Easy Benchmarks
Workspace
Overview
Benchmarks
Benchmarks list
Compare
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
LLMs
Audio
Image
Video
Feedback
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

357 models have this metric.

$0.040/M

Current leader: Gemma 3n E4B Instruct

Project links

Prices come from Artificial Analysis pricing data in the committed snapshot.

Artificial Analysis methodology

Top Output $ Models

Top models ranked by Output $.

Leaderboard

RankModelCreatorValueSpeedBlended Price
#1Gemma 3n E4B InstructGoogle$0.040/M50 tok/s$0.025/M
#2
Llama 3.2 Instruct 1B
Meta
$0.050/M
92.9 tok/s
$0.050/M
#3Qwen3.5 0.8B (Non-reasoning)Alibaba$0.050/M88 tok/s$0.020/M
#4Qwen3.5 0.8B (Reasoning)Alibaba$0.050/Mn/a$0.020/M
#5Gemma 3 4B InstructGoogle$0.080/Mn/a$0.050/M
#6Granite 4.1 8BIBM$0.100/M134.2 tok/s$0.063/M
#7Llama 3.1 Instruct 8BMeta$0.100/M201.5 tok/s$0.100/M
#8Ministral 3 3BMistral$0.100/M174.3 tok/s$0.100/M
#9Qwen3.5 2B (Non-reasoning)Alibaba$0.100/M318.9 tok/s$0.040/M
#10Qwen3.5 2B (Reasoning)Alibaba$0.100/Mn/a$0.040/M
#11Sarvam 30B (high)Sarvam$0.110/M147.9 tok/s$0.047/M
#12LFM2 24B A2BLiquid AI$0.120/M127.6 tok/s$0.052/M
#13Nova MicroAmazon$0.140/M284.2 tok/s$0.061/M
#14Llama 3 Instruct 8BMeta$0.145/M88.3 tok/s$0.070/M
#15Llama 3.2 Instruct 3BMeta$0.150/M52.3 tok/s$0.150/M
#16Ministral 3 8BMistral$0.150/M103.6 tok/s$0.150/M
#17Qwen3.5 4B (Non-reasoning)Alibaba$0.150/M208.9 tok/s$0.060/M
#18Qwen3.5 4B (Reasoning)Alibaba$0.150/M195.8 tok/s$0.060/M
#19Qwen3.5 9B (Reasoning)Alibaba$0.150/M69.4 tok/s$0.113/M
#20Solar MiniUpstage$0.150/M75.9 tok/s$0.150/M
#21NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA$0.160/M118 tok/s$0.070/M
#22Sarvam 105B (high)Sarvam$0.170/M100.7 tok/s$0.074/M
#23Mistral Small 3Mistral$0.190/M153.7 tok/s$0.104/M
#24NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA$0.195/M133.6 tok/s$0.086/M
#25Apertus 8B InstructSwiss AI Initiative$0.200/Mn/a$0.125/M
#26gpt-oss-20B (high)OpenAI$0.200/M240 tok/s$0.088/M
#27gpt-oss-20B (low)OpenAI$0.200/M224.2 tok/s$0.095/M
#28Ministral 3 14BMistral$0.200/M106.9 tok/s$0.200/M
#29NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA$0.200/M87.3 tok/s$0.088/M
#30Olmo 3 7B InstructAllen Institute for AI$0.200/Mn/a$0.125/M
#31Qwen2.5 TurboAlibaba$0.200/M66.4 tok/s$0.088/M
#32Qwen3 8B (Non-reasoning)Alibaba$0.200/M64.4 tok/s$0.185/M
#33NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA$0.220/M133.6 tok/s$0.096/M
#34Mistral 7B InstructMistral$0.225/M110.4 tok/s$0.206/M
#35Mistral Small 3.1Mistral$0.235/M158.2 tok/s$0.138/M
#36Nova LiteAmazon$0.240/M191.7 tok/s$0.105/M
#37Llama 3.2 Instruct 11B (Vision)Meta$0.245/M87.4 tok/s$0.245/M
#38Gemma 3 27B InstructGoogle$0.250/Mn/a$0.145/M
