Fastest Output Speed Ranking
Ranked by Artificial Analysis measured output speed (tokens/sec)
OpenRouter Route Price Auto-updated daily
| # | Model | Provider | Input | Output | Context | Quality |
|---|---|---|---|---|---|---|
| 1 | Inception: Mercury 2 | | $0.250 | $0.750 | 128K | AA Index 22 |
| 2 | Google: Gemini 2.5 Flash Lite MultimodalVoice | | $0.100 | $0.400 | 1.05M | AA Index 11 |
| 3 | Ling-3.0-flash | | $0.021 | $0.063 | 262K | AA Index 38 |
| 4 | Google: Gemini 3.5 Flash Lite MultimodalVoice | | $0.300 | $2.50 | 1.05M | AA Index 37 |
| 5 | Google: Gemini 3.7 Flash MultimodalVoice | | $0.375 | $1.88 | 1.05M | AA Index 56 |
| 6 | Google: Gemini 3.1 Flash Lite Preview MultimodalVoice | | $0.250 | $1.50 | 1.05M | AA Index 26 |
| 7 | NVIDIA: Nemotron 3 Nano Omni (free) MultimodalVoice | | Free | Free | 256K | AA Index 15 |
| 8 | NVIDIA: Nemotron 3.5 Lightning | | $0.080 | $0.200 | 262K | AA Index 24 |
| 9 | Amazon: Nova Micro 1.0 |  🇺🇸 Amazon | $0.035 | $0.140 | 128K | AA Index 4 |
| 10 | NVIDIA: Nemotron 3 Nano 30B A3B | | $0.050 | $0.200 | 262K | AA Index 15 |
| 11 | OpenAI: o3 Mini Reasoning | | $1.10 | $4.40 | 200K | AA Index 19 |
| 12 | NVIDIA: Nemotron Nano 9B V2 | | $0.040 | $0.160 | 131K | AA Index 9 |
| 13 | Meta: Muse Spark 1.1 MultimodalVoice | meta | $1.25 | $4.25 | 1.05M | AA Index 53 |
| 14 | StepFun: Step 3.5 Flash | | $0.100 | $0.300 | 262K | AA Index 26 |
| 15 | Google: Gemini 2.5 Flash MultimodalVoice | | $0.300 | $2.50 | 1.05M | AA Index 14 |
| 16 | Qwen: Qwen3.7 Max | | $1.48 | $4.42 | 1M | AA Index 47 |
| 17 | Mistral: Ministral 3 3B 2512 Multimodal | | $0.100 | $0.100 | 131K | AA Index 7 |
| 18 | Google: Gemini 3.6 Flash MultimodalVoice | | $0.750 | $3.75 | 1.05M | AA Index 52 |
| 19 | Qwen: Qwen3 Next 80B A3B Thinking | | $0.150 | $1.20 | 262K | AA Index 17 |
| 20 | Google: Gemini 3.5 Flash MultimodalVoice | | — | — | 1.05M | AA Index 52 |
| 21 | Amazon: Nova 2 Lite Multimodal | 🇺🇸 Amazon | $0.300 | $2.50 | 1M | AA Index 19 |
| 22 | Google: Gemini 3 Flash Preview MultimodalVoice | | $0.500 | $3.00 | 1.05M | AA Index 39 |
| 23 | NVIDIA: Nemotron 3 Ultra | | $0.600 | $3.60 | 512K | AA Index 38 |
| 24 | Qwen: Qwen3 Next 80B A3B Instruct | | $0.100 | $1.10 | 262K | AA Index 14 |
| 25 | Mistral: Mistral Small 4 Multimodal | | $0.150 | $0.600 | 262K | AA Index 20 |
| 26 | Arcee AI: Trinity Large Thinking | | $0.220 | $0.850 | 262K | AA Index 19 |
| 27 | OpenAI: GPT-5.4 Mini Multimodal | | $0.750 | $4.50 | 400K | AA Index 41 |
| 28 | OpenAI: GPT-5.4 Nano Multimodal | | $0.200 | $1.25 | 400K | AA Index 40 |
| 29 | OpenAI: GPT-5 Nano Multimodal | | $0.050 | $0.400 | 400K | AA Index 20 |
| 30 | Amazon: Nova Lite 1.0 Multimodal | 🇺🇸 Amazon | $0.060 | $0.240 | 300K | AA Index 7 |
