Qwen3-235B-A22B
$0.20$0.8040,9600.546NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.2423YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7682YesNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.47109NoNo
gpt-oss-safeguard-20b
--131,0720.23829YesNo
aya-expanse-32b
---0.2141NoNo
c4ai-command-r7b-12-2024
---0.2175YesNo
command-a-reasoning-08-2025
---0.2986YesNo
QwQ-32B
$0.18$0.20131,0721.0829YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5361.1826NoYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7949YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0721.0756NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8526NoYes
tiny-aya-global
---0.30122NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9428NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.33112YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.4244NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.0817NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4386YesYes
Ling-2.6-1T
$0.30$2.50262,1441.1584YesNo
Qwen3-14B
$0.07$0.2040,9601.0443YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.1958YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.4576NoNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.1984YesYes
Arch-Router-1.5B
---0.1075NoYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.6331YesNo
GLM-4.7
cerebras
fastest
---0.21278YesNo
GLM-4.7
-------
rnj-1-instruct
$0.15$0.1532,7680.32120YesYes
command-a-vision-07-2025
---0.1746NoNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.9350YesNo
GLM-4.5
---2.7031YesNo
c4ai-command-r7b-arabic-02-2025
---0.2897YesNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5361.2017NoNo
GLM-4.5V
---2.8915YesNo
GLM-4.5V-FP8
---3.0425YesNo
GLM-4.6V
---3.4532YesNo
aya-vision-32b
---0.3037NoNo
GLM-4.6V-FP8
---2.4144YesNo
c4ai-command-r-08-2024
---1.514NoNo
DeepSeek-V3.1
$0.27$1.00131,0721.5626YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.9777NoYes
MiniMax-M2.1
$0.30$1.20204,8001.1657YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5361.6017NoNo
Kimi-K2-Thinking
$0.60$2.50262,1441.0451NoNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.05110YesNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.6183NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.7255YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.1152NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.1448YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2266YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.4222YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.6921YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2362NoNo
cogito-671b-v2.1
-------
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2040NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5219NoNo
MiniMax-M1-80k
$0.55$2.201,000,0002.3138YesNo
DeepSeek-R1-0528
$0.70$2.50163,8402.2121YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.6112NoNo
GLM-4-32B-0414
$0.55$1.6632,0000.7639NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6931NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5121NoYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2667NoNo