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.
379 models have this metric.
Current leader: Llama 3.1 Instruct 8B
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 | Llama 3.1 Instruct 8B | Meta | $0.090/M | n/a | $0.079/M |
| #2 |
| $0.100/M |
| 101.1 tok/s |
| $0.040/M |
| #3 | Gemma 4 E4B (Reasoning) | $0.100/M | 101.2 tok/s | $0.040/M |
| #4 | Granite 4.1 8B | IBM | $0.100/M | 121.4 tok/s | $0.063/M |
| #5 | Ministral 3 3B | Mistral | $0.100/M | 282.2 tok/s | $0.100/M |
| #6 | Sarvam 30B (high) | Sarvam | $0.110/M | n/a | $0.047/M |
| #7 | Gemma 3n E4B Instruct | $0.120/M | n/a | $0.075/M |
| #8 | HyperNova 60B 2605 | Multiverse Computing | $0.140/M | 415 tok/s | $0.065/M |
| #9 | Nova Micro | Amazon | $0.140/M | 263.1 tok/s | $0.061/M |
| #10 | Llama 3 Instruct 8B | Meta | $0.145/M | n/a | $0.070/M |
| #11 | Ministral 3 8B | Mistral | $0.150/M | 108 tok/s | $0.150/M |
| #12 | Qwen3.5 4B (Non-reasoning) | Alibaba | $0.150/M | 19.4 tok/s | $0.060/M |
| #13 | Qwen3.5 4B (Reasoning) | Alibaba | $0.150/M | 26.3 tok/s | $0.060/M |
| #14 | Solar Mini | Upstage | $0.150/M | n/a | $0.150/M |
| #15 | NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | $0.160/M | 236.2 tok/s | $0.070/M |
| #16 | Sarvam 105B (high) | Sarvam | $0.170/M | n/a | $0.074/M |
| #17 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA | $0.195/M | 176.5 tok/s | $0.086/M |
| #18 | Apertus 8B Instruct | Swiss AI Initiative | $0.200/M | n/a | $0.125/M |
| #19 | gpt-oss-20b (high) | OpenAI | $0.200/M | 187.9 tok/s | $0.103/M |
| #20 | Ministral 3 14B | Mistral | $0.200/M | 94.9 tok/s | $0.200/M |
| #21 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA | $0.200/M | 234.5 tok/s | $0.088/M |
| #22 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | $0.200/M | 289 tok/s | $0.088/M |
| #23 | Olmo 3 7B Instruct | Allen Institute for AI | $0.200/M | n/a | $0.125/M |
| #24 | Qwen2.5 Turbo | Alibaba | $0.200/M | n/a | $0.088/M |
| #25 | Qwen3.5 9B (Reasoning) | Alibaba | $0.200/M | 58.1 tok/s | $0.151/M |
| #26 | gpt-oss-20b (low) | OpenAI | $0.225/M | 192 tok/s | $0.109/M |
| #27 | Hy3-preview (Non-reasoning) | Tencent | $0.235/M | n/a | $0.107/M |
| #28 | Hy3-preview (Reasoning) | Tencent | $0.235/M | n/a | $0.107/M |
| #29 | Nova Lite | Amazon | $0.240/M | n/a | $0.105/M |
| #30 | Granite 3.3 8B (Non-reasoning) | IBM | $0.250/M | n/a | $0.085/M |
| #31 | Granite 4.0 H Small | IBM | $0.250/M | 55.3 tok/s | $0.107/M |
| #32 | Llama 2 Chat 7B | Meta | $0.250/M | n/a | $0.100/M |
| #33 | Mistral 7B Instruct | Mistral | $0.250/M | n/a | $0.250/M |
| #34 | DeepSeek V4 Flash (Non-reasoning) | DeepSeek | $0.280/M | 101.9 tok/s | $0.175/M |
| #35 | DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek | $0.280/M | n/a | $0.175/M |
| #36 | DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | $0.280/M | 100.4 tok/s | $0.175/M |
| #37 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | $0.280/M | n/a | $0.175/M |
| #38 | MiMo-V2.5 | Xiaomi | $0.280/M | 67.1 tok/s | $0.175/M |
