Providers/DeepInfra
DeepInfra logo

DeepInfra

Inference providerdeepinfra.com ↗Status ↗
MODELS
72
ENDPOINTS
74
MIN INPUT
$0.019
MEDIAN BLENDED
$0.262
AVG UPTIME
97.7%
CHEAPEST FOR
36 models
Models on DeepInfra · prices & measurements for models served by DeepInfra’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
MODELINPUTOUTPUTCONTEXTQUANTTTFTTPSSMOKEVS BEST ELSEWHERE
Mistral logoMistral NemoMistral$0.019$0.03131Kfp80.76s°33° tok/s—$0.018 elsewhere
Meta logoLlama 3.1 8B InstructMetaBEST PRICE$0.02$0.04131Kfp8✕✕3/5cheapest here
OpenAI logogpt-oss-20bOpenAI$0.03$0.14131Kbf160.28s°100° tok/s2/5$0.018 elsewhere
OpenAI logogpt-oss-120bOpenAI$0.037$0.17131Kbf160.46s°48° tok/s4/5$0.03 elsewhere
Sao10K logoLlama 3 8B LunarisSao10KBEST PRICE$0.04$0.058Kfp80.28s°99° tok/s—cheapest here
NVIDIA logoNemotron 3 Nano 30B A3BNVIDIABEST PRICE$0.05$0.20262Kfp41.2s°114° tok/s—cheapest here
Google logoGemma 3 4BGoogle$0.05$0.10131Kbf16✕✕—only provider
Google logoGemma 3 12BGoogleBEST PRICE$0.05$0.15131Kbf160.93s°39° tok/s—cheapest here
Mistral logoMistral Small 3Mistral$0.05$0.0833Kfp80.88s°60° tok/s—only provider
InclusionAI logoLing 3.0 Flash VLInclusionAI$0.06$0.18131Kfp16✕✕—$0.021 elsewhere
IBM Granite logoGranite 4.2 8BIBM GraniteBEST PRICE$0.06$0.25131Kbf161.6s°79° tok/s—cheapest here
InclusionAI logoLing 3.0 Flash FinInclusionAI$0.06$0.18262Kfp40.43s°189° tok/s—$0.042 elsewhere
NVIDIA logoNemotron 3.5 LightningNVIDIA$0.06$0.16262Kbf160.32s°455° tok/s—$0.039 elsewhere
DeepSeek logoDeepSeek V4 Flash 0731DeepSeek$0.06$0.181.05Mfp80.91s°47° tok/s—$0.01 elsewhere
InclusionAI logoLing 3.0 FlashInclusionAI$0.06$0.18131Kbf16✕✕—$0.021 elsewhere
Google logoGemma 4 26B A4B Google$0.07$0.34262Kfp80.68s°30° tok/s5/5$0.042 elsewhere
Microsoft logoPhi 4Microsoft$0.07$0.1416Kbf161.1s°75° tok/s—only provider
Z.ai logoGLM 5.3 FlashZ.ai$0.075$0.251.05Mfp4✕✕—$0.032 elsewhere
Mistral logoMistral Small 3.2 24BMistralBEST PRICE$0.075$0.20128Kfp8✕✕—cheapest here
Qwen logoQwen3 32BQwenBEST PRICE$0.08$0.2841Kfp81.5s°27° tok/s—cheapest here
Google logoGemma 3 27BGoogleBEST PRICE$0.08$0.16131Kfp8✕✕3/5cheapest here
NVIDIA logoNemotron 3 SuperNVIDIA$0.085$0.40262Kbf16✕✕—$0.08 elsewhere
DeepSeek logoDeepSeek V4 Flash 0423DeepSeek$0.09$0.181.05Mfp8✕✕5/5$0.017 elsewhere
Google logoGemma 4 31BGoogleBEST PRICE$0.09$0.34262Kfp4✕✕5/5cheapest here
Qwen logoQwen3 Next 80B A3B InstructQwenBEST PRICE$0.09$1.10262Kfp80.5s°31° tok/s—cheapest here
Qwen logoQwen3 235B A22B Instruct 2507Qwen$0.09$0.55262Kfp80.5s°30° tok/s5/5$0.087 elsewhere
Qwen logoQwen3.6 35B A3BQwen$0.10$0.95262Kfp80.62s°43° tok/s2/5$0.05 elsewhere
Qwen logoQwen3.5-9BQwen$0.10$0.15262Kbf160.77s°48° tok/s—$0.08 elsewhere
Meta logoLlama 4 ScoutMetaBEST PRICE$0.10$0.30328Kfp80.43s°62° tok/s—cheapest here
Meta logoLlama 3.3 70B InstructMetaBEST PRICE$0.10$0.32131Kfp81.7s°39° tok/s5/5cheapest here
Qwen logoQwen3 30B A3BQwenBEST PRICE$0.12$0.5041Kfp80.42s°52° tok/s—cheapest here
Qwen logoQwen3 14BQwen$0.12$0.2441Kfp80.86s°57° tok/s—$0.10 elsewhere
Tencent logoHy3TencentBEST PRICE$0.13$0.53262Kfp40.73s°178° tok/s2/5cheapest here
Xiaomi logoMiMo-V2.6-FlashXiaomi$0.14$0.281.05Mfp8✕✕—$0.10 elsewhere
