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

371 models have this metric.

$0.040/M

Current leader: Gemma 3n E4B Instruct

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
#1Gemma 3n E4B InstructGoogle$0.040/M49.7 tok/s$0.025/M
#2
Ministral 3 3B
Mistral
$0.100/M
158.5 tok/s
$0.100/M
#3Granite 4.1 8BIBM$0.100/M117.8 tok/s$0.063/M
#4Llama 3.1 Instruct 8BMeta$0.100/M155.5 tok/s$0.100/M
#5Llama 3.2 Instruct 1BMeta$0.100/M86.4 tok/s$0.100/M
#6Sarvam 30B (high)Sarvam$0.110/M200.7 tok/s$0.047/M
#7Nova MicroAmazon$0.140/M249.8 tok/s$0.061/M
#8MCHyperNova 60B 2605Multiverse Computing$0.140/M350.9 tok/s$0.065/M
#9Llama 3 Instruct 8BMeta$0.145/M79.8 tok/s$0.070/M
#10Ministral 3 8BMistral$0.150/M89 tok/s$0.150/M
#11Qwen3.5 4B (Non-reasoning)Alibaba$0.150/M23 tok/s$0.060/M
#12Qwen3.5 9B (Reasoning)Alibaba$0.150/M67.6 tok/s$0.113/M
#13Qwen3.5 4B (Reasoning)Alibaba$0.150/M22.8 tok/s$0.060/M
#14Llama 3.2 Instruct 3BMeta$0.150/M51.7 tok/s$0.150/M
#15Solar MiniUpstage$0.150/M78.2 tok/s$0.150/M
#16NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA$0.160/M85.9 tok/s$0.070/M
#17Sarvam 105B (high)Sarvam$0.170/M115.9 tok/s$0.074/M
#18NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA$0.195/M138.9 tok/s$0.086/M
#19gpt-oss-20b (low)OpenAI$0.200/M260.9 tok/s$0.095/M
#20gpt-oss-20b (high)OpenAI$0.200/M224.5 tok/s$0.088/M
#21Ministral 3 14BMistral$0.200/M75.5 tok/s$0.200/M
#22NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA$0.200/M99.8 tok/s$0.088/M
#23NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA$0.200/M111.7 tok/s$0.088/M
#24Olmo 3 7B InstructAllen Institute for AI$0.200/Mn/a$0.125/M
#25Apertus 8B InstructSwiss AI Initiative$0.200/Mn/a$0.125/M
#26Qwen2.5 TurboAlibaba$0.200/M113.6 tok/s$0.088/M
#27Nova LiteAmazon$0.240/M147.8 tok/s$0.105/M
#28Granite 4.0 H SmallIBM$0.250/M439.5 tok/s$0.107/M
#29Llama 2 Chat 7BMeta$0.250/M95.6 tok/s$0.100/M
#30Mistral 7B InstructMistral$0.250/M91.5 tok/s$0.250/M
#31Granite 3.3 8B (Non-reasoning)IBM$0.250/M414.9 tok/s$0.085/M
#32DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek$0.280/M101.1 tok/s$0.175/M
#33DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek$0.280/Mn/a$0.175/M
#34DeepSeek V4 Flash (Non-reasoning)DeepSeek$0.280/M90.1 tok/s$0.175/M
#35MiMo-V2.5Xiaomi$0.280/M75.5 tok/s$0.175/M
#36Gemma 4 12B (Non-reasoning)Google$0.300/M121.2 tok/s$0.150/M
#37Gemma 4 12B (Reasoning)Google$0.300/M125.3 tok/s$0.150/M
#38Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA$0.300/M320 tok/s$0.131/M
#39Step 3.5 Flash 2603StepFun$0.300/M256.9 tok/s$0.150/M
