Providers/DeepInfra
DeepInfra logo

DeepInfra

Inference providerdeepinfra.comStatus ↗
MODELS
72
ENDPOINTS
76
MIN INPUT
$0.019
MEDIAN BLENDED
$0.37
AVG UPTIME
98.2%
CHEAPEST FOR
41 models
Models on DeepInfra · prices & measurements for models served by DeepInfra’s APIUSD / MTOK · VERIFIED 4 MINUTES AGO
MODELINPUTOUTPUTCONTEXTQUANTTTFTTPSSMOKEVS BEST ELSEWHERE
Mistral logoMistral NemoMistralBEST PRICE$0.019$0.03131Kfp8cheapest here
Meta logoLlama 3.1 8B InstructMetaBEST PRICE$0.02$0.04131Kfp81.1s°37° tok/s3/5cheapest here
OpenAI logogpt-oss-20bOpenAIBEST PRICE$0.03$0.14131Kbf160.26s°141° tok/s2/5cheapest here
OpenAI logogpt-oss-120bOpenAI$0.037$0.17131Kbf160.55s°54° tok/s4/5$0.03 elsewhere
SALlama 3 8B LunarisSao10KBEST PRICE$0.04$0.058Kfp80.15s°88° tok/scheapest here
NVIDIA logoNemotron 3 Nano 30B A3BNVIDIABEST PRICE$0.05$0.20262Kfp40.83s°441° tok/scheapest here
Google logoGemma 3 4BGoogle$0.05$0.10131Kbf160.62s°72° tok/sonly provider
Google logoGemma 3 12BGoogle$0.05$0.15131Kbf160.64s°42° tok/sonly provider
Mistral logoMistral Small 3Mistral$0.05$0.0833Kfp81.4s°51° tok/sonly provider
INLing-3.0-flashInclusionAI$0.06$0.18131Kbf160.84s°83° tok/s$0.021 elsewhere
Z.ai logoGLM 4.7 FlashZ.aiBEST PRICE$0.06$0.40203Kbf160.55s°98° tok/scheapest here
Google logoGemma 4 26B A4B Google$0.07$0.34262Kfp80.65s°25° tok/s5/5$0.042 elsewhere
MIPhi 4Microsoft$0.07$0.1416Kbf160.71s°84° tok/sonly provider
Mistral logoMistral Small 3.2 24BMistralBEST PRICE$0.075$0.20128Kfp80.9s°59° tok/scheapest here
NVIDIA logoNemotron 3.5 LightningNVIDIABEST PRICE$0.08$0.20262Kbf160.29s°103° tok/scheapest here
DeepSeek logoDeepSeek V4 Flash 0731DeepSeek$0.08$0.181.05Mfp80.56s°86° tok/s$0.04 elsewhere
Qwen logoQwen3 32BQwenBEST PRICE$0.08$0.2841Kfp82.4s°25° tok/scheapest here
Google logoGemma 3 27BGoogleBEST PRICE$0.08$0.16131Kfp85.5s°14° tok/s3/5cheapest here
NVIDIA logoNemotron 3 SuperNVIDIABEST PRICE$0.085$0.40262Kbf162.2s°cheapest here
DeepSeek logoDeepSeek V4 Flash 0423DeepSeek$0.09$0.181.05Mfp81.9s°87° tok/s5/5$0.056 elsewhere
Google logoGemma 4 31BGoogle$0.09$0.34262Kfp40.84s°56° tok/s5/5$0.08 elsewhere
Qwen logoQwen3 Next 80B A3B InstructQwenBEST PRICE$0.09$1.10262Kfp80.58s°104° tok/scheapest here
Qwen logoQwen3 235B A22B Instruct 2507Qwen$0.09$0.55262Kfp80.41s°31° tok/s5/5$0.087 elsewhere
Qwen logoQwen3.6 35B A3BQwen$0.10$0.95262Kfp80.54s°159° tok/s2/5$0.07 elsewhere
Qwen logoQwen3.5-9BQwenBEST PRICE$0.10$0.15262Kbf160.68s°58° tok/scheapest here
Meta logoLlama 4 ScoutMetaBEST PRICE$0.10$0.30328Kfp80.41s°50° tok/scheapest here
Meta logoLlama 3.3 70B InstructMetaBEST PRICE$0.10$0.32131Kfp81.9s°12° tok/s5/5cheapest here
Qwen logoQwen3 30B A3BQwenBEST PRICE$0.12$0.5041Kfp80.53s°216° tok/scheapest here
Qwen logoQwen3 14BQwen$0.12$0.2441Kfp80.82s°70° tok/s$0.10 elsewhere
TEHy3Tencent$0.14$0.58262Kfp80.8s°158° tok/s2/5$0.126 elsewhere
Qwen logoQwen3.5-35B-A3BQwenBEST PRICE$0.14$1.00262Kfp80.4s°184° tok/s3/5cheapest here
Qwen logoQwen3 VL 30B A3B InstructQwen$0.15$0.60262Kfp80.61s°45° tok/s$0.13 elsewhere
Meta logoLlama Guard 4 12BMetaBEST PRICE$0.18$0.18164Kbf161.4s°32° tok/scheapest here
STStep 3.7 FlashStepFunBEST PRICE$0.20$1.15262K0.55s°148° tok/scheapest here