DeepSeek logoDeepSeek V4.1 FlashDeepSeek$0.14$0.421.05Mfp80.36s°145° tok/s—$0.018 elsewhere
Qwen logoQwen3.5-35B-A3BQwen$0.14$1.00262Kfp81.8s°104° tok/s3/5$0.08 elsewhere
Qwen logoQwen3.8 27BQwen$0.15$1.88262Kbf161.3s°35° tok/s—$0.024 elsewhere
Qwen logoQwen3 VL 30B A3B InstructQwen$0.15$0.60262Kfp80.51s°36° tok/s—$0.13 elsewhere
Meta logoLlama Guard 4 12BMeta$0.18$0.18164Kbf16✕✕—only provider
NVIDIA logoNemotron 3.5 Content SafetyNVIDIA$0.20$0.20131Kbf16✕✕—only provider
Qwen logoQwen3 VL 235B A22B InstructQwenBEST PRICE$0.20$0.88262Kfp8✕✕—cheapest here
DeepSeek logoDeepSeek V4 Flash Vision ExpDeepSeekBEST PRICE$0.216$0.6471.05Mfp80.51s°190° tok/s—cheapest here
DeepSeek logoDeepSeek V3.1DeepSeekBEST PRICE$0.25$0.95164Kfp4✕✕5/5cheapest here
Qwen logoQwen3.5-27BQwen$0.26$2.60262Kfp8✕✕3/5$0.195 elsewhere
DeepSeek logoDeepSeek V3.2DeepSeek$0.26$0.38164Kfp41.1s°13° tok/s5/5$0.209 elsewhere
MiniMax logoMiniMax M3MiniMax$0.28$1.10524Kfp8✕✕5/5$0.23 elsewhere
Meta logoMuse Glimmer 30BMetaBEST PRICE$0.30$1.20131Kbf160.94s°85° tok/s—cheapest here
Qwen logoQwen3 Coder 480B A35BQwen$0.30$1.00262Kfp4✕✕—$0.22 elsewhere
Qwen logoQwen3.6 27BQwen$0.32$3.20262Kfp8✕✕2/5$0.30 elsewhere
DeepSeek logoDeepSeek V3DeepSeek$0.32$0.89164Kfp40.73s°18° tok/s—$0.257 elsewhere
Qwen logoQwen2.5 72B InstructQwenBEST PRICE$0.36$0.4033Kfp82.2s°30° tok/s—cheapest here
Z.ai logoGLM 4.7Z.aiBEST PRICE$0.40$1.75203Kfp4✕✕2/5cheapest here
Meta logoLlama 3.1 70B InstructMetaBEST PRICE$0.40$0.40131Kfp81.5s°41° tok/s—cheapest here
Gryphe logoMythoMax 13BGryphe$0.40$0.404Kfp160.28s°53° tok/s—$0.08 elsewhere
Xiaomi logoMiMo-V2.6-ProXiaomiBEST PRICE$0.43$0.871.05Mfp8✕✕—cheapest here
Thinking Machines logoInkling SmallThinking Machines$0.45$1.20524Kfp8✕✕—only provider
Qwen logoQwen3.5 397B A17BQwen$0.45$3.00262Kfp8✕✕3/5$0.39 elsewhere
NVIDIA logoNemotron 3 UltraNVIDIABEST PRICE$0.50$2.20262Kfp41s°267° tok/s—cheapest here
Z.ai logoGLM 4.6Z.ai$0.50$2.00203Kfp4✕✕3/5$0.43 elsewhere
DeepSeek logoR1 0528DeepSeekBEST PRICE$0.50$2.15164Kfp40.56s°41° tok/s—cheapest here
Z.ai logoGLM 5.3Z.ai$0.563$2.501.05Mfp40.92s°147° tok/s—$0.039 elsewhere
Z.ai logoGLM 5.2Z.ai$0.563$1.801.05Mfp40.87s°92° tok/s—$0.03 elsewhere
Nous Research logoHermes 3 70B InstructNous Research$0.70$0.70131Kfp8✕✕—only provider
Moonshot AI logoKimi K2.6Moonshot AI$0.75$3.50262Kfp41.4s°34° tok/s—$0.465 elsewhere
Tencent logoHy4 previewTencentBEST PRICE$0.834$2.501.05Mfp8———cheapest here
Sao10K logoLlama 3.1 Euryale 70B v2.2Sao10KBEST PRICE$0.85$0.85131Kfp81.7s°48° tok/s—cheapest here
Thinking Machines logoInklingThinking MachinesBEST PRICE$0.95$4.05524Kfp80.38s°261° tok/s—cheapest here
Nous Research logoHermes 3 405B InstructNous Research$1.00$1.00131Kfp8✕✕—only provider
DeepSeek logoDeepSeek V4 Pro 0813DeepSeek$1.30$2.601.05Mfp80.94s°54° tok/s—$0.158 elsewhere
DeepSeek logoDeepSeek V4 Pro 0423DeepSeek$1.30$2.601.05Mfp8✕✕—$0.30 elsewhere
Qwen logoQwen3.8 2.4T A95BQwenBEST PRICE$2.00$6.00262Kfp41.3s°87° tok/s4/5cheapest here
Moonshot AI logoKimi K3Moonshot AI$2.85$14.251.05Mmxfp41.3s°74° tok/s4/5$0.68 elsewhere
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for DeepInfra’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page