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.
371 models have this metric.
Current leader: Gemma 3n E4B Instruct
Project links
Prices come from the current Artificial Analysis pricing dataset, read from Supabase when configured.
Top models ranked by Output $.
| Rank | Model | Creator | Value | Speed | Blended Price |
|---|---|---|---|---|---|
| #1 | Gemma 3n E4B Instruct | $0.040/M | 49.7 tok/s | $0.025/M | |
| #2 |
| Mistral |
| $0.100/M |
| 158.5 tok/s |
| $0.100/M |
| #3 | Granite 4.1 8B | IBM | $0.100/M | 117.8 tok/s | $0.063/M |
| #4 | Llama 3.1 Instruct 8B | Meta | $0.100/M | 155.5 tok/s | $0.100/M |
| #5 | Llama 3.2 Instruct 1B | Meta | $0.100/M | 86.4 tok/s | $0.100/M |
| #6 | Sarvam 30B (high) | Sarvam | $0.110/M | 200.7 tok/s | $0.047/M |
| #7 | Nova Micro | Amazon | $0.140/M | 249.8 tok/s | $0.061/M |
| #8 | HyperNova 60B 2605 | Multiverse Computing | $0.140/M | 350.9 tok/s | $0.065/M |
| #9 | Llama 3 Instruct 8B | Meta | $0.145/M | 79.8 tok/s | $0.070/M |
| #10 | Ministral 3 8B | Mistral | $0.150/M | 89 tok/s | $0.150/M |
| #11 | Qwen3.5 4B (Non-reasoning) | Alibaba | $0.150/M | 23 tok/s | $0.060/M |
| #12 | Qwen3.5 9B (Reasoning) | Alibaba | $0.150/M | 67.6 tok/s | $0.113/M |
| #13 | Qwen3.5 4B (Reasoning) | Alibaba | $0.150/M | 22.8 tok/s | $0.060/M |
| #14 | Llama 3.2 Instruct 3B | Meta | $0.150/M | 51.7 tok/s | $0.150/M |
| #15 | Solar Mini | Upstage | $0.150/M | 78.2 tok/s | $0.150/M |
| #16 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | $0.160/M | 85.9 tok/s | $0.070/M |
| #17 | Sarvam 105B (high) | Sarvam | $0.170/M | 115.9 tok/s | $0.074/M |
| #18 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | $0.195/M | 138.9 tok/s | $0.086/M |
| #19 | gpt-oss-20b (low) | OpenAI | $0.200/M | 260.9 tok/s | $0.095/M |
| #20 | gpt-oss-20b (high) | OpenAI | $0.200/M | 224.5 tok/s | $0.088/M |
| #21 | Ministral 3 14B | Mistral | $0.200/M | 75.5 tok/s | $0.200/M |
| #22 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | $0.200/M | 99.8 tok/s | $0.088/M |
| #23 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | $0.200/M | 111.7 tok/s | $0.088/M |
| #24 | Olmo 3 7B Instruct | Allen Institute for AI | $0.200/M | n/a | $0.125/M |
| #25 | Apertus 8B Instruct | Swiss AI Initiative | $0.200/M | n/a | $0.125/M |
| #26 | Qwen2.5 Turbo | Alibaba | $0.200/M | 113.6 tok/s | $0.088/M |
| #27 | Nova Lite | Amazon | $0.240/M | 147.8 tok/s | $0.105/M |
| #28 | Granite 4.0 H Small | IBM | $0.250/M | 439.5 tok/s | $0.107/M |
| #29 | Llama 2 Chat 7B | Meta | $0.250/M | 95.6 tok/s | $0.100/M |
| #30 | Mistral 7B Instruct | Mistral | $0.250/M | 91.5 tok/s | $0.250/M |
| #31 | Granite 3.3 8B (Non-reasoning) | IBM | $0.250/M | 414.9 tok/s | $0.085/M |
| #32 | DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | $0.280/M | 101.1 tok/s | $0.175/M |
| #33 | DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek | $0.280/M | n/a | $0.175/M |
| #34 | DeepSeek V4 Flash (Non-reasoning) | DeepSeek | $0.280/M | 90.1 tok/s | $0.175/M |
| #35 | MiMo-V2.5 | Xiaomi | $0.280/M | 75.5 tok/s | $0.175/M |
| #36 | Gemma 4 12B (Non-reasoning) | $0.300/M | 121.2 tok/s | $0.150/M |
| #37 | Gemma 4 12B (Reasoning) | $0.300/M | 125.3 tok/s | $0.150/M |
| #38 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | $0.300/M | 320 tok/s | $0.131/M |
