Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.64$3.381,048,5760.8931YesNo
DeepSeek-V4-Pro
together
fastest
$2.10$4.40512,0000.6643YesYes
DeepSeek-V4-Pro
--1,048,5761.1337YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.5438YesYes
command-a-plus-05-2026-w4a4
---0.4848YesNo
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5760.6471YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.7789YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.5725YesYes
command-a-plus-05-2026-bf16
---0.2354YesNo
Qwen3.6-35B-A3B
$0.15$0.95262,1440.23134YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.6019YesYes
gemma-4-31B-it
$0.20$0.50262,1440.6813YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1441.3416YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1442.4324YesNo
Kimi-K2.6
$1.20$4.50262,1440.3517YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.3789YesNo
Kimi-K2.6
$0.75$3.50262,1440.7513YesNo
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1441.4530YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1441.0721YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.3746NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.141,342NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7760NoYes
Llama-3.1-8B-Instruct
---0.32125YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7521.2946YesYes
GLM-5.1
--202,7521.6117YesNo
GLM-5.1
---4.4726YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7521.0422YesYes
command-a-plus-05-2026-fp8
---0.6169YesNo
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3069YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4640YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.19809YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.5152NoYes
gpt-oss-20b
$0.05$0.20131,0720.92151YesYes
gpt-oss-20b
$0.05$0.20131,0720.28151YesNo
gpt-oss-20b
$0.05$0.20131,0720.6490YesNo
gpt-oss-20b
$0.05$0.18131,0720.4524YesYes
gpt-oss-120b
$0.15$0.75131,0720.18426YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.39227YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.151,116YesNo
gpt-oss-120b
$0.22$0.59131,0720.50564NoNo
gpt-oss-120b
$0.10$0.40131,0720.92108YesYes
gpt-oss-120b
$0.15$0.60131,0720.27142YesYes
gpt-oss-120b
$0.15$0.60131,0720.37181YesNo
gpt-oss-120b
---0.35150YesYes
gpt-oss-120b
$0.09$0.47131,0720.4295YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.0143YesNo
MiniMax-M2.7
$0.30$1.20196,6081.2727YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6081.9765NoNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.23113YesYes
Llama-3.2-1B-Instruct
--131,0000.46198NoNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.3467YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4816YesYes
Kimi-K2.5
$0.60$3.00262,1441.1536YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.4162YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.5481YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.8198YesNo
Step-3.5-Flash
$0.10$0.30262,1440.4430YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4877NoYes
Qwen3-Coder-Next
$0.20$1.50262,1441.19115YesNo
Qwen3-8B
$0.07$0.1840,9600.9357YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7786YesNo
Ling-2.6-1T
$0.30$2.50262,1441.0486YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.8169YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.74107YesNo
DeepSeek-R1
$0.70$2.5064,0001.6025YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
-------
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.3160YesNo
GLM-4.7-Flash
zai-org
fastest
---2.0268NoNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.8435YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.1253YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.61182YesYes
Qwen3.5-397B-A17B
---0.4487YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.4430YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2846YesYes
DeepSeek-OCR
$0.03$0.038,1921.02197NoNo
QwQ-32B
$0.18$0.20131,0720.8329YesYes
Qwen3.5-27B
$0.30$2.40262,1441.5052YesNo
DeepSeek-V3
$0.40$1.3064,0001.1033YesNo
DeepSeek-V3
-------
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3624NoYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.8688YesYes
GLM-5
novita
cheapest
$1.00$3.20202,8003.8922NoNo
GLM-5
together
fastest
$1.00$3.20202,7522.1672YesYes
GLM-5
---4.0931YesNo
gpt-oss-safeguard-20b
--131,0720.11846YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.7575YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.2730YesYes
tiny-aya-earth
---0.82113NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9395YesNo
gemma-3-27b-it
---0.5246YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.19263YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5537YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0721.53225YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9617NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.1750NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.7880YesYes
Llama-3.3-70B-Instruct
---0.3181YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4034YesYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.37340YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.88319YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3862NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7733YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.66120NoYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.5135YesNo
