Easy Benchmarks
Workspace
Overview
Benchmarks
Benchmarks list
Compare
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
LLMs
Audio
Image
Video
Log inSign up
Back

Output Price

Output token price per 1M tokens.

Output Price measures the listed cost of generated text. Output tokens are often priced higher than input tokens, so this metric can dominate workloads with long answers or generated artifacts.

Test type: Provider output-token price comparison. Lower values rank better.

Coverage

379 models have this metric.

$0.090/M

Current leader: Llama 3.1 Instruct 8B

Project links

Prices come from the current Artificial Analysis pricing dataset, read from Supabase when configured.

Artificial Analysis model leaderboardArtificial Analysis methodology

Top Output $ Models

Top models ranked by Output $.

Leaderboard

RankModelCreatorValueSpeedBlended Price
#1Llama 3.1 Instruct 8BMeta$0.090/Mn/a$0.079/M
#2
Gemma 4 E4B (Non-reasoning)
Google
$0.100/M
101.1 tok/s
$0.040/M
#3Gemma 4 E4B (Reasoning)Google$0.100/M101.2 tok/s$0.040/M
#4Granite 4.1 8BIBM$0.100/M121.4 tok/s$0.063/M
#5Ministral 3 3BMistral$0.100/M282.2 tok/s$0.100/M
#6Sarvam 30B (high)Sarvam$0.110/Mn/a$0.047/M
#7Gemma 3n E4B InstructGoogle$0.120/Mn/a$0.075/M
#8MCHyperNova 60B 2605Multiverse Computing$0.140/M415 tok/s$0.065/M
#9Nova MicroAmazon$0.140/M263.1 tok/s$0.061/M
#10Llama 3 Instruct 8BMeta$0.145/Mn/a$0.070/M
#11Ministral 3 8BMistral$0.150/M108 tok/s$0.150/M
#12Qwen3.5 4B (Non-reasoning)Alibaba$0.150/M19.4 tok/s$0.060/M
#13Qwen3.5 4B (Reasoning)Alibaba$0.150/M26.3 tok/s$0.060/M
#14Solar MiniUpstage$0.150/Mn/a$0.150/M
#15NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA$0.160/M236.2 tok/s$0.070/M
#16Sarvam 105B (high)Sarvam$0.170/Mn/a$0.074/M
#17NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA$0.195/M176.5 tok/s$0.086/M
#18Apertus 8B InstructSwiss AI Initiative$0.200/Mn/a$0.125/M
#19gpt-oss-20b (high)OpenAI$0.200/M187.9 tok/s$0.103/M
#20Ministral 3 14BMistral$0.200/M94.9 tok/s$0.200/M
#21NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA$0.200/M234.5 tok/s$0.088/M
#22NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA$0.200/M289 tok/s$0.088/M
#23Olmo 3 7B InstructAllen Institute for AI$0.200/Mn/a$0.125/M
#24Qwen2.5 TurboAlibaba$0.200/Mn/a$0.088/M
#25Qwen3.5 9B (Reasoning)Alibaba$0.200/M58.1 tok/s$0.151/M
#26gpt-oss-20b (low)OpenAI$0.225/M192 tok/s$0.109/M
#27TEHy3-preview (Non-reasoning)Tencent$0.235/Mn/a$0.107/M
#28TEHy3-preview (Reasoning)Tencent$0.235/Mn/a$0.107/M
#29Nova LiteAmazon$0.240/Mn/a$0.105/M
#30Granite 3.3 8B (Non-reasoning)IBM$0.250/Mn/a$0.085/M
#31Granite 4.0 H SmallIBM$0.250/M55.3 tok/s$0.107/M
#32Llama 2 Chat 7BMeta$0.250/Mn/a$0.100/M
#33Mistral 7B InstructMistral$0.250/Mn/a$0.250/M
#34DeepSeek V4 Flash (Non-reasoning)DeepSeek$0.280/M101.9 tok/s$0.175/M
