Inference Providers

·

Metrics for top trending models

MiniMax-M2.7
-------
MiniMax-M2.7
together
cheapest
$0.30$1.20196,6080.2757YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.25202YesNo
GLM-5.1
together
cheapest fastest
$1.40$4.40202,7520.5949YesYes
GLM-5.1
--202,7521.0240YesNo
GLM-5.1
---3.8532NoNo
gemma-4-31B-it
-------
gemma-4-31B-it
$0.20$0.50262,1440.5056YesYes
Qwen3.5-9B
$0.10$0.15262,1440.6855YesNo
GLM-5.1-FP8
--202,7521.1031YesNo
GLM-5.1-FP8
-------
MiniMax-M2.5
-------
MiniMax-M2.5
---0.55124YesNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.241,381NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
nscale
cheapest
$0.06$0.06131,0720.6960NoYes
Llama-3.1-8B-Instruct
---0.33147YesYes
gpt-oss-120b
$0.15$0.75131,0720.13448YesNo
gpt-oss-120b
-------
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.27561YesNo
gpt-oss-120b
$0.22$0.59131,0721.27467YesYes
gpt-oss-120b
nscale
cheapest
$0.10$0.40131,0720.82115YesYes
gpt-oss-120b
$0.15$0.60131,0720.34105YesYes
gpt-oss-120b
$0.15$0.60131,0721.09104YesNo
gpt-oss-120b
---0.29174YesYes
gpt-oss-120b
$0.09$0.47131,0720.28107YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.7798NoNo
DeepSeek-R1
together
fastest
$3.00$7.00163,8400.42103NoNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.12846YesNo
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.20131,0721.31145YesYes
gpt-oss-20b
$0.05$0.20131,0720.24161YesYes
gpt-oss-20b
$0.05$0.20131,0720.40158YesNo
gpt-oss-20b
ovhcloud
cheapest
$0.05$0.18131,0720.31105YesYes
Kimi-K2.5
-------
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.5466YesYes
Kimi-K2.5
--262,1441.1937YesNo
DeepSeek-V3.2
-------
DeepSeek-V3.2
--163,8401.5045YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.20120YesYes
Qwen3.5-397B-A17B
-------
Qwen3.5-397B-A17B
together
cheapest
$0.60$3.60262,1440.5571YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.4796YesYes
GLM-5
-------
GLM-5
together
cheapest
$1.00$3.20202,7520.8146YesYes
GLM-5
fireworks-ai
fastest
--202,7521.1256YesNo
GLM-5
-------
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.7959YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.38145YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7786YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.31316YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.60$1.20131,0721.01247YesYes
Llama-3.3-70B-Instruct
nscale
cheapest
$0.40$0.40131,0720.8416NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8989NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.6988YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.50139NoNo
Llama-3.3-70B-Instruct
---0.4084YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4230YesYes
DeepSeek-V3
-------
DeepSeek-V3
$1.25$1.25131,0720.5048YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.3391YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4575YesYes
QwQ-32B
$0.18$0.20131,0720.7927YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7862NoYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.34106YesYes
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.8317NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4438NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.75143NoNo
gemma-3-27b-it
---0.4248YesYes
gemma-3n-E4B-it
$0.02$0.0432,7680.2614NoYes
GLM-4.5-Air
-------
GLM-4.5-Air
---1.5794YesNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8466NoNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0720.51197YesYes
DeepSeek-V3-0324
hyperbolic
cheapest
$1.25$1.25163,8400.7559NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.5136YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.20357YesNo
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8333YesYes
Kimi-K2-Thinking
-------
Kimi-K2-Thinking
---1.9730YesNo
MiniMax-M2.1
-------
MiniMax-M2.1
--204,8000.64150YesNo
gpt-oss-safeguard-20b
--131,0720.12854YesNo
GLM-4.7
-------
GLM-4.7
cerebras
fastest
---0.23407YesNo
GLM-4.7
--202,7521.02143YesNo
GLM-4.7
---2.6634YesNo
GLM-4.6
-------
GLM-4.6
---2.9826YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.15250YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.8028YesYes
Qwen3-32B
$0.09$0.2532,7680.2836YesYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8028NoYes
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
hyperbolic
cheapest
$3.00$3.00163,8400.7757NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.5294NoYes
Qwen3-VL-30B-A3B-Instruct
-------
Qwen3-VL-30B-A3B-Instruct
--262,1440.22104YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8295YesNo
tiny-aya-global
---0.30112NoNo
GLM-4.5
-------
GLM-4.5
---2.5149YesNo
c4ai-command-r7b-12-2024
---0.2288YesNo
GLM-4.6V
---3.5026YesNo
GLM-4.7-FP8
---2.7128NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7757NoYes
command-a-reasoning-08-2025
---0.3281YesNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.8625NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2367NoNo
command-a-translate-08-2025
---0.3465YesNo
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.22580YesNo
Qwen3-235B-A22B-Instruct-2507
nscale
cheapest
$0.20$0.6032,7681.0424YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.5037YesYes
Qwen3-235B-A22B-Instruct-2507
---0.38102YesYes
Qwen3-VL-30B-A3B-Thinking
-------
Qwen3-VL-30B-A3B-Thinking
--262,1440.23131YesNo
Arch-Router-1.5B
---0.1179NoYes
command-a-vision-07-2025
---0.2044NoNo
c4ai-command-r7b-arabic-02-2025
---0.1972YesNo
aya-expanse-32b
---0.1842NoNo
c4ai-command-r-08-2024
---2.4624YesNo
GLM-4.5V
-------
GLM-4.5V
---2.4035YesNo
GLM-4.6-FP8
---2.3226YesNo
GLM-4.5V-FP8
---2.5536YesNo
GLM-4.6V-FP8
---4.4121NoNo
Qwen3-235B-A22B
-------
Qwen3-235B-A22B
$0.20$0.6032,0001.3617YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.6447NoYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0720.97383YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.2538NoYes
Qwen3-14B
$0.07$0.2040,9600.8650YesNo
Llama-3.1-70B-Instruct
---0.2986YesYes
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.10199YesNo
Kimi-K2-Instruct-0905
-------
Kimi-K2-Instruct-0905
--262,1440.5940YesNo
rnj-1-instruct
$0.15$0.1532,7680.16123YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2053NoNo
cogito-671b-v2.1
-------
tiny-aya-water
---0.22121NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1414NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.9859NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.2329NoYes
aya-vision-32b
---0.3437NoNo
c4ai-command-a-03-2025
---0.8429YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0721.0027NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3096YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.8082NoYes
Qwen3-Coder-480B-A35B-Instruct
-------
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
cheapest fastest
$2.00$2.00262,1440.4776NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2255YesYes
tiny-aya-earth
---0.26121NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.5063YesYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2056YesYes
DeepSeek-V3.1
-------
DeepSeek-V3.1
together
cheapest fastest
$0.60$1.70131,0720.5237YesYes
DeepSeek-V3.1
--163,8400.5032NoNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3644YesYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.1855NoNo
tiny-aya-fire
---0.19122NoNo