| 31 | OpenAI: gpt-oss-120b | | $0.037 | $0.170 | 131K | AA Index 24 |
| 32 | Mistral: Mistral Small 3 | | $0.050 | $0.080 | 33K | AA Index 7 |
| 33 | inclusionAI: Ling 3.0 Tiny (free) | | Free | Free | 262K | AA Index 25 |
| 34 | Upstage: Solar Pro 3 | | $0.150 | $0.600 | 131K | AA Index 14 |
| 35 | Mistral: Mistral Small 3.2 24B Multimodal | | $0.075 | $0.200 | 131K | AA Index 11 |
| 36 | Qwen: Qwen3.5-35B-A3B Multimodal | | $0.250 | $1.25 | 262K | AA Index 30 |
| 37 | Mistral: Mistral Small 3.1 24B Multimodal | | $0.351 | $0.555 | 128K | AA Index 15 |
| 38 | Qwen: Qwen3 30B A3B Thinking 2507 | | $0.200 | $2.40 | 82K | AA Index 15 |
| 39 | NVIDIA: Nemotron 3 Super | | $0.085 | $0.400 | 1M | AA Index 26 |
| 40 | OpenAI: o4 Mini MultimodalReasoning | | $1.10 | $4.40 | 200K | AA Index 26 |
| 41 | Mistral: Mistral Medium 3.5 Multimodal | | — | — | 262K | AA Index 30 |
| 42 | OpenAI: GPT-4o (2024-11-20) Multimodal | | $2.50 | $10.00 | 128K | AA Index 11 |
| 43 | SpaceXAI: Grok 4.3 Multimodal | | $1.25 | $2.50 | 1M | AA Index 38 |
| 44 | OpenAI: GPT-4.1 Multimodal | | $2.00 | $8.00 | 1.05M | AA Index 20 |
| 45 | OpenAI: GPT-4.1 Nano Multimodal | | $0.100 | $0.400 | 1.05M | AA Index 10 |
| 46 | Qwen: Qwen3 30B A3B Instruct 2507 | | $0.048 | $0.193 | 262K | AA Index 9 |
| 47 | Qwen: Qwen3.5-122B-A10B Multimodal | | $0.260 | $2.08 | 262K | AA Index 33 |
| 48 | Google: Gemini 2.5 Pro Preview 06-05 MultimodalVoice | | $1.25 | $10.00 | 1.05M | AA Index 26 |
| 49 | Meta: Llama 3.1 8B Instruct | | $0.050 | $0.080 | 131K | AA Index 7 |
| 50 | Thinking Machines: Inkling Small MultimodalVoice | thinkingmachines | $0.450 | $1.20 | 1.05M | AA Index 41 |
| 51 | Meta: Llama 4 Scout Multimodal | | $0.110 | $0.340 | 1.31M | AA Index 10 |
| 52 | Nex AGI: Nex-N2-Pro (free) Multimodal | | Free | Free | 262K | AA Index 42 |
| 53 | inclusionAI: Ring-2.6-1T | | — | — | 262K | AA Index 32 |
| 54 | OpenAI: GPT-5.6 Luna Multimodal | | $0.200 | $1.20 | 1.05M | AA Index 52 |
| 55 | Anthropic: Claude Haiku 4.5 Multimodal | | $1.00 | $5.00 | 200K | AA Index 30 |
| 56 | MiniMax: MiniMax M3 Multimodal | | $0.300 | $1.20 | 1.05M | AA Index 45 |
| 57 | OpenAI: GPT-5.4 Multimodal | | $2.50 | $15.00 | 1.05M | AA Index 53 |
| 58 | Mistral: Ministral 3 8B 2512 Multimodal | | $0.150 | $0.150 | 262K | AA Index 9 |
| 59 | OpenAI: o3 MultimodalReasoning | | $2.00 | $8.00 | 200K | AA Index 31 |
| 60 | OpenAI: GPT-5.3-Codex MultimodalCode | | $1.75 | $14.00 | 400K | AA Index 46 |
| 61 | MoonshotAI: Kimi K2 Thinking | | $0.600 | $2.50 | 262K | AA Index 33 |
| 62 | IBM: Granite 4.1 8B | | $0.050 | $0.100 | 131K | AA Index 6 |
| 63 | Qwen: Qwen3.6 35B A3B Multimodal | | $0.140 | $1.00 | 262K | AA Index 32 |