#40Ling 2.6 FlashInclusionAI$0.300/M172.8 tok/s$0.150/M
#41Mistral Small 3Mistral$0.300/M145.3 tok/s$0.150/M
#42Mistral Small 3.1Mistral$0.300/M144.9 tok/s$0.150/M
#43Mistral Small 3.2Mistral$0.300/M144.9 tok/s$0.150/M
#44Devstral Small (Jul '25)Mistral$0.300/Mn/a$0.150/M
#45Step 3.5 FlashStepFun$0.300/M247.4 tok/s$0.150/M
#46MiMo-V2-Flash (Reasoning)Xiaomi$0.300/Mn/a$0.150/M
#47Llama 3.2 Instruct 11B (Vision)Meta$0.345/M72.8 tok/s$0.345/M
#48Gemma 4 31B (Non-reasoning)Google$0.400/M43.7 tok/s$0.205/M
#49Gemma 4 26B A4B (Non-reasoning)Google$0.400/M70.8 tok/s$0.198/M
#50Gemma 4 26B A4B (Reasoning)Google$0.400/Mn/a$0.198/M
#51Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA$0.400/M52.2 tok/s$0.400/M
#52Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA$0.400/M51.8 tok/s$0.400/M
#53Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research$0.400/M96.2 tok/s$0.198/M
#54Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research$0.400/M92.1 tok/s$0.198/M
#55GPT-4.1 nanoOpenAI$0.400/M148 tok/s$0.175/M
#56GPT-5 nano (minimal)OpenAI$0.400/M168.7 tok/s$0.138/M
#57GPT-5 nano (medium)OpenAI$0.400/M155.7 tok/s$0.138/M
#58GPT-5 nano (high)OpenAI$0.400/M154.5 tok/s$0.138/M
#59Gemini 2.5 Flash-Lite (Reasoning)Google$0.400/M237.8 tok/s$0.175/M
#60Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google$0.400/Mn/a$0.175/M
#61Gemini 2.5 Flash-Lite (Non-reasoning)Google$0.400/M182.3 tok/s$0.175/M
#62Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google$0.400/Mn/a$0.175/M
#63GLM-4.7-Flash (Reasoning)Z AI$0.400/M83.7 tok/s$0.153/M
#64GLM-4.7-Flash (Non-reasoning)Z AI$0.400/M122.7 tok/s$0.153/M
#65Jamba 1.5 MiniAI21 Labs$0.400/Mn/a$0.250/M
#66Jamba 1.6 MiniAI21 Labs$0.400/M179.6 tok/s$0.250/M
#67DeepSeek V3.2 (Reasoning)DeepSeek$0.420/Mn/a$0.315/M
#68DeepSeek V3.2 (Non-reasoning)DeepSeek$0.420/Mn/a$0.315/M
#69DeepSeek V3.2 Exp (Non-reasoning)DeepSeek$0.420/Mn/a$0.315/M
#70DeepSeek V3.2 Exp (Reasoning)DeepSeek$0.420/Mn/a$0.315/M
#71TEHy3-preview (Reasoning)Tencent$0.430/M124.1 tok/s$0.200/M
#72TEHy3-preview (Non-reasoning)Tencent$0.430/M121.5 tok/s$0.200/M
#73Qwen2.5 Instruct 72BAlibaba$0.495/Mn/a$0.480/M
#74Phi-4Microsoft$0.500/M27 tok/s$0.219/M
#75Grok 3 mini Reasoning (high)SpaceXAI$0.500/M45.7 tok/s$0.350/M
#76Grok 4 Fast (Reasoning)SpaceXAI$0.500/Mn/a$0.275/M
#77Grok 4 Fast (Non-reasoning)SpaceXAI$0.500/Mn/a$0.275/M
#78Llama 3.1 Instruct 70BMeta$0.560/M33.8 tok/s$0.560/M
#79Ring-flash-2.0InclusionAI$0.570/Mn/a$0.247/M
#80Ling-flash-2.0InclusionAI$0.570/M61.8 tok/s$0.247/M