Large Context Window AI Models
Compare 428 AI models with context windows of 32K tokens or more. The largest models support 2M tokens -- enough to process entire codebases, books, or hundreds of documents in a single prompt. Data updated hourly.
196
1M+ Tokens
133
200K+ Tokens
72
128K Tokens
27
32K–64K Tokens
2M
Largest Context
428
Models (32K+)
598K
Average Context
1M+ Tokens
(196 models)The largest context windows available. These models can process entire codebases, full books, or hundreds of documents in a single request.
| # | Model | Provider | Context Window | Pages | Input / 1M | Output / 1M |
|---|---|---|---|---|---|---|
| 1 | Grok 4.20 | xAI | 2M | ~3K | $1.25 | $2.50 |
| 2 | Grok 4.20 Multi-Agent | xAI | 2M | ~3K | $1.25 | $2.50 |
| 3 | Llama 4 Scout | Meta | 1.3M | ~2K | $0.10 | $0.30 |
| 4 | GPT Astra Latest | ~openai | 1.1M | ~1K | $10.00 | $50.00 |
| 5 | GPT Luna Latest | ~openai | 1.1M | ~1K | $0.10 | $0.50 |
| 6 | GPT Sol Latest | ~openai | 1.1M | ~1K | $2.00 | $10.00 |
| 7 | GPT Terra Latest | ~openai | 1.1M | ~1K | $1.00 | $5.00 |
| 8 | GPT-5.4 | OpenAI | 1.1M | ~1K | $2.50 | $15.00 |
| 9 | GPT-5.4 (batch) | OpenAI | 1.1M | ~1K | $1.25 | $7.50 |
| 10 | GPT-5.4 Pro | OpenAI | 1.1M | ~1K | $30.00 | $180.00 |
| 11 | GPT-5.4 Pro (batch) | OpenAI | 1.1M | ~1K | $15.00 | $90.00 |
| 12 | GPT-5.5 | OpenAI | 1.1M | ~1K | $5.00 | $30.00 |
| 13 | GPT-5.5 (batch) | OpenAI | 1.1M | ~1K | $2.50 | $15.00 |
| 14 | GPT-5.5 Pro | OpenAI | 1.1M | ~1K | $30.00 | $180.00 |
| 15 | GPT-5.5 Pro (batch) | OpenAI | 1.1M | ~1K | $15.00 | $90.00 |
| 16 | GPT-5.6 Luna | OpenAI | 1.1M | ~1K | $0.20 | $1.20 |
| 17 | GPT-5.6 Luna (batch) | OpenAI | 1.1M | ~1K | $0.10 | $0.60 |
| 18 | GPT-5.6 Luna Pro | OpenAI | 1.1M | ~1K | $0.20 | $1.20 |
| 19 | GPT-5.6 Luna Pro (batch) | OpenAI | 1.1M | ~1K | $0.10 | $0.60 |
| 20 | GPT-5.6 Sol | OpenAI | 1.1M | ~1K | $4.00 | $20.00 |
| 21 | GPT-5.6 Sol (batch) | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 22 | GPT-5.6 Sol Pro | OpenAI | 1.1M | ~1K | $4.00 | $20.00 |
| 23 | GPT-5.6 Sol Pro (batch) | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 24 | GPT-5.6 Terra | OpenAI | 1.1M | ~1K | $2.00 | $12.00 |
| 25 | GPT-5.6 Terra (batch) | OpenAI | 1.1M | ~1K | $1.00 | $6.00 |
| 26 | GPT-5.6 Terra Pro | OpenAI | 1.1M | ~1K | $2.00 | $12.00 |
| 27 | GPT-5.6 Terra Pro (batch) | OpenAI | 1.1M | ~1K | $1.00 | $6.00 |
| 28 | GPT-6 Astra | OpenAI | 1.1M | ~1K | $10.00 | $50.00 |
| 29 | GPT-6 Astra (batch) | OpenAI | 1.1M | ~1K | $5.00 | $25.00 |
| 30 | GPT-6 Astra Pro | OpenAI | 1.1M | ~1K | $10.00 | $50.00 |
| 31 | GPT-6 Astra Pro (batch) | OpenAI | 1.1M | ~1K | $5.00 | $25.00 |
| 32 | GPT-6 Luna | OpenAI | 1.1M | ~1K | $0.10 | $0.50 |
| 33 | GPT-6 Luna (batch) | OpenAI | 1.1M | ~1K | $0.05 | $0.25 |
| 34 | GPT-6 Luna Pro | OpenAI | 1.1M | ~1K | $0.10 | $0.50 |
| 35 | GPT-6 Luna Pro (batch) | OpenAI | 1.1M | ~1K | $0.05 | $0.25 |
| 36 | GPT-6 Sol | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 37 | GPT-6 Sol (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 38 | GPT-6 Sol Pro | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 39 | GPT-6 Sol Pro (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 40 | GPT-6.1 Sol | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 41 | GPT-6.1 Sol (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 42 | GPT-6.1 Sol Pro | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 43 | GPT-6.1 Sol Pro (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 44 | GPT-6.1 Terra | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 45 | GPT-6.1 Terra (batch) | OpenAI | 1.1M | ~1K | $0.50 | $2.50 |
| 46 | GPT-6.1 Terra Pro | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 47 | GPT-6.1 Terra Pro (batch) | OpenAI | 1.1M | ~1K | $0.50 | $2.50 |