#39Granite 3.3 8B (Non-reasoning)IBM$0.250/M400.9 tok/s$0.085/M
#40Granite 4.0 H SmallIBM$0.250/M454.2 tok/s$0.107/M
#41Llama 2 Chat 7BMeta$0.250/M100.6 tok/s$0.100/M
#42Mistral Small 3.2Mistral$0.250/M127.1 tok/s$0.128/M
#43DeepSeek V4 Flash (Non-reasoning)DeepSeek$0.280/M97.4 tok/s$0.175/M
#44DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek$0.280/Mn/a$0.175/M
#45DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek$0.280/M98.3 tok/s$0.175/M
#46MiMo-V2.5Xiaomi$0.280/M77.4 tok/s$0.175/M
#47Gemma 3 12B InstructGoogle$0.290/Mn/a$0.140/M
#48Qwen3 30B A3B (Non-reasoning)Alibaba$0.290/M68.6 tok/s$0.133/M
#49Devstral Small (Jul '25)Mistral$0.300/M42.3 tok/s$0.150/M
#50Gemma 4 12B (Reasoning)Google$0.300/M158.6 tok/s$0.150/M
#51Hermes 3 - Llama-3.1 70BNous Research$0.300/M34.1 tok/s$0.300/M
#52Ling 2.6 FlashInclusionAI$0.300/Mn/a$0.150/M
#53MiMo-V2-Flash (Feb 2026)Xiaomi$0.300/M124.9 tok/s$0.150/M
#54MiMo-V2-Flash (Non-reasoning)Xiaomi$0.300/M122.8 tok/s$0.150/M
#55MiMo-V2-Flash (Reasoning)Xiaomi$0.300/M129.5 tok/s$0.150/M
#56Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA$0.300/M276.7 tok/s$0.131/M
#57Step 3.5 FlashStepFun$0.300/M217.5 tok/s$0.150/M
#58Step 3.5 Flash 2603StepFun$0.300/M231 tok/s$0.150/M
#59Gemini 2.5 Flash-Lite (Non-reasoning)Google$0.400/M229.5 tok/s$0.175/M
#60Gemini 2.5 Flash-Lite (Reasoning)Google$0.400/M265.2 tok/s$0.175/M
#61Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google$0.400/Mn/a$0.175/M
#62Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google$0.400/Mn/a$0.175/M
#63Gemma 4 26B A4B (Non-reasoning)Google$0.400/M48 tok/s$0.198/M
#64Gemma 4 26B A4B (Reasoning)Google$0.400/Mn/a$0.198/M
#65Gemma 4 31B (Non-reasoning)Google$0.400/M54.9 tok/s$0.205/M
#66GLM-4.7-Flash (Non-reasoning)Z AI$0.400/M105.6 tok/s$0.153/M
#67GLM-4.7-Flash (Reasoning)Z AI$0.400/M94.1 tok/s$0.153/M
#68GPT-4.1 nanoOpenAI$0.400/M118.2 tok/s$0.175/M
#69GPT-5 nano (high)OpenAI$0.400/M150.4 tok/s$0.138/M
#70GPT-5 nano (medium)OpenAI$0.400/M167 tok/s$0.138/M
#71GPT-5 nano (minimal)OpenAI$0.400/M153.9 tok/s$0.138/M
#72Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research$0.400/M84.9 tok/s$0.198/M
#73Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research$0.400/M87.2 tok/s$0.198/M
#74Jamba 1.5 MiniAI21 Labs$0.400/Mn/a$0.250/M
#75Jamba 1.6 MiniAI21 Labs$0.400/M185.9 tok/s$0.250/M
#76Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA$0.400/M43.9 tok/s$0.175/M
#77Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA$0.400/M44.2 tok/s$0.175/M
#78Qwen2.5 Instruct 72BAlibaba$0.400/Mn/a$0.370/M
#79Qwen3 30B A3B 2507 InstructAlibaba$0.400/M105.2 tok/s$0.213/M
#80DeepSeek V3.2 Exp (Non-reasoning)DeepSeek$0.415/Mn/a$0.310/M