Large Context Window AI Models
Compare 429 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.
170
1M+ Tokens
153
200K+ Tokens
79
128K Tokens
27
32K–64K Tokens
2M
Largest Context
429
Models (32K+)
548K
Average Context
1M+ Tokens
(170 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 | DeepSeek V4 Flash 0731 | DeepSeek | 1.3M | ~2K | $0.03 | $0.32 |
| 4 | DeepSeek V4 Flash Latest | ~deepseek | 1.3M | ~2K | $0.03 | $0.32 |
| 5 | GLM 5.3 | Zhipu AI | 1.3M | ~2K | $1.40 | $4.40 |
| 6 | GLM 5.3 Flash | Zhipu AI | 1.3M | ~2K | $0.04 | $0.60 |
| 7 | GLM Flash Latest | ~z-ai | 1.3M | ~2K | $0.04 | $0.14 |
| 8 | GLM Latest | ~z-ai | 1.3M | ~2K | $0.56 | $1.76 |
| 9 | Llama 4 Scout | Meta | 1.3M | ~2K | $0.10 | $0.30 |
| 10 | GPT Astra Latest | ~openai | 1.1M | ~1K | $10.00 | $50.00 |
| 11 | GPT Luna Latest | ~openai | 1.1M | ~1K | $0.10 | $0.50 |
| 12 | GPT Sol Latest | ~openai | 1.1M | ~1K | $2.00 | $10.00 |
| 13 | GPT Terra Latest | ~openai | 1.1M | ~1K | $2.00 | $12.00 |
| 14 | GPT-5.4 | OpenAI | 1.1M | ~1K | $2.50 | $15.00 |
| 15 | GPT-5.4 (batch) | OpenAI | 1.1M | ~1K | $1.25 | $7.50 |
| 16 | GPT-5.4 Pro | OpenAI | 1.1M | ~1K | $30.00 | $180.00 |
| 17 | GPT-5.4 Pro (batch) | OpenAI | 1.1M | ~1K | $15.00 | $90.00 |
| 18 | GPT-5.5 | OpenAI | 1.1M | ~1K | $5.00 | $30.00 |
| 19 | GPT-5.5 (batch) | OpenAI | 1.1M | ~1K | $2.50 | $15.00 |
| 20 | GPT-5.5 Pro | OpenAI | 1.1M | ~1K | $30.00 | $180.00 |
| 21 | GPT-5.5 Pro (batch) | OpenAI | 1.1M | ~1K | $15.00 | $90.00 |
| 22 | GPT-5.6 Luna | OpenAI | 1.1M | ~1K | $0.20 | $1.20 |
| 23 | GPT-5.6 Luna (batch) | OpenAI | 1.1M | ~1K | $0.10 | $0.60 |
| 24 | GPT-5.6 Luna Pro | OpenAI | 1.1M | ~1K | $0.20 | $1.20 |
| 25 | GPT-5.6 Luna Pro (batch) | OpenAI | 1.1M | ~1K | $0.10 | $0.60 |
| 26 | GPT-5.6 Sol | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 27 | GPT-5.6 Sol (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 28 | GPT-5.6 Sol Pro | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 29 | GPT-5.6 Sol Pro (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 30 | GPT-5.6 Terra | OpenAI | 1.1M | ~1K | $2.00 | $12.00 |
| 31 | GPT-5.6 Terra (batch) | OpenAI | 1.1M | ~1K | $1.00 | $6.00 |
| 32 | GPT-5.6 Terra