| 48 | MiMo-V2.5-Pro | Xiaomi | 1.1M | ~1K | $0.48 | $1.80 |
| 49 | MiMo-V2.6-Flash | Xiaomi | 1.1M | ~1K | $0.14 | $0.28 |
| 50 | MiMo-V2.6-Pro | Xiaomi | 1.1M | ~1K | $0.43 | $0.87 |
| 51 | LongCat 2.0 | Meituan | 1.0M | ~1K | $0.30 | $1.20 |
| 52 | Beam 1.0 501B A23B | reflection | 1.0M | ~1K | $0.30 | $1.00 |
| 53 | Crouton Alpha | stealth | 1.0M | ~1K | Free | Free |
| 54 | DeepSeek Flash Latest | ~deepseek | 1.0M | ~1K | $0.0060 | $0.50 |
| 55 | DeepSeek Pro Latest | ~deepseek | 1.0M | ~1K | $0.10 | $8.00 |
| 56 | DeepSeek V4 Flash 0423 | DeepSeek | 1.0M | ~1K | $0.09 | $0.18 |
| 57 | DeepSeek V4 Flash 0731 | DeepSeek | 1.0M | ~1K | $0.06 | $0.30 |
| 58 | DeepSeek V4 Flash Latest | ~deepseek | 1.0M | ~1K | $0.06 | $0.30 |
| 59 | DeepSeek V4 Flash Vision Exp | DeepSeek | 1.0M | ~1K | $0.44 | $1.32 |
| 60 | DeepSeek V4 Pro 0423 | DeepSeek | 1.0M | ~1K | $0.89 | $1.78 |
| 61 | DeepSeek V4 Pro 0813 | DeepSeek | 1.0M | ~1K | $0.12 | $4.66 |
| 62 | DeepSeek V4.1 Flash | DeepSeek | 1.0M | ~1K | $0.05 | $0.57 |
| 63 | DeepSeek V4.1 Flash (batch) | DeepSeek | 1.0M | ~1K | $0.11 | $0.34 |
| 64 | DeepSeek V4.1 Flash 1017 | DeepSeek | 1.0M | ~1K | $0.15 | $0.60 |
| 65 | Ember-1 | fireworks | 1.0M | ~1K | $3.00 | $15.00 |
| 66 | Gemini 2.5 Flash | 1.0M | ~1K | $0.30 | $2.50 | |
| 67 | Gemini 2.5 Flash Lite | 1.0M | ~1K | $0.10 | $0.40 | |
| 68 | Gemini 2.5 Pro | 1.0M | ~1K | $1.25 | $10.00 | |
| 69 | Gemini 2.5 Pro Preview 06-05 | 1.0M | ~1K | $1.25 | $10.00 | |
| 70 | Gemini 3 Flash Preview | 1.0M | ~1K | $0.50 | $3.00 | |
| 71 | Gemini 3 Flash Preview (batch) | 1.0M | ~1K | $0.25 | $1.50 | |
| 72 | Gemini 3.1 Flash Lite | 1.0M | ~1K | $0.25 | $1.50 | |
| 73 | Gemini 3.1 Flash Lite (batch) | 1.0M | ~1K | $0.13 | $0.75 | |
| 74 | Gemini 3.1 Flash Lite Preview | 1.0M | ~1K | $0.25 | $1.50 | |
| 75 | Gemini 3.1 Pro Preview | 1.0M | ~1K | $2.00 | $12.00 | |
| 76 | Gemini 3.1 Pro Preview (batch) | 1.0M | ~1K | $1.00 | $6.00 | |
| 77 | Gemini 3.1 Pro Preview Custom Tools | 1.0M | ~1K | $2.00 | $12.00 | |
| 78 | Gemini 3.5 Flash | 1.0M | ~1K | $1.50 | $9.00 | |
| 79 | Gemini 3.5 Flash (batch) | 1.0M | ~1K | $0.75 | $4.50 | |
| 80 | Gemini 3.5 Flash Lite | 1.0M | ~1K | $0.30 | $2.50 | |
| 81 | Gemini 3.5 Flash Lite (batch) | 1.0M | ~1K | $0.15 | $1.25 | |
| 82 | Gemini 3.6 Flash | 1.0M | ~1K | $0.75 | $3.75 | |
| 83 | Gemini 3.6 Flash (batch) | 1.0M | ~1K | $0.38 | $1.88 | |
| 84 | Gemini 3.7 Flash | 1.0M | ~1K | $0.75 | $3.75 | |
| 85 | Gemini 3.7 Flash (batch) | 1.0M | ~1K | $0.38 | $1.88 | |
| 86 | Gemini 3.8 Flash | 1.0M | ~1K | $0.83 | $4.13 | |
| 87 | Gemini 3.8 Flash (batch) | 1.0M | ~1K | $0.38 | $1.88 | |
| 88 | Gemini 4 Argon | 1.0M | ~1K | $2.00 | $10.00 | |
| 89 | Gemini 4 Argon (batch) | 1.0M | ~1K | $1.00 | $5.00 | |
| 90 | Gemini Flash Latest | 1.0M | ~1K | $0.75 | $3.75 | |
| 91 | Gemini Pro Latest | 1.0M | ~1K | $2.00 | $10.00 | |
| 92 | GLM 5.2 | Zhipu AI | 1.0M | ~1K | $0.0060 | $6.80 |
| 93 | GLM 5.3 | Zhipu AI | 1.0M | ~1K | $0.07 | $1.40 |
| 94 | GLM 5.3 (batch) | Zhipu AI | 1.0M | ~1K | $0.45 | $2.00 |
| 95 | GLM 5.3 Flash | Zhipu AI | 1.0M | ~1K | $0.15 | $0.50 |
| 96 | GLM 5.3 Flash (batch) | Zhipu AI | 1.0M | ~1K | $0.05 | $0.18 |
| 97 | GLM 5.3 FlashX | Zhipu AI | 1.0M | ~1K | $0.37 | $1.25 |
| 98 | GLM 5.3 FlashX Legal | Zhipu AI | 1.0M | ~1K | $0.37 | $1.25 |
| 99 | GLM Flash Latest | ~z-ai | 1.0M | ~1K | $0.03 | $0.09 |
| 100 | GLM Latest | ~z-ai | 1.0M | ~1K | $0.07 | $1.40 |
| 101 | Hy4 | Tencent | 1.0M | ~1K | $0.42 | $1.25 |
| 102 | Hy4 preview | Tencent | 1.0M | ~1K | $0.83 | $2.50 |
| 103 | Kimi K3 | Moonshot AI | 1.0M | ~1K | $0.19 | $16.00 |
| 104 | Kimi K3 (batch) | Moonshot AI | 1.0M | ~1K | $2.28 | $11.40 |
| 105 | Kimi K3.1 Pro | Moonshot AI | 1.0M | ~1K | $2.00 | $10.00 |
| 106 | Kimi Latest | ~moonshotai | 1.0M | ~1K | $0.15 | $9.34 |
