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.
325 models have this metric.
Current leader: Gemma 3n E4B Instruct
Project links
Prices come from Artificial Analysis pricing data in the committed snapshot.
Top models ranked by Output $.
| Rank | Model | Creator | Value | Speed | Blended Price |
|---|---|---|---|---|---|
| #1 | Gemma 3n E4B Instruct | $0.040/M | 15.3 tok/s | $0.025/M | |
| #2 |
| Alibaba |
| $0.050/M |
| 273.6 tok/s |
| $0.020/M |
| #3 | Qwen3.5 0.8B (Reasoning) | Alibaba | $0.050/M | n/a | $0.020/M |
| #4 | Granite 4.1 8B | IBM | $0.100/M | 134.6 tok/s | $0.063/M |
| #5 | Llama 3.1 Instruct 8B | Meta | $0.100/M | 164.4 tok/s | $0.100/M |
| #6 | Llama 3.2 Instruct 1B | Meta | $0.100/M | 97.7 tok/s | $0.100/M |
| #7 | Ministral 3 3B | Mistral | $0.100/M | 287.6 tok/s | $0.100/M |
| #8 | Qwen3.5 2B (Non-reasoning) | Alibaba | $0.100/M | 227 tok/s | $0.040/M |
| #9 | Qwen3.5 2B (Reasoning) | Alibaba | $0.100/M | n/a | $0.040/M |
| #10 | LFM2 24B A2B | Liquid AI | $0.120/M | 196.9 tok/s | $0.052/M |
| #11 | Nova Micro | Amazon | $0.140/M | 332.1 tok/s | $0.061/M |
| #12 | Llama 3 Instruct 8B | Meta | $0.145/M | 82.2 tok/s | $0.070/M |
| #13 | Llama 3.2 Instruct 3B | Meta | $0.150/M | 52.2 tok/s | $0.150/M |
| #14 | Ministral 3 8B | Mistral | $0.150/M | 157.6 tok/s | $0.150/M |
| #15 | Qwen3.5 4B (Non-reasoning) | Alibaba | $0.150/M | 200.2 tok/s | $0.060/M |
| #16 | Qwen3.5 4B (Reasoning) | Alibaba | $0.150/M | 204.8 tok/s | $0.060/M |
| #17 | Qwen3.5 9B (Reasoning) | Alibaba | $0.150/M | 62.9 tok/s | $0.113/M |
| #18 | Solar Mini | Upstage | $0.150/M | 41.7 tok/s | $0.150/M |
| #19 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | $0.160/M | 121.6 tok/s | $0.070/M |
| #20 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | $0.195/M | 153.3 tok/s | $0.086/M |
| #21 | Apertus 8B Instruct | Swiss AI Initiative | $0.200/M | n/a | $0.125/M |
| #22 | gpt-oss-20B (high) | OpenAI | $0.200/M | 242.3 tok/s | $0.100/M |
| #23 | Ministral 3 14B | Mistral | $0.200/M | 121.6 tok/s | $0.200/M |
| #24 | Olmo 3 7B Instruct | Allen Institute for AI | $0.200/M | n/a | $0.125/M |
| #25 | Qwen2.5 Turbo | Alibaba | $0.200/M | 77.7 tok/s | $0.087/M |
| #26 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | $0.220/M | 154.8 tok/s | $0.096/M |
| #27 | gpt-oss-20B (low) | OpenAI | $0.225/M | 249.7 tok/s | $0.108/M |
| #28 | Nova Lite | Amazon | $0.240/M | 186.8 tok/s | $0.105/M |
| #29 | Llama 3.2 Instruct 11B (Vision) | Meta | $0.245/M | 77.4 tok/s | $0.245/M |
| #30 | Granite 3.3 8B (Non-reasoning) | IBM | $0.250/M | 410.5 tok/s | $0.085/M |
| #31 | Granite 4.0 H Small | IBM | $0.250/M | 238.9 tok/s | $0.107/M |
| #32 | Llama 2 Chat 7B | Meta | $0.250/M | 99.7 tok/s | $0.100/M |
| #33 | Mistral 7B Instruct | Mistral | $0.250/M | 156.9 tok/s | $0.250/M |
| #34 | DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek | $0.280/M | n/a | $0.175/M |
| #35 | DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | $0.280/M | 77.4 tok/s | $0.175/M |
| #36 | Devstral Small (Jul '25) | Mistral | $0.300/M | 194.2 tok/s | $0.150/M |
| #37 | Hermes 3 - Llama-3.1 70B | Nous Research | $0.300/M | 28.8 tok/s | $0.300/M |
| #38 | Ling 2.6 Flash | InclusionAI | $0.300/M | 206 tok/s | $0.150/M |