| 64 | OpenAI: gpt-oss-20b | | $0.030 | $0.130 | 131K | AA Index 15 |
| 65 | DeepSeek: DeepSeek V4 Flash 0731 | | $0.060 | $0.120 | 1.31M | AA Index 52 |
| 66 | Qwen: Qwen3 VL 8B Instruct Multimodal | | $0.117 | $0.455 | 262K | AA Index 8 |
| 67 | Qwen: Qwen3 VL 8B Thinking Multimodal | | $0.180 | $2.10 | 131K | AA Index 10 |
| 68 | Qwen: Qwen3 VL 30B A3B Instruct Multimodal | | $0.130 | $0.520 | 262K | AA Index 10 |
| 69 | Mistral: Mistral Medium 3.1 Multimodal | | $0.400 | $2.00 | 131K | AA Index 15 |
| 70 | Qwen: Qwen3 Coder Next Code | | $0.120 | $0.800 | 262K | AA Index 21 |
| 71 | Google: Gemini 3.1 Pro Preview MultimodalVoice | | $2.00 | $12.00 | 1.05M | AA Index 48 |
| 72 | Qwen: Qwen3 VL 30B A3B Thinking Multimodal | | $0.200 | $2.40 | 262K | AA Index 13 |
| 73 | NVIDIA: Nemotron Nano 12B 2 VL Multimodal | | $0.200 | $0.600 | 131K | AA Index 9 |
| 74 | OpenAI: GPT-5 Multimodal | | $1.25 | $10.00 | 400K | AA Index 35 |
| 75 | OpenAI: GPT-5.6 Terra Multimodal | | $2.00 | $12.00 | 1.05M | AA Index 57 |
| 76 | Qwen: Qwen3 30B A3B | | $0.120 | $0.500 | 131K | AA Index 9 |
| 77 | Qwen: Qwen3 32B | | $0.080 | $0.280 | 131K | AA Index 11 |
| 78 | OpenAI: GPT-5.1 Multimodal | | $1.25 | $10.00 | 400K | AA Index 37 |
| 79 | Meta: Llama 4 Maverick Multimodal | | $0.200 | $0.800 | 1.05M | AA Index 14 |
| 80 | NVIDIA: Llama 3.1 Nemotron 70B Instruct | | — | — | 131K | AA Index 7 |
| 81 | OpenAI: GPT-4o (2024-05-13) Multimodal | | — | — | 128K | AA Index 8 |
| 82 | Mistral: Ministral 3 14B 2512 Multimodal | | $0.200 | $0.200 | 262K | AA Index 11 |
| 83 | NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 | | $0.400 | $0.400 | 131K | AA Index 12 |
| 84 | StepFun: Step 3.7 Flash Multimodal | | — | — | 262K | AA Index 31 |
| 85 | MiniMax: MiniMax M2.1 | | $0.300 | $1.20 | 205K | AA Index 32 |
| 86 | MiniMax: MiniMax M2.5 | | $0.270 | $1.08 | 205K | AA Index 34 |
| 87 | Qwen: Qwen3.5 397B A17B Multimodal | | $0.390 | $2.34 | 262K | AA Index 34 |
| 88 | Qwen: Qwen3 VL 32B Instruct Multimodal | | $0.104 | $0.416 | 131K | AA Index 18 |
| 89 | Qwen: Qwen3 Coder 30B A3B Instruct Code | | $0.070 | $0.280 | 262K | AA Index 14 |
| 90 | MiniMax: MiniMax M2 | | $0.255 | $1.02 | 205K | AA Index 29 |
| 91 | OpenAI: GPT-5 Mini Multimodal | | $0.250 | $2.00 | 400K | AA Index 32 |
| 92 | OpenAI: GPT-4o (2024-08-06) Multimodal | | — | — | 128K | AA Index 9 |
| 93 | Z.ai: GLM 5.3 | | $1.40 | $4.40 | 1.05M | AA Index 60 |
| 94 | OpenAI: GPT-4o-mini Multimodal | | — | — | 128K | AA Index 7 |
| 95 | OpenAI: GPT-5.5 Multimodal | | $5.00 | $30.00 | 1.05M | AA Index 56 |
| 96 | Meta: Llama 3.3 70B Instruct | | $0.710 | $0.710 | 131K | AA Index 9 |