GLM-5.1-FP8
---4.4729NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.9456NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8267NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.4135YesNo
GLM-4.7
cerebras
fastest
---0.26491YesNo
GLM-4.7
-------
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6387NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5730YesNo
DeepSeek-V3-0324
$0.27$1.12163,8400.8833YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.0561YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7740YesYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.8043YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.7355YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.1435YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.35282YesNo
Qwen3-32B
$0.10$0.4540,9600.4944NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9601.0827YesYes
Qwen3-32B
$0.09$0.2532,7680.3340YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.2053YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.6076NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2366YesYes
Kimi-K2-Instruct
$0.57$2.30131,0721.4320YesNo
tiny-aya-water
---0.18122NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.6061NoYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0721.0049YesNo
GLM-4.5-Air
---3.1316YesNo
tiny-aya-fire
---0.58114NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9528NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.4067YesNo
GLM-4.7-FP8
---1.9567NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.9211NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6923NoNo
MiniMax-M2.1
$0.30$1.20204,8001.3568YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.85166YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0721.15135NoNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.6718YesYes
MiniMax-M2
$0.30$1.20204,8000.7961YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7687NoYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.7338NoYes
Kimi-K2-Thinking
$0.60$2.50262,1441.0935YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8243YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9424NoYes
Qwen3-30B-A3B
$0.09$0.4540,9600.7256YesNo
GLM-4.5V-FP8
---2.5823NoNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2556NoYes
GLM-4.6V
---3.2141YesNo
Qwen3-235B-A22B
$0.20$0.8040,9600.5313NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0423YesYes
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.5412YesNo
GLM-4.5V
zai-org
fastest
---3.0818YesNo
rnj-1-instruct
$0.15$0.1532,7680.21111YesYes
GLM-4.6V-FP8
---2.9236NoNo
aya-vision-32b
---0.2337NoNo
command-a-reasoning-08-2025
---0.4049YesNo
c4ai-command-r7b-arabic-02-2025
---0.26112YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1314NoNo
tiny-aya-global
---0.17123NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.2550NoNo
cogito-671b-v2.1
-------
GLM-4.6-FP8
---3.4615YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2450NoNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest fastest
$0.09$0.58131,0721.1547YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.1223YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.7033YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2682YesYes
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0721.0642YesNo
GLM-4.5
---2.8939YesNo
c4ai-command-a-03-2025
---0.2563YesNo
command-a-vision-07-2025
---0.1746NoNo
Gemma-4-31B-it-pearl
$0.28$0.8632,0000.2754YesNo
c4ai-command-r7b-12-2024
---0.4185YesNo
c4ai-command-r-08-2024
---0.2154YesNo
aya-expanse-32b
---0.3539NoNo
command-a-translate-08-2025
---0.4064YesNo
DeepSeek-R1-0528
$0.70$2.50163,8402.4321YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2421YesYes
DeepSeek-V3.1
$0.27$1.00131,0721.6019YesYes
DeepSeek-V3.1
-------
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7737YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3041NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.8919NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.2049YesNo
GLM-4.6
$0.55$2.20204,8001.6127YesNo
GLM-4.6
-------
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.0514NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.0940NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.7910NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1923.0125NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6235NoNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.36112NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5221NoYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3648NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.0217NoNo
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3581YesYes
Llama-3.1-70B-Instruct
---0.4382YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.4660YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.1548YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2351NoYes
Qwen3-14B
$0.07$0.2040,9600.9651YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.9825NoYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.9060NoYes
Arch-Router-1.5B
---0.1870NoYes
MiMo-V2-Flash
$0.10$0.30262,1442.9578NoNo
DeepSeek-V3.2
$0.27$0.40163,8401.5624YesYes
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0720.93103YesNo