| 107 | Lyria 3 Clip Preview | 1.0M | ~1K | Free | Free | |
| 108 | Lyria 3 Pro Preview | 1.0M | ~1K | Free | Free | |
| 109 | MiMo-V2.6-Pro-UltraSpeed | Xiaomi | 1.0M | ~1K | $4.35 | $8.70 |
| 110 | MiniMax M3 | MiniMax | 1.0M | ~1K | $0.30 | $1.20 |
| 111 | MiniMax M3.1 Flash | MiniMax | 1.0M | ~1K | $0.15 | $0.60 |
| 112 | Mistral Large 4 | Mistral AI | 1.0M | ~1K | $0.70 | $2.10 |
| 113 | Muse Spark 1.1 | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 114 | Muse Spark 1.2 | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 115 | Muse Spark 1.2 Contributor | meta | 1.0M | ~1K | $0.10 | $0.20 |
| 116 | Muse Spark 1.3 | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 117 | Muse Spark 1.3 Contributor | meta | 1.0M | ~1K | $0.10 | $0.20 |
| 118 | Muse Spark Open | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 119 | Muse Wonder | meta | 1.0M | ~1K | $4.00 | $20.00 |
| 120 | Nemotron 3 Super | NVIDIA | 1.0M | ~1K | $0.07 | $0.40 |
| 121 | Nemotron 3.5 Super VL | NVIDIA | 1.0M | ~1K | $0.15 | $0.50 |
| 122 | Pareto 26.10 | unbiased | 1.0M | ~1K | $0.80 | $3.20 |
| 123 | Pareto Latest | ~unbiased | 1.0M | ~1K | $0.80 | $3.20 |
| 124 | Particle-1 | particle-ai | 1.0M | ~1K | $0.05 | $0.50 |
| 125 | Qwen3.8 2.4T A95B | Alibaba | 1.0M | ~1K | $2.00 | $6.00 |
| 126 | ricursiveAI/Ripple-65B-Preview | ricursiveai | 1.0M | ~1K | $0.20 | $0.60 |
| 127 | Step 5 Preview | StepFun | 1.0M | ~1K | $1.00 | $2.70 |
| 128 | GPT-4.1 | OpenAI | 1.0M | ~1K | $2.00 | $8.00 |
| 129 | GPT-4.1 (batch) | OpenAI | 1.0M | ~1K | $1.00 | $4.00 |
| 130 | GPT-4.1 Mini | OpenAI | 1.0M | ~1K | $0.40 | $1.60 |
| 131 | GPT-4.1 Mini (batch) | OpenAI | 1.0M | ~1K | $0.20 | $0.80 |
| 132 | GPT-4.1 Nano | OpenAI | 1.0M | ~1K | $0.10 | $0.40 |
| 133 | GPT-4.1 Nano (batch) | OpenAI | 1.0M | ~1K | $0.05 | $0.20 |
| 134 | Palmyra X5 | Writer | 1.0M | ~1K | $0.60 | $6.00 |
| 135 | Qwen3.8 27B | Alibaba | 1.0M | ~1K | $0.15 | $1.88 |
| 136 | Claude Fable 5 | Anthropic | 1M | ~1K | $10.00 | $50.00 |
| 137 | Claude Fable 5 (batch) | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 138 | Claude Fable 5.1 | Anthropic | 1M | ~1K | $10.00 | $50.00 |
| 139 | Claude Fable 5.1 (batch) | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 140 | Claude Fable Latest | ~anthropic | 1M | ~1K | $10.00 | $50.00 |
| 141 | Claude Haiku 5.5 | Anthropic | 1M | ~1K | $0.10 | $0.50 |
| 142 | Claude Haiku 5.5 (batch) | Anthropic | 1M | ~1K | $0.05 | $0.25 |
| 143 | Claude Haiku Latest | ~anthropic | 1M | ~1K | $0.10 | $0.50 |
| 144 | Claude Opus 4.6 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 145 | Claude Opus 4.6 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 146 | Claude Opus 4.7 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 147 | Claude Opus 4.7 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 148 | Claude Opus 4.8 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 149 | Claude Opus 4.8 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 150 | Claude Opus 5 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 151 | Claude Opus 5 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 152 | Claude Opus 5.5 | Anthropic | 1M | ~1K | $4.00 | $20.00 |
| 153 | Claude Opus 5.5 (batch) | Anthropic | 1M | ~1K | $2.00 | $10.00 |
| 154 | Claude Opus Latest | ~anthropic | 1M | ~1K | $4.00 | $20.00 |
| 155 | Claude Sonnet 4.5 | Anthropic | 1M | ~1K | $3.00 | $15.00 |
| 156 | Claude Sonnet 4.5 (batch) | Anthropic | 1M | ~1K | $1.50 | $7.50 |
| 157 | Claude Sonnet 4.6 | Anthropic | 1M | ~1K | $3.00 | $15.00 |
| 158 | Claude Sonnet 4.6 (batch) | Anthropic | 1M | ~1K | $1.50 | $7.50 |
| 159 | Claude Sonnet 5 | Anthropic | 1M | ~1K | $2.00 | $10.00 |
| 160 | Claude Sonnet 5 (batch) | Anthropic | 1M | ~1K | $1.00 | $5.00 |