| #39 | Step 3.5 Flash 2603 | StepFun | $0.300/M | 256.9 tok/s | $0.150/M |
| #40 | Ling 2.6 Flash | InclusionAI | $0.300/M | 172.8 tok/s | $0.150/M |
| #41 | Mistral Small 3 | Mistral | $0.300/M | 145.3 tok/s | $0.150/M |
| #42 | Mistral Small 3.1 | Mistral | $0.300/M | 144.9 tok/s | $0.150/M |
| #43 | Mistral Small 3.2 | Mistral | $0.300/M | 144.9 tok/s | $0.150/M |
| #44 | Devstral Small (Jul '25) | Mistral | $0.300/M | n/a | $0.150/M |
| #45 | Step 3.5 Flash | StepFun | $0.300/M | 247.4 tok/s | $0.150/M |
| #46 | MiMo-V2-Flash (Reasoning) | Xiaomi | $0.300/M | n/a | $0.150/M |
| #47 | Llama 3.2 Instruct 11B (Vision) | Meta | $0.345/M | 72.8 tok/s | $0.345/M |
| #48 | Gemma 4 31B (Non-reasoning) | $0.400/M | 43.7 tok/s | $0.205/M |
| #49 | Gemma 4 26B A4B (Non-reasoning) | $0.400/M | 70.8 tok/s | $0.198/M |
| #50 | Gemma 4 26B A4B (Reasoning) | $0.400/M | n/a | $0.198/M |
| #51 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | $0.400/M | 52.2 tok/s | $0.400/M |
| #52 | Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | $0.400/M | 51.8 tok/s | $0.400/M |
| #53 | Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | $0.400/M | 96.2 tok/s | $0.198/M |
| #54 | Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | $0.400/M | 92.1 tok/s | $0.198/M |
| #55 | GPT-4.1 nano | OpenAI | $0.400/M | 148 tok/s | $0.175/M |
| #56 | GPT-5 nano (minimal) | OpenAI | $0.400/M | 168.7 tok/s | $0.138/M |
| #57 | GPT-5 nano (medium) | OpenAI | $0.400/M | 155.7 tok/s | $0.138/M |
| #58 | GPT-5 nano (high) | OpenAI | $0.400/M | 154.5 tok/s | $0.138/M |
| #59 | Gemini 2.5 Flash-Lite (Reasoning) | $0.400/M | 237.8 tok/s | $0.175/M |
| #60 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | $0.400/M | n/a | $0.175/M |
| #61 | Gemini 2.5 Flash-Lite (Non-reasoning) | $0.400/M | 182.3 tok/s | $0.175/M |
| #62 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | $0.400/M | n/a | $0.175/M |
| #63 | GLM-4.7-Flash (Reasoning) | Z AI | $0.400/M | 83.7 tok/s | $0.153/M |
| #64 | GLM-4.7-Flash (Non-reasoning) | Z AI | $0.400/M | 122.7 tok/s | $0.153/M |
| #65 | Jamba 1.5 Mini | AI21 Labs | $0.400/M | n/a | $0.250/M |
| #66 | Jamba 1.6 Mini | AI21 Labs | $0.400/M | 179.6 tok/s | $0.250/M |
| #67 | DeepSeek V3.2 (Reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #68 | DeepSeek V3.2 (Non-reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #69 | DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #70 | DeepSeek V3.2 Exp (Reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #71 | Hy3-preview (Reasoning) | Tencent | $0.430/M | 124.1 tok/s | $0.200/M |
| #72 | Hy3-preview (Non-reasoning) | Tencent | $0.430/M | 121.5 tok/s | $0.200/M |
| #73 | Qwen2.5 Instruct 72B | Alibaba | $0.495/M | n/a | $0.480/M |
| #74 | Phi-4 | Microsoft | $0.500/M | 27 tok/s | $0.219/M |
| #75 | Grok 3 mini Reasoning (high) | SpaceXAI | $0.500/M | 45.7 tok/s | $0.350/M |
| #76 | Grok 4 Fast (Reasoning) | SpaceXAI | $0.500/M | n/a | $0.275/M |
| #77 | Grok 4 Fast (Non-reasoning) | SpaceXAI | $0.500/M | n/a | $0.275/M |
| #78 | Llama 3.1 Instruct 70B | Meta | $0.560/M | 33.8 tok/s | $0.560/M |
| #79 | Ring-flash-2.0 | InclusionAI | $0.570/M | n/a | $0.247/M |
| #80 | Ling-flash-2.0 | InclusionAI | $0.570/M | 61.8 tok/s | $0.247/M |