| 97 | Z.ai: GLM 4.7 Flash | | $0.060 | $0.400 | 203K | AA Index 23 |
| 98 | Anthropic: Claude Sonnet 5 Multimodal | | $2.00 | $10.00 | 1M | AA Index 55 |
| 99 | Qwen: Qwen3.5-9B Multimodal | | $0.100 | $0.150 | 262K | AA Index 22 |
| 100 | Qwen: Qwen3.5-27B Multimodal | | $0.195 | $1.56 | 262K | AA Index 35 |
| 101 | Z.ai: GLM 4.7 | | $0.400 | $1.75 | 205K | AA Index 34 |
| 102 | OpenAI: GPT-5.2 Multimodal | | $1.75 | $14.00 | 400K | AA Index 43 |
| 103 | OpenAI: GPT-4.1 Mini Multimodal | | $0.400 | $1.60 | 1.05M | AA Index 15 |
| 104 | xAI: Grok 3 Mini Beta | | $0.300 | $0.500 | 131K | AA Index 23 |
| 105 | Z.ai: GLM 4.5V Multimodal | | $0.600 | $1.80 | 66K | AA Index 9 |
| 106 | Qwen: Qwen3 Coder 480B A35B Code | | $0.300 | $1.00 | 262K | AA Index 18 |
| 107 | OpenAI: GPT-5.6 Sol Multimodal | | $2.00 | $10.00 | 1.05M | AA Index 61 |
| 108 | Anthropic: Claude Fable 5 Multimodal | | $10.00 | $50.00 | 1M | AA Index 62 |
| 109 | Xiaomi: MiMo-V2.5 MultimodalVoice | | $0.140 | $0.280 | 1.05M | AA Index 38 |
| 110 | Tencent: Hy3 | | $0.083 | $0.330 | 262K | AA Index 42 |
| 111 | Z.ai: GLM 5.2 | | $1.19 | $3.74 | 1.05M | AA Index 53 |
| 112 | Qwen: Qwen3 235B A22B Thinking 2507 | | $0.230 | $2.30 | 131K | AA Index 20 |
| 113 | Z.ai: GLM 5.1 | | $1.26 | $3.96 | 205K | AA Index 41 |
| 114 | DeepSeek: DeepSeek V4 Pro 0423 | | $0.870 | $1.74 | 1.05M | AA Index 45 |
| 115 | DeepSeek: DeepSeek V4 Pro 0813 | | $1.12 | $3.37 | 1.05M | AA Index 53 |
| 116 | Cohere: Command A | | $2.50 | $10.00 | 256K | AA Index 7 |
| 117 | MoonshotAI: Kimi K2.5 Multimodal | | $0.450 | $2.25 | 262K | AA Index 36 |
| 118 | Z.ai: GLM 4.6V Multimodal | | $0.300 | $0.900 | 131K | AA Index 17 |
| 119 | Qwen: Qwen3 14B | | $0.120 | $0.240 | 131K | AA Index 10 |
| 120 | Qwen: Qwen3 235B A22B | | $0.455 | $1.82 | 131K | AA Index 13 |
| 121 | Anthropic: Claude Opus 4.8 Multimodal | | — | — | 1M | AA Index 57 |
| 122 | Qwen: Qwen3 VL 235B A22B Thinking Multimodal | | $0.400 | $4.00 | 131K | AA Index 21 |
| 123 | Mistral: Mistral Medium 3 Multimodal | | $0.400 | $2.00 | 131K | AA Index 12 |
| 124 | SpaceXAI: Grok Build 0.1 Multimodal | | — | — | 256K | AA Index 41 |
| 125 | Upstage: Solar Pro 4 | | — | — | 524K | AA Index 42 |
| 126 | MiniMax: MiniMax M2.7 | | $0.300 | $1.20 | 205K | AA Index 39 |
| 127 | Z.ai: GLM 5 | | $0.600 | $1.92 | 205K | AA Index 41 |
| 128 | Meta: Llama 3.1 70B Instruct | | — | — | 131K | AA Index 7 |
| 129 | Qwen: Qwen3.7 Plus Multimodal | | $0.320 | $1.28 | 1M | AA Index 39 |
| 130 | Anthropic: Claude Sonnet 4.6 Multimodal | | $3.00 | $15.00 | 1M | AA Index 48 |
| 131 | SpaceXAI: Grok 4.5 Multimodal | | $2.00 | $6.00 | 500K | AA Index 56 |
| 132 | Claude Opus 5 Multimodal | | $5.00 | $25.00 | 1M | AA Index 63 |