| 161 | Claude Sonnet 5.5 | Anthropic | 1M | ~1K | $2.00 | $10.00 |
| 162 | Claude Sonnet 5.5 (batch) | Anthropic | 1M | ~1K | $1.00 | $5.00 |
| 163 | Claude Sonnet Latest | ~anthropic | 1M | ~1K | $2.00 | $10.00 |
| 164 | Extract | scaledown | 1M | ~1K | $0.04 | Free |
| 165 | Fugu Max | sakana | 1M | ~1K | $2.00 | $6.00 |
| 166 | Fugu Ultra | sakana | 1M | ~1K | $5.00 | $30.00 |
| 167 | Fugu Ultra v2 | sakana | 1M | ~1K | $5.00 | $30.00 |
| 168 | GLM 5.3 Prime | Zhipu AI | 1M | ~1K | $2.80 | $8.80 |
| 169 | Grok 4.3 | xAI | 1M | ~1K | $1.25 | $2.50 |
| 170 | Grok 4.3 (batch) | xAI | 1M | ~1K | $1.00 | $2.00 |
| 171 | Jev Router | typesafe | 1M | ~1K | $-1000000.0000 | $-1000000.0000 |
| 172 | Ling 3.1 Flash | inclusionai | 1M | ~1K | $0.07 | $0.22 |
| 173 | Mercury 3 | Inception | 1M | ~1K | $0.10 | $0.35 |
| 174 | MiMo-V2.5 | Xiaomi | 1M | ~1K | $0.40 | $2.00 |
| 175 | MiniMax M1 | MiniMax | 1M | ~1K | $0.55 | $2.20 |
| 176 | Nemotron 3 Ultra (free) | NVIDIA | 1M | ~1K | Free | Free |
| 177 | Nemotron 3.5 Lightning (free) | NVIDIA | 1M | ~1K | Free | Free |
| 178 | Nemotron 3.5 Super VL (free) | NVIDIA | 1M | ~1K | Free | Free |
| 179 | Nova 2 Lite | Amazon | 1M | ~1K | $0.30 | $2.50 |
| 180 | Nova Premier 1.0 | Amazon | 1M | ~1K | $2.50 | $12.50 |
| 181 | Qwen-Plus | Alibaba | 1M | ~1K | $0.26 | $0.78 |
| 182 | Qwen3 Coder Flash | Alibaba | 1M | ~1K | $0.20 | $0.97 |
| 183 | Qwen3.5 Plus 2026-02-15 | Alibaba | 1M | ~1K | $0.26 | $1.56 |
| 184 | Qwen3.5 Plus 2026-04-20 | Alibaba | 1M | ~1K | $0.30 | $1.80 |
| 185 | Qwen3.5-Flash | Alibaba | 1M | ~1K | $0.07 | $0.26 |
| 186 | Qwen3.6 Flash | Alibaba | 1M | ~1K | $0.19 | $1.13 |
| 187 | Qwen3.6 Plus | Alibaba | 1M | ~1K | $0.33 | $1.95 |
| 188 | Qwen3.7 Flash | Alibaba | 1M | ~1K | $0.03 | $0.13 |
| 189 | Qwen3.7 Max | Alibaba | 1M | ~1K | $1.48 | $4.42 |
| 190 | Qwen3.7 Plus | Alibaba | 1M | ~1K | $0.32 | $1.28 |
| 191 | Qwen3.8 Flash | Alibaba | 1M | ~1K | $0.15 | $0.47 |
| 192 | Qwen3.8 Max (0902) | Alibaba | 1M | ~1K | $2.00 | $6.00 |
| 193 | Qwen3.8 Max Prime | Alibaba | 1M | ~1K | $4.00 | $12.00 |
| 194 | Qwen3.8 Omni Flash | Alibaba | 1M | ~1K | $0.15 | $0.47 |
| 195 | Summarize | scaledown | 1M | ~1K | $0.04 | Free |
| 196 | Switchyard | NVIDIA | 1M | ~1K | $-1000000.0000 | $-1000000.0000 |
200K+ Tokens
(133 models)Extended context models ideal for long documents, legal contracts, research papers, and multi-file code analysis.
| # | Model | Provider | Context Window | Pages | Input / 1M | Output / 1M |
|---|---|---|---|---|---|---|
| 1 | Inkling | thinkingmachines | 524K | ~699 | $1.00 | $4.05 |
| 2 | Inkling Small | thinkingmachines | 524K | ~699 | $0.45 | $1.20 |
| 3 | Llama 4 Maverick | Meta | 524K | ~699 | $0.35 | $1.00 |
| 4 | Solar Mini 4 | Upstage | 524K | ~699 | $0.05 | $0.20 |
| 5 | Solar Pro 4 | Upstage | 524K | ~699 | $0.15 | $0.60 |
| 6 | Dots3-Note Preview (free) | dots-studio | 512K | ~683 | Free | Free |
| 7 | Grok 4.5 | xAI | 500K | ~667 | $2.00 | $6.00 |
| 8 | Grok 4.6 | xAI | 500K | ~667 | $2.00 | $6.00 |
| 9 | Grok 4.6 (batch) | xAI | 500K | ~667 | $1.60 | $4.80 |
| 10 | Grok 4.7 | xAI | 500K | ~667 | $2.00 | $6.00 |
| 11 | Grok 4.7 (batch) | xAI | 500K | ~667 | $1.60 | $4.80 |
| 12 | Grok Latest | ~x-ai | 500K | ~667 | $2.00 | $6.00 |
| 13 | GPT Chat Latest | OpenAI | 400K | ~533 | $5.00 | $30.00 |
| 14 | GPT Mini Latest | ~openai | 400K | ~533 | $0.75 | $4.50 |
| 15 | GPT-5 | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 16 | GPT-5 (batch) | OpenAI | 400K | ~533 | $0.63 | $5.00 |
| 17 | GPT-5 Image | OpenAI | 400K | ~533 | $10.00 | $10.00 |
| 18 | GPT-5 Image Mini | OpenAI | 400K | ~533 | $2.50 | $2.00 |
| 19 | GPT-5 Mini | OpenAI | 400K | ~533 | $0.25 | $2.00 |
| 20 | GPT-5 Mini (batch) | OpenAI | 400K | ~533 | $0.13 | $1.00 |
| 21 | GPT-5 Nano | OpenAI | 400K | ~533 | $0.05 | $0.40 |