| #39 | MiMo-V2-Flash (Feb 2026) | Xiaomi | $0.300/M | 120.6 tok/s | $0.150/M |
| #40 | MiMo-V2-Flash (Non-reasoning) | Xiaomi | $0.300/M | 116.7 tok/s | $0.150/M |
| #41 | MiMo-V2-Flash (Reasoning) | Xiaomi | $0.300/M | 118.8 tok/s | $0.150/M |
| #42 | Mistral Small 3 | Mistral | $0.300/M | 135.9 tok/s | $0.150/M |
| #43 | Mistral Small 3.1 | Mistral | $0.300/M | 138.8 tok/s | $0.150/M |
| #44 | Mistral Small 3.2 | Mistral | $0.300/M | 153.8 tok/s | $0.150/M |
| #45 | Step 3.5 Flash | StepFun | $0.300/M | 123.6 tok/s | $0.150/M |
| #46 | Gemini 2.5 Flash-Lite (Non-reasoning) | $0.400/M | 239.9 tok/s | $0.175/M |
| #47 | Gemini 2.5 Flash-Lite (Reasoning) | $0.400/M | 243.6 tok/s | $0.175/M |
| #48 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | $0.400/M | n/a | $0.175/M |
| #49 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | $0.400/M | n/a | $0.175/M |
| #50 | Gemma 4 26B A4B (Reasoning) | $0.400/M | n/a | $0.198/M |
| #51 | GLM-4.7-Flash (Non-reasoning) | Z AI | $0.400/M | 89.6 tok/s | $0.152/M |
| #52 | GLM-4.7-Flash (Reasoning) | Z AI | $0.400/M | 110.5 tok/s | $0.152/M |
| #53 | GPT-4.1 nano | OpenAI | $0.400/M | 125.2 tok/s | $0.175/M |
| #54 | GPT-5 nano (high) | OpenAI | $0.400/M | 136 tok/s | $0.138/M |
| #55 | GPT-5 nano (medium) | OpenAI | $0.400/M | 150.3 tok/s | $0.138/M |
| #56 | GPT-5 nano (minimal) | OpenAI | $0.400/M | 139.1 tok/s | $0.138/M |
| #57 | Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | $0.400/M | 83.5 tok/s | $0.198/M |
| #58 | Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | $0.400/M | 78.6 tok/s | $0.198/M |
| #59 | Jamba 1.5 Mini | AI21 Labs | $0.400/M | n/a | $0.250/M |
| #60 | Jamba 1.6 Mini | AI21 Labs | $0.400/M | 184.5 tok/s | $0.250/M |
| #61 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | $0.400/M | 51.3 tok/s | $0.175/M |
| #62 | Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | $0.400/M | 50.8 tok/s | $0.175/M |
| #63 | DeepSeek V3.2 (Non-reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #64 | DeepSeek V3.2 (Reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #65 | DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #66 | DeepSeek V3.2 Exp (Reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #67 | Qwen3 0.6B (Non-reasoning) | Alibaba | $0.420/M | 204.8 tok/s | $0.188/M |
| #68 | Qwen3 1.7B (Non-reasoning) | Alibaba | $0.420/M | 139 tok/s | $0.188/M |
| #69 | Qwen3 4B (Non-reasoning) | Alibaba | $0.420/M | 104.4 tok/s | $0.188/M |
| #70 | Grok 3 mini Reasoning (high) | xAI | $0.500/M | 215.5 tok/s | $0.350/M |
| #71 | Grok 4 Fast (Non-reasoning) | xAI | $0.500/M | 77.4 tok/s | $0.275/M |
| #72 | Grok 4 Fast (Reasoning) | xAI | $0.500/M | 76.2 tok/s | $0.275/M |
| #73 | Grok 4.1 Fast (Non-reasoning) | xAI | $0.500/M | 112.1 tok/s | $0.275/M |
| #74 | Grok 4.1 Fast (Reasoning) | xAI | $0.500/M | 140.9 tok/s | $0.275/M |
| #75 | Phi-4 | Microsoft | $0.500/M | 41.6 tok/s | $0.219/M |
| #76 | Llama 3.1 Instruct 70B | Meta | $0.560/M | 32.2 tok/s | $0.560/M |
| #77 | Ling-flash-2.0 | InclusionAI | $0.570/M | 87.3 tok/s | $0.247/M |
| #78 | Ring-flash-2.0 | InclusionAI | $0.570/M | 91 tok/s | $0.247/M |
| #79 | Seed-OSS-36B-Instruct | ByteDance Seed | $0.570/M | 40 tok/s | $0.300/M |
| #80 | Gemini 2.0 Flash (Feb '25) | $0.600/M | n/a | $0.263/M |