Qwen logoQwen3 VL 235B A22B InstructQwenBEST PRICE$0.20$0.88262Kfp80.66s°21° tok/scheapest here
Meta logoLlama 4 MaverickMetaBEST PRICE$0.20$0.801.05Mfp80.37s°95° tok/s4/5cheapest here
DeepSeek logoDeepSeek V3 0324DeepSeekBEST PRICE$0.24$0.90164Kfp40.85s°32° tok/scheapest here
MiniMax logoMiniMax M2.7MiniMax$0.25$1.00197Kfp825.6s°17° tok/s2/5$0.24 elsewhere
DeepSeek logoDeepSeek V3.1DeepSeekBEST PRICE$0.25$0.95164Kfp41.5s°9° tok/s5/5cheapest here
Qwen logoQwen3.5-27BQwen$0.26$2.60262Kfp80.8s°81° tok/s3/5$0.195 elsewhere
DeepSeek logoDeepSeek V3.2DeepSeek$0.26$0.38164Kfp41.1s°10° tok/s5/5$0.209 elsewhere
MiniMax logoMiniMax M3MiniMax$0.28$1.10524Kfp80.48s°19° tok/s5/5$0.23 elsewhere
Qwen logoQwen3.5-122B-A10BQwen$0.29$2.40262Kfp40.75s°123° tok/s3/5$0.26 elsewhere
Meta logoMuse Glimmer 30BMetaBEST PRICE$0.30$1.20131Kbf160.86s°177° tok/scheapest here
Qwen logoQwen3 Coder 480B A35BQwen$0.30$1.00262Kfp40.41s°145° tok/s$0.22 elsewhere
Qwen logoQwen3.6 27BQwen$0.32$3.20262Kfp80.96s°41° tok/s2/5$0.30 elsewhere
DeepSeek logoDeepSeek V3DeepSeek$0.32$0.89164Kfp40.4s°126° tok/s$0.257 elsewhere
Qwen logoQwen2.5 72B InstructQwenBEST PRICE$0.36$0.4033Kfp81.2s°47° tok/scheapest here
XIMiMo-V2.5Xiaomi$0.40$2.00262Kbf160.71s°39° tok/s$0.119 elsewhere
Z.ai logoGLM 4.7Z.aiBEST PRICE$0.40$1.75203Kfp40.84s°29° tok/s2/5cheapest here
Meta logoLlama 3.1 70B InstructMetaBEST PRICE$0.40$0.40131Kfp80.95s°52° tok/scheapest here
GRMythoMax 13BGryphe$0.40$0.404Kfp160.28s°53° tok/s$0.06 elsewhere
TMInkling SmallThinking MachinesBEST PRICE$0.45$1.20524Kfp80.59s°301° tok/scheapest here
Qwen logoQwen3.5 397B A17BQwen$0.45$3.00262Kfp81.3s°25° tok/s3/5$0.39 elsewhere
Moonshot AI logoKimi K2.5Moonshot AIBEST PRICE$0.45$2.25262Kfp40.73s°43° tok/s3/5cheapest here
NVIDIA logoNemotron 3 UltraNVIDIABEST PRICE$0.50$2.20262Kfp43.4s°cheapest here
Z.ai logoGLM 4.6Z.ai$0.50$2.00203Kfp40.67s°78° tok/s3/5$0.43 elsewhere
DeepSeek logoR1 0528DeepSeekBEST PRICE$0.50$2.15164Kfp40.68s°20° tok/scheapest here
Z.ai logoGLM 5Z.aiBEST PRICE$0.60$2.08203Kfp40.55s°90° tok/s2/5cheapest here
Moonshot AI logoKimi K2.7 CodeMoonshot AI$0.68$3.40262Kfp40.4s°58° tok/s5/5$0.67 elsewhere
NRHermes 3 70B InstructNous Research$0.70$0.70131Kfp82.2s°39° tok/sonly provider
Z.ai logoGLM 5.2Z.ai$0.75$2.401.05Mfp40.94s°74° tok/s$0.50 elsewhere
Moonshot AI logoKimi K2.6Moonshot AI$0.75$3.50262Kfp41.1s°32° tok/s$0.58 elsewhere
SALlama 3.1 Euryale 70B v2.2Sao10KBEST PRICE$0.85$0.85131Kfp80.91s°47° tok/scheapest here
TMInklingThinking MachinesBEST PRICE$0.95$4.05524Kfp80.46s°199° tok/scheapest here
XIMiMo-V2.5-ProXiaomi$1.00$3.001.05Mfp80.58s°80° tok/s$0.304 elsewhere
NRHermes 3 405B InstructNous Research$1.00$1.00131Kfp82.3s°16° tok/sonly provider
Z.ai logoGLM 5.1Z.ai$1.05$3.50203Kfp41s°13° tok/s2/5$0.91 elsewhere
DeepSeek logoDeepSeek V4 Pro 0813DeepSeek$1.30$2.601.05Mfp8$0.66 elsewhere
DeepSeek logoDeepSeek V4 Pro 0423DeepSeek$1.30$2.601.05Mfp81.3s°57° tok/s$0.522 elsewhere
Qwen logoQwen3.8 2.4T A95BQwenBEST PRICE$2.00$6.00262Kfp41.3s°76° tok/s4/5cheapest here
Moonshot AI logoKimi K3Moonshot AI$2.85$14.251.05Mbf162s°25° tok/s4/5$2.60 elsewhere
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) for DeepInfra’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page