| 22 | GPT-5 Nano (batch) | OpenAI | 400K | ~533 | $0.02 | $0.20 |
| 23 | GPT-5 Pro | OpenAI | 400K | ~533 | $15.00 | $120.00 |
| 24 | GPT-5 Pro (batch) | OpenAI | 400K | ~533 | $7.50 | $60.00 |
| 25 | GPT-5.1 | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 26 | GPT-5.1 (batch) | OpenAI | 400K | ~533 | $0.63 | $5.00 |
| 27 | GPT-5.1-Codex | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 28 | GPT-5.1-Codex-Max | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 29 | GPT-5.1-Codex-Mini | OpenAI | 400K | ~533 | $0.25 | $2.00 |
| 30 | GPT-5.2 | OpenAI | 400K | ~533 | $1.75 | $14.00 |
| 31 | GPT-5.2 (batch) | OpenAI | 400K | ~533 | $0.88 | $7.00 |
| 32 | GPT-5.2 Pro | OpenAI | 400K | ~533 | $21.00 | $168.00 |
| 33 | GPT-5.2 Pro (batch) | OpenAI | 400K | ~533 | $10.50 | $84.00 |
| 34 | GPT-5.2-Codex | OpenAI | 400K | ~533 | $1.75 | $14.00 |
| 35 | GPT-5.3-Codex | OpenAI | 400K | ~533 | $1.75 | $14.00 |
| 36 | GPT-5.4 Mini | OpenAI | 400K | ~533 | $0.75 | $4.50 |
| 37 | GPT-5.4 Mini (batch) | OpenAI | 400K | ~533 | $0.38 | $2.25 |
| 38 | GPT-5.4 Nano | OpenAI | 400K | ~533 | $0.20 | $1.25 |
| 39 | GPT-5.4 Nano (batch) | OpenAI | 400K | ~533 | $0.10 | $0.63 |
| 40 | Nova Lite 1.0 | Amazon | 300K | ~400 | $0.06 | $0.24 |
| 41 | Nova Pro 1.0 | Amazon | 300K | ~400 | $0.80 | $3.20 |
| 42 | GPT-5.4 Image 2 | OpenAI | 272K | ~363 | $8.00 | $15.00 |
| 43 | Aion 3.5 | aion-labs | 262K | ~350 | $3.00 | $6.00 |
| 44 | Aion 3.5 Mini | aion-labs | 262K | ~350 | $0.70 | $1.40 |
| 45 | Devstral 2 2512 | Mistral AI | 262K | ~350 | $0.40 | $2.00 |
| 46 | Falcon-H1-Arabic 34B Instruct | TII | 262K | ~350 | Free | Free |
| 47 | Falcon-H1-Arabic 7B Instruct | TII | 262K | ~350 | Free | Free |
| 48 | Flint (free) | recursive | 262K | ~350 | Free | Free |
| 49 | Gemma 4 26B A4B | 262K | ~350 | $0.09 | $0.30 | |
| 50 | Gemma 4 26B A4B (free) | 262K | ~350 | Free | Free | |
| 51 | Gemma 4 31B | 262K | ~350 | $0.20 | $0.40 | |
| 52 | Gemma 4 31B (free) | 262K | ~350 | Free | Free | |
| 53 | Glimpse | elorian | 262K | ~350 | $0.60 | $3.00 |
| 54 | Hy3 | Tencent | 262K | ~350 | $0.13 | $0.53 |
| 55 | Hy3 preview | Tencent | 262K | ~350 | $0.18 | $0.60 |
| 56 | Kimi K2 0905 | Moonshot AI | 262K | ~350 | $0.60 | $2.50 |
| 57 | Kimi K2 Thinking | Moonshot AI | 262K | ~350 | $0.60 | $2.50 |
| 58 | Kimi K2.5 | Moonshot AI | 262K | ~350 | $0.50 | $2.50 |
| 59 | Kimi K2.6 | Moonshot AI | 262K | ~350 | $0.65 | $3.41 |
| 60 | Kimi K2.7 Code | Moonshot AI | 262K | ~350 | $0.60 | $3.50 |
| 61 | Ling 3.0 Flash | inclusionai | 262K | ~350 | $0.02 | $0.06 |
| 62 | Ling 3.0 Tiny | inclusionai | 262K | ~350 | $0.01 | $0.04 |
| 63 | Ministral 3 14B 2512 | Mistral AI | 262K | ~350 | $0.20 | $0.20 |
| 64 | Ministral 3 8B 2512 | Mistral AI | 262K | ~350 | $0.15 | $0.15 |
| 65 | Mistral Large 3 2512 | Mistral AI | 262K | ~350 | $0.50 | $1.50 |
| 66 | Mistral Medium 3.5 | Mistral AI | 262K | ~350 | $1.50 | $7.50 |
| 67 | Mistral Medium 3.5 (batch) | Mistral AI | 262K | ~350 | $0.75 | $3.75 |
| 68 | Mistral Small 4 | Mistral AI | 262K | ~350 | $0.15 | $0.60 |
| 69 | Nemotron 3 Nano 30B A3B | NVIDIA | 262K | ~350 | $0.06 | $0.24 |
| 70 | Nemotron 3 Ultra | NVIDIA | 262K | ~350 | $0.60 | $2.40 |
| 71 | Nemotron 3.5 Lightning | NVIDIA | 262K | ~350 | $0.07 | $0.20 |
| 72 | Pareto 26.9 | unbiased | 262K | ~350 | $2.50 | $7.50 |
| 73 | Qwen3 235B A22B Instruct 2507 | Alibaba | 262K | ~350 | $0.14 | $0.80 |
| 74 | Qwen3 30B A3B Instruct 2507 | Alibaba | 262K | ~350 | $0.10 | $0.30 |
| 75 | Qwen3 Coder 30B A3B Instruct | Alibaba | 262K | ~350 | $0.15 | $0.60 |
| 76 | Qwen3 Coder 480B A35B | Alibaba | 262K | ~350 | $0.30 | $1.00 |
| 77 | Qwen3 Coder Next | Alibaba | 262K | ~350 | $0.12 | $0.80 |
| 78 | Qwen3 Next 80B A3B Instruct | Alibaba | 262K | ~350 | $0.09 | $1.10 |