| 133 | Z.ai: GLM 4.5 Air | | $0.130 | $0.850 | 131K | AA Index 17 |
| 134 | SpaceXAI: Grok 4.6 Multimodal | | — | $6.00 | 500K | AA Index 61 |
| 135 | Anthropic: Claude Opus 4.7 Multimodal | | $5.00 | $25.00 | 1M | AA Index 55 |
| 136 | Qwen: Qwen3.8 27B Multimodal | | $0.425 | $2.55 | 1M | AA Index 52 |
| 137 | Thinking Machines: Inkling MultimodalVoice | thinkingmachines | $0.950 | $4.05 | 1.05M | AA Index 42 |
| 138 | Mistral: Devstral 2 2512 | | $0.440 | $2.20 | 262K | AA Index 19 |
| 139 | Meta: Llama 3.2 11B Vision Instruct Multimodal | | $0.345 | $0.345 | 131K | AA Index 3 |
| 140 | Anthropic: Claude Opus 4.5 Multimodal | | $5.00 | $25.00 | 200K | AA Index 42 |
| 141 | Qwen: Qwen3.6 27B Multimodal | | $0.320 | $3.20 | 262K | AA Index 38 |
| 142 | Z.ai: GLM 4.6 | | $0.500 | $2.00 | 205K | AA Index 29 |
| 143 | Qwen: Qwen3 VL 235B A22B Instruct Multimodal | | $0.210 | $1.90 | 262K | AA Index 14 |
| 144 | Z.ai: GLM 5.3 Flash Multimodal | | $0.075 | $0.250 | 1.31M | AA Index 57 |
| 145 | Anthropic: Claude Sonnet 4.5 Multimodal | | $3.00 | $15.00 | 1M | AA Index 37 |
| 146 | Mistral: Mistral Large 3 2512 Multimodal | | $0.500 | $1.50 | 262K | AA Index 16 |
| 147 | MoonshotAI: Kimi K2.7 Code Multimodal | | $0.670 | $3.40 | 262K | AA Index 43 |
| 148 | Anthropic: Claude Opus 4.6 Multimodal | | $5.00 | $25.00 | 1M | AA Index 45 |
| 149 | Microsoft: Phi 4 Mini Instruct | | — | — | 131K | AA Index 6 |
| 150 | Xiaomi: MiMo-V2.5-Pro | | $0.435 | $0.870 | 1.05M | AA Index 43 |
| 151 | Qwen: Qwen3.6 Max Preview | | $1.03 | $6.16 | 262K | AA Index 41 |
| 152 | MoonshotAI: Kimi K2 0905 | | $0.600 | $2.50 | 262K | AA Index 24 |
| 153 | Meituan: LongCat 2.0 | meituan | $0.300 | $1.20 | 1.05M | AA Index 34 |
| 154 | MoonshotAI: Kimi K2 0711 | | $0.570 | $2.30 | 131K | AA Index 20 |
| 155 | MoonshotAI: Kimi K2.6 Multimodal | | $0.950 | $4.00 | 262K | AA Index 45 |
| 156 | Qwen: Qwen3 8B | | $0.117 | $0.455 | 131K | AA Index 8 |
| 157 | Qwen: Qwen3 Max | | $0.780 | $3.90 | 262K | AA Index 24 |
| 158 | MoonshotAI: Kimi K3 Multimodal | | $3.00 | $15.00 | 1.05M | AA Index 60 |
| 159 | Google: Gemma 4 31B Multimodal | | $0.090 | $0.340 | 262K | AA Index 30 |
| 160 | Nous: Hermes 3 70B Instruct | | $0.700 | $0.700 | 131K | AA Index 5 |
| 161 | Amazon: Nova Premier 1.0 Multimodal | 🇺🇸 Amazon | $2.50 | $12.50 | 1M | AA Index 13 |
| 162 | OpenAI: GPT-4 Turbo Multimodal | | — | — | 128K | AA Index 8 |
| 163 | DeepSeek: R1 Distill Llama 70B | | $0.800 | $0.800 | 8K | AA Index 10 |
| 164 | Cohere: North Mini Code (free) | | Free | Free | 256K | AA Index 20 |
| 165 | Qwen: Qwen3.8 2.4T A95B | | — | — | 1.05M | AA Index 58 |
| 166 | Qwen: Qwen3.8 Max Multimodal | | $2.00 | $6.00 | 1M | AA Index 58 |