#35DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek$0.280/Mn/a$0.175/M
#36DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek$0.280/M100.4 tok/s$0.175/M
#37DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek$0.280/Mn/a$0.175/M
#38MiMo-V2.5Xiaomi$0.280/M67.1 tok/s$0.175/M
#39Gemma 4 12B (Non-reasoning)Google$0.300/M111 tok/s$0.150/M
#40Gemma 4 12B (Reasoning)Google$0.300/M122.2 tok/s$0.150/M
#41Ling 2.6 FlashInclusionAI$0.300/M84.9 tok/s$0.150/M
#42MiMo-V2-Flash (Reasoning)Xiaomi$0.300/Mn/a$0.150/M
#43Mistral Small 3Mistral$0.300/Mn/a$0.150/M
#44Mistral Small 3.1Mistral$0.300/Mn/a$0.150/M
#45Mistral Small 3.2Mistral$0.300/Mn/a$0.150/M
#46Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA$0.300/M319.3 tok/s$0.131/M
#47Step 3.5 FlashStepFun$0.300/Mn/a$0.150/M
#48Step 3.5 Flash 2603StepFun$0.300/Mn/a$0.150/M
#49Llama 3.2 Instruct 11B (Vision)Meta$0.345/M6.1 tok/s$0.345/M
#50Gemini 2.5 Flash-Lite (Non-reasoning)Google$0.400/Mn/a$0.175/M
#51Gemini 2.5 Flash-Lite (Reasoning)Google$0.400/Mn/a$0.175/M
#52Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google$0.400/Mn/a$0.175/M
#53Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google$0.400/Mn/a$0.175/M
#54Gemma 4 26B A4B (Non-reasoning)Google$0.400/M61.9 tok/s$0.198/M
#55Gemma 4 26B A4B (Reasoning)Google$0.400/Mn/a$0.198/M
#56Gemma 4 31B (Non-reasoning)Google$0.400/M75.4 tok/s$0.205/M
#57GLM-4.7-Flash (Non-reasoning)Z AI$0.400/Mn/a$0.153/M
#58GLM-4.7-Flash (Reasoning)Z AI$0.400/Mn/a$0.153/M
#59GPT-4.1 nanoOpenAI$0.400/Mn/a$0.175/M
#60GPT-5 nano (high)OpenAI$0.400/Mn/a$0.138/M
#61GPT-5 nano (medium)OpenAI$0.400/Mn/a$0.138/M
#62GPT-5 nano (minimal)OpenAI$0.400/Mn/a$0.138/M
#63Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research$0.400/M85.5 tok/s$0.198/M
#64Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research$0.400/M95.7 tok/s$0.198/M
#65Jamba 1.5 MiniAI21 Labs$0.400/Mn/a$0.250/M
#66Jamba 1.6 MiniAI21 Labs$0.400/Mn/a$0.250/M
#67Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA$0.400/M77 tok/s$0.400/M
#68Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA$0.400/M93.3 tok/s$0.400/M
#69DeepSeek V3.2 (Non-reasoning)DeepSeek$0.420/Mn/a$0.315/M
#70DeepSeek V3.2 (Reasoning)DeepSeek$0.420/Mn/a$0.315/M
#71DeepSeek V3.2 Exp (Non-reasoning)DeepSeek$0.420/Mn/a$0.315/M
#72DeepSeek V3.2 Exp (Reasoning)DeepSeek$0.420/Mn/a$0.315/M
#73Qwen2.5 Instruct 72BAlibaba$0.495/Mn/a$0.480/M
#74Grok 3 mini Reasoning (high)SpaceXAI$0.500/Mn/a$0.350/M
#75Grok 4 Fast (Non-reasoning)SpaceXAI$0.500/Mn/a$0.275/M
#76Grok 4 Fast (Reasoning)SpaceXAI$0.500/Mn/a$0.275/M
#77Phi-4Microsoft$0.500/M41.9 tok/s$0.219/M
#78TEHy3Tencent$0.557/M70.7 tok/s$0.241/M
#79Llama 3.1 Instruct 70BMeta$0.560/Mn/a$0.560/M
#80Ling-flash-2.0InclusionAI$0.570/Mn/a$0.247/M