| #39 | Gemma 4 12B (Non-reasoning) | $0.300/M | 111 tok/s | $0.150/M |
| #40 | Gemma 4 12B (Reasoning) | $0.300/M | 122.2 tok/s | $0.150/M |
| #41 | Ling 2.6 Flash | InclusionAI | $0.300/M | 84.9 tok/s | $0.150/M |
| #42 | MiMo-V2-Flash (Reasoning) | Xiaomi | $0.300/M | n/a | $0.150/M |
| #43 | Mistral Small 3 | Mistral | $0.300/M | n/a | $0.150/M |
| #44 | Mistral Small 3.1 | Mistral | $0.300/M | n/a | $0.150/M |
| #45 | Mistral Small 3.2 | Mistral | $0.300/M | n/a | $0.150/M |
| #46 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | $0.300/M | 319.3 tok/s | $0.131/M |
| #47 | Step 3.5 Flash | StepFun | $0.300/M | n/a | $0.150/M |
| #48 | Step 3.5 Flash 2603 | StepFun | $0.300/M | n/a | $0.150/M |
| #49 | Llama 3.2 Instruct 11B (Vision) | Meta | $0.345/M | 6.1 tok/s | $0.345/M |
| #50 | Gemini 2.5 Flash-Lite (Non-reasoning) | $0.400/M | n/a | $0.175/M |
| #51 | Gemini 2.5 Flash-Lite (Reasoning) | $0.400/M | n/a | $0.175/M |
| #52 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | $0.400/M | n/a | $0.175/M |
| #53 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | $0.400/M | n/a | $0.175/M |
| #54 | Gemma 4 26B A4B (Non-reasoning) | $0.400/M | 61.9 tok/s | $0.198/M |
| #55 | Gemma 4 26B A4B (Reasoning) | $0.400/M | n/a | $0.198/M |
| #56 | Gemma 4 31B (Non-reasoning) | $0.400/M | 75.4 tok/s | $0.205/M |
| #57 | GLM-4.7-Flash (Non-reasoning) | Z AI | $0.400/M | n/a | $0.153/M |
| #58 | GLM-4.7-Flash (Reasoning) | Z AI | $0.400/M | n/a | $0.153/M |
| #59 | GPT-4.1 nano | OpenAI | $0.400/M | n/a | $0.175/M |
| #60 | GPT-5 nano (high) | OpenAI | $0.400/M | n/a | $0.138/M |
| #61 | GPT-5 nano (medium) | OpenAI | $0.400/M | n/a | $0.138/M |
| #62 | GPT-5 nano (minimal) | OpenAI | $0.400/M | n/a | $0.138/M |
| #63 | Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | $0.400/M | 85.5 tok/s | $0.198/M |
| #64 | Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | $0.400/M | 95.7 tok/s | $0.198/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 | n/a | $0.250/M |
| #67 | Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA | $0.400/M | 77 tok/s | $0.400/M |
| #68 | Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | $0.400/M | 93.3 tok/s | $0.400/M |
| #69 | DeepSeek V3.2 (Non-reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #70 | DeepSeek V3.2 (Reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #71 | DeepSeek V3.2 Exp (Non-reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #72 | DeepSeek V3.2 Exp (Reasoning) | DeepSeek | $0.420/M | n/a | $0.315/M |
| #73 | Qwen2.5 Instruct 72B | Alibaba | $0.495/M | n/a | $0.480/M |
| #74 | Grok 3 mini Reasoning (high) | SpaceXAI | $0.500/M | n/a | $0.350/M |
| #75 | Grok 4 Fast (Non-reasoning) | SpaceXAI | $0.500/M | n/a | $0.275/M |
| #76 | Grok 4 Fast (Reasoning) | SpaceXAI | $0.500/M | n/a | $0.275/M |
| #77 | Phi-4 | Microsoft | $0.500/M | 41.9 tok/s | $0.219/M |
| #78 | Hy3 | Tencent | $0.557/M | 70.7 tok/s | $0.241/M |
| #79 | Llama 3.1 Instruct 70B | Meta | $0.560/M | n/a | $0.560/M |
| #80 | Ling-flash-2.0 | InclusionAI | $0.570/M | n/a | $0.247/M |