| 79 | Qwen3 VL 235B A22B Instruct | Alibaba | 262K | ~350 | $0.21 | $1.90 |
| 80 | Qwen3 VL 30B A3B Instruct | Alibaba | 262K | ~350 | $0.15 | $0.60 |
| 81 | Qwen3 VL 30B A3B Thinking | Alibaba | 262K | ~350 | $0.29 | $1.00 |
| 82 | Qwen3 VL 8B Instruct | Alibaba | 262K | ~350 | $0.25 | $0.75 |
| 83 | Qwen3.5 397B A17B | Alibaba | 262K | ~350 | $0.50 | $3.60 |
| 84 | Qwen3.5-122B-A10B | Alibaba | 262K | ~350 | $0.26 | $2.08 |
| 85 | Qwen3.5-27B | Alibaba | 262K | ~350 | $0.26 | $2.60 |
| 86 | Qwen3.5-35B-A3B | Alibaba | 262K | ~350 | $0.14 | $1.00 |
| 87 | Qwen3.5-9B | Alibaba | 262K | ~350 | $0.17 | $0.25 |
| 88 | Qwen3.6 27B | Alibaba | 262K | ~350 | $0.45 | $2.70 |
| 89 | Qwen3.6 35B A3B | Alibaba | 262K | ~350 | $0.10 | $0.90 |
| 90 | Qwen3.7 Plus (batch) | Alibaba | 262K | ~350 | $0.23 | $0.92 |
| 91 | Sakana Namazu | sakana | 262K | ~350 | $0.95 | $4.00 |
| 92 | Seed 1.6 | ByteDance | 262K | ~350 | $0.25 | $2.00 |
| 93 | Seed 1.6 Flash | ByteDance | 262K | ~350 | $0.07 | $0.30 |
| 94 | Seed 2.1 Turbo | ByteDance | 262K | ~350 | $0.50 | $2.50 |
| 95 | Seed-2.0-Code | ByteDance | 262K | ~350 | $0.50 | $3.00 |
| 96 | Seed-2.0-Lite | ByteDance | 262K | ~350 | $0.25 | $2.00 |
| 97 | Seed-2.0-Mini | ByteDance | 262K | ~350 | $0.10 | $0.40 |
| 98 | Step 3.5 Flash | StepFun | 262K | ~350 | $0.10 | $0.30 |
| 99 | Step 3.7 Flash | StepFun | 262K | ~350 | $0.20 | $1.15 |
| 100 | Ternary Bonsai 2 27B | prism-ml | 262K | ~350 | $0.07 | $0.50 |
| 101 | Ternary Bonsai 2 9B | prism-ml | 262K | ~350 | $0.08 | $0.13 |
| 102 | Xing4.0 29B A4B (free) | xingchen-agi | 262K | ~350 | Free | Free |
| 103 | Mercury 2.5 | Inception | 260K | ~347 | $0.04 | $0.15 |
| 104 | Codestral 2508 | Mistral AI | 256K | ~341 | $0.30 | $0.90 |
| 105 | Command A | Cohere | 256K | ~341 | $2.50 | $10.00 |
| 106 | Grok Build 0.1 | xAI | 256K | ~341 | $1.00 | $2.00 |
| 107 | Mistral Small 3.2 24B | Mistral AI | 256K | ~341 | $0.07 | $0.20 |
| 108 | Nemotron 3 Nano Omni (free) | NVIDIA | 256K | ~341 | Free | Free |
| 109 | North Mini Code (free) | Cohere | 256K | ~341 | Free | Free |
| 110 | GLM 4.6 | Zhipu AI | 205K | ~273 | $0.50 | $2.00 |
| 111 | GLM 4.7 | Zhipu AI | 205K | ~273 | $0.60 | $2.20 |
| 112 | GLM 5 | Zhipu AI | 205K | ~273 | $1.00 | $3.20 |
| 113 | GLM 5.1 | Zhipu AI | 205K | ~273 | $1.40 | $4.40 |
| 114 | MiniMax M2.5 | MiniMax | 205K | ~273 | $0.27 | $0.95 |
| 115 | MiniMax M2.7 | MiniMax | 205K | ~273 | $0.21 | $0.84 |
| 116 | GLM 5 Turbo | Zhipu AI | 203K | ~270 | $1.20 | $4.00 |
| 117 | GLM 5V Turbo | Zhipu AI | 203K | ~270 | $1.20 | $4.00 |
| 118 | Claude Haiku 4.5 | Anthropic | 200K | ~267 | $1.00 | $5.00 |
| 119 | Claude Haiku 4.5 (batch) | Anthropic | 200K | ~267 | $0.50 | $2.50 |
| 120 | Claude Opus 4.1 | Anthropic | 200K | ~267 | $15.00 | $75.00 |
| 121 | Claude Opus 4.1 (batch) | Anthropic | 200K | ~267 | $7.50 | $37.50 |
| 122 | Claude Opus 4.5 | Anthropic | 200K | ~267 | $5.00 | $25.00 |
| 123 | Claude Opus 4.5 (batch) | Anthropic | 200K | ~267 | $2.50 | $12.50 |
| 124 | Composer 2 | Cursor | 200K | ~267 | $0.50 | $2.50 |
| 125 | Composer 2 Fast | Cursor | 200K | ~267 | $1.50 | $7.50 |
| 126 | GLM 4.7 Flash | Zhipu AI | 200K | ~267 | $0.06 | $0.40 |
| 127 | o3 | OpenAI | 200K | ~267 | $2.00 | $8.00 |
| 128 | o3 (batch) | OpenAI | 200K | ~267 | $1.00 | $4.00 |
| 129 | o3 Mini (batch) | OpenAI | 200K | ~267 | $0.55 | $2.20 |
| 130 | o3 Pro | OpenAI | 200K | ~267 | $20.00 | $80.00 |
| 131 | o4 Mini (batch) | OpenAI | 200K | ~267 | $0.55 | $2.20 |
| 132 | Sonar Pro | Perplexity | 200K | ~267 | $3.00 | $15.00 |
| 133 | Sonar Pro Search | Perplexity | 200K | ~267 | $3.00 | $15.00 |
128K Tokens
(72 models)The current standard for frontier models. Sufficient for most production use cases, including long conversations and medium-length documents.
| # | Model | Provider | Context Window | Pages | Input / 1M | Output / 1M |
|---|---|---|---|---|---|---|
| 1 | Command A+ | Cohere | 192K | ~256 | $0.30 | $1.50 |
| 2 | DeepSeek V3 | DeepSeek | 164K | ~218 | $0.32 | $0.89 |
| 3 | DeepSeek V3 0324 | DeepSeek | 164K | ~218 | $0.29 | $1.14 |
| 4 | DeepSeek V3.1 | DeepSeek | 164K | ~218 | $0.25 | $0.95 |
| 5 | DeepSeek V3.1 Terminus | DeepSeek | 164K | ~218 | $0.27 | $1.00 |
| 6 | DeepSeek V3.2 | DeepSeek | 164K | ~218 | $0.26 | $0.38 |
| 7 | DeepSeek V3.2 Exp | DeepSeek | 164K | ~218 | $0.27 | $0.41 |
| 8 | Llama Guard 4 12B | Meta | 164K | ~218 | $0.18 | $0.18 |
| 9 | R1 0528 | DeepSeek | 164K | ~218 | $0.50 | $2.15 |
| 10 | Aion-2.0 | aion-labs | 131K | ~175 | $0.80 | $1.60 |
| 11 | Aion-3.0 | aion-labs | 131K | ~175 | $3.00 | $6.00 |
| 12 | Aion-3.0-Mini | aion-labs | 131K | ~175 | $0.70 | $1.40 |
| 13 | Falcon-H1-Arabic 3B Instruct | TII | 131K | ~175 | Free | Free |
| 14 | Gemini Omni 1.1 Flash | 131K | ~175 | $1.50 | $9.00 | |
| 15 | Gemini Omni 1.2 Flash | 131K | ~175 | $1.50 | $9.00 | |
| 16 | Gemma 3 12B | 131K | ~175 | $0.05 | $0.15 | |
| 17 | Gemma 3 27B | 131K | ~175 | $0.08 | $0.35 | |
| 18 | Gemma 3 4B | 131K | ~175 | $0.05 | $0.10 | |
| 19 | GLM 4.5 | Zhipu AI | 131K | ~175 | $0.60 | $2.20 |
| 20 | GLM 4.5 Air | Zhipu AI | 131K | ~175 | $0.13 | $0.85 |
| 21 | GLM 4.6V | Zhipu AI | 131K | ~175 | $0.30 | $0.90 |
| 22 | gpt-oss-120b | OpenAI | 131K | ~175 | $0.02 | $0.09 |
| 23 | gpt-oss-120b (batch) | OpenAI | 131K | ~175 | $0.03 | $0.14 |
| 24 | gpt-oss-20b | OpenAI | 131K | ~175 | $0.03 | $0.13 |
| 25 | gpt-oss-20b (batch) | OpenAI | 131K | ~175 | $0.02 | $0.11 |
| 26 | gpt-oss-safeguard-20b | OpenAI | 131K | ~175 | $0.07 | $0.30 |
| 27 | Granite 4.2 8B | IBM | 131K | ~175 | $0.06 | $0.25 |
| 28 | Hunyuan A13B Instruct | Tencent | 131K | ~175 | $0.14 | $0.57 |
| 29 | Kimi K2 0711 | Moonshot AI | 131K | ~175 | $0.57 | $2.30 |
| 30 | Ling 3.0 Flash VL | inclusionai | 131K | ~175 | $0.06 | $0.18 |
| 31 | Llama 3.1 70B Instruct | Meta | 131K | ~175 | $0.72 | $0.72 |
| 32 | Llama 3.1 8B Instruct | Meta | 131K | ~175 | $0.05 | $0.08 |
| 33 | Llama 3.2 3B Instruct | Meta | 131K | ~175 | $0.05 | $0.34 |
| 34 | Llama 3.3 70B Instruct | Meta | 131K | ~175 | $0.59 | $0.79 |
| 35 | Ministral 3 3B 2512 | Mistral AI | 131K | ~175 | $0.10 | $0.10 |
| 36 | Mistral Large 2407 | Mistral AI | 131K | ~175 | $2.00 | $6.00 |
| 37 | Mistral Medium 3 | Mistral AI | 131K | ~175 | $0.40 | $2.00 |
| 38 | Mistral Medium 3.1 | Mistral AI | 131K | ~175 | $0.40 | $2.00 |
| 39 | Mistral Nemo | Mistral AI | 131K | ~175 | $0.03 | $0.03 |
| 40 | Muse Glimmer 30B | meta | 131K | ~175 | $0.30 | $1.20 |
| 41 | Nano Banana 2 (Gemini 3.1 Flash Image) | 131K | ~175 | $0.50 | $3.00 | |
| 42 | Nano Banana Pro (Gemini 3 Pro Image) | 131K | ~175 | $2.00 | $12.00 | |
| 43 | Nemotron 3.5 Content Safety | NVIDIA | 131K | ~175 | $0.20 | $0.20 |
| 44 | Qwen3 32B | Alibaba | 131K | ~175 | $0.08 | $0.28 |
| 45 | Command R (08-2024) | Cohere | 128K | ~171 | $0.15 | $0.60 |
| 46 | Command R+ (08-2024) | Cohere | 128K | ~171 | $2.50 | $10.00 |
| 47 | Command R7B (12-2024) | Cohere | 128K | ~171 | $0.04 | $0.15 |
| 48 | GPT Audio | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 49 | GPT Audio Mini | OpenAI | 128K | ~171 | $0.60 | $2.40 |
| 50 | GPT-4 Turbo (batch) | OpenAI | 128K | ~171 | $5.00 | $15.00 |
| 51 | GPT-4o | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 52 | GPT-4o (2024-05-13) | OpenAI | 128K | ~171 | $5.00 | $15.00 |
| 53 | GPT-4o (2024-08-06) | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 54 | GPT-4o (2024-11-20) | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 55 | GPT-4o (batch) | OpenAI | 128K | ~171 | $1.25 | $5.00 |
| 56 | GPT-4o-mini | OpenAI | 128K | ~171 | $0.15 | $0.60 |
| 57 | GPT-4o-mini (2024-07-18) | OpenAI | 128K | ~171 | $0.15 | $0.60 |
| 58 | GPT-4o-mini (batch) | OpenAI | 128K | ~171 | $0.07 | $0.30 |
| 59 | GPT-5.2 Chat | OpenAI | 128K | ~171 | $1.75 | $14.00 |
| 60 | LFM2.5-2.6B | Liquid AI | 128K | ~171 | $0.35 | $0.50 |
| 61 | LFM2.5-24B-A2B | Liquid AI | 128K | ~171 | $0.05 | $0.70 |
| 62 | Mercury 2 | Inception | 128K | ~171 | $0.25 | $0.75 |
| 63 | Mistral Large | Mistral AI | 128K | ~171 | $2.00 | $6.00 |
| 64 | Mistral Small 3.1 24B | Mistral AI | 128K | ~171 | $0.35 | $0.55 |
| 65 | Nova Micro 1.0 | Amazon | 128K | ~171 | $0.04 | $0.14 |
| 66 | Qwen2.5 VL 72B Instruct | Alibaba | 128K | ~171 | $0.80 | $1.00 |
| 67 | Qwen3 235B A22B Thinking 2507 | Alibaba | 128K | ~171 | $0.45 | $3.50 |
| 68 | Schematron V2 Small | inference-net | 128K | ~171 | $0.05 | $0.23 |
| 69 | Schematron V2 Turbo | inference-net | 128K | ~171 | $0.03 | $0.15 |
| 70 | Sonar Deep Research | Perplexity | 128K | ~171 | $2.00 | $8.00 |
| 71 | Sonar Reasoning Pro | Perplexity | 128K | ~171 | $2.00 | $8.00 |
| 72 | UI-TARS 7B | ByteDance | 128K | ~171 | $0.10 | $0.20 |
32K–64K Tokens
(27 models)Moderate context windows suitable for shorter documents, code files, and focused conversations.
| # | Model | Provider | Context Window | Pages | Input / 1M | Output / 1M |
|---|---|---|---|---|---|---|
| 1 | Sonar | Perplexity | 127K | ~169 | $1.00 | $1.00 |
| 2 | GLM 4.5V | Zhipu AI | 66K | ~87 | $0.60 | $1.80 |
| 3 | LFM2.5-2.6B (free) | Liquid AI | 66K | ~87 | Free | Free |
| 4 | Mixtral 8x22B Instruct | Mistral AI | 66K | ~87 | $2.00 | $6.00 |
| 5 | Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 66K | ~87 | $0.50 | $3.00 | |
| 6 | Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 66K | ~87 | $0.25 | $1.50 | |
| 7 | Nano Banana 2.1 | 66K | ~87 | $1.50 | $7.50 | |
| 8 | Nano Banana Pro (Gemini 3 Pro Image Preview) | 66K | ~87 | $2.00 | $12.00 | |
| 9 | Reka Flash 3 | rekaai | 66K | ~87 | $0.10 | $0.20 |
| 10 | Llama 3.2 1B Instruct | Meta | 60K | ~80 | $0.03 | $0.20 |
| 11 | Qwen3 14B | Alibaba | 41K | ~55 | $0.12 | $0.24 |
| 12 | Qwen3 30B A3B | Alibaba | 41K | ~55 | $0.12 | $0.50 |
| 13 | Perceptron Mk1.5 | perceptron | 37K | ~49 | $0.15 | $1.50 |
| 14 | Falcon Arabic 7B Instruct | TII | 33K | ~44 | Free | Free |
| 15 | Falcon Mamba 7B Instruct | TII | 33K | ~44 | Free | Free |
| 16 | Falcon3 10B Instruct | TII | 33K | ~44 | Free | Free |
| 17 | Falcon3 7B Instruct | TII | 33K | ~44 | Free | Free |
| 18 | Mistral Small 3 | Mistral AI | 33K | ~44 | $0.05 | $0.08 |
| 19 | Nano Banana (Gemini 2.5 Flash Image) | 33K | ~44 | $0.30 | $2.50 | |
| 20 | Perceptron Mk1 | perceptron | 33K | ~44 | $0.15 | $1.50 |
| 21 | Qwen2.5 72B Instruct | Alibaba | 33K | ~44 | $0.36 | $0.40 |
| 22 | Qwen2.5 7B Instruct | Alibaba | 33K | ~44 | $0.10 | $0.20 |
| 23 | Qwen2.5 Coder 32B Instruct | Alibaba | 33K | ~44 | $0.66 | $1.00 |
| 24 | Saba | Mistral AI | 33K | ~44 | $0.20 | $0.60 |
| 25 | Voxtral Small 24B 2507 | Mistral AI | 33K | ~44 | $0.10 | $0.30 |
| 26 | Moondream 3 Preview | moondream | 32K | ~43 | $0.30 | $2.50 |
| 27 | Moondream 3.1 | moondream | 32K | ~43 | $0.30 | $2.50 |
What Is a Context Window and Why Does It Matter?
Context window = working memory
A model's context window is the total number of tokens (roughly words) it can process in a single request. This includes both your input prompt and the model's output. A model with a 128K context window can process about 170 pages of text at once, while a 1M-token model can handle roughly 1,300 pages -- enough for entire books or large codebases.
Larger context enables new use cases
With small context windows (under 32K), you must chunk documents and use retrieval-augmented generation (RAG). Large context models eliminate this complexity for many workloads: analyzing full legal contracts, reviewing entire repositories, summarizing research paper collections, or maintaining very long conversations with full history retained.
Context size vs. effective recall
Not all context is created equal. Some models perform well on "needle in a haystack" tests at their full context length, while others degrade on information retrieval when prompts get very long. The advertised context window is the maximum, but effective performance may vary. Check our leaderboard for quality scores that account for real-world performance.
Cost implications of large context
Using a large context window means sending more tokens per request, which increases cost. For example, filling a 1M-token context at $3/1M input tokens costs $3 per request. For cost-sensitive workloads, consider whether RAG with a smaller context model might be more efficient than filling a large context window end to end.
Explore More
Dive deeper into model capabilities, compare context windows side by side, or see overall rankings across all dimensions.
Frequently Asked Questions
A large context window model can process long inputs - from 128K tokens (about 100 pages) up to 2M tokens (about 1,500 pages). This allows analyzing entire codebases, long documents, or extensive conversation histories in a single request.
Large context models excel when you need the AI to reason across an entire document at once. RAG (Retrieval-Augmented Generation) is better for searching across massive document collections. Large context is simpler to implement but costs more per request.
No. While many models advertise 1M+ token context windows, their effective recall can vary significantly. Some models lose accuracy when important information is buried in the middle of very long contexts. Our rankings account for practical performance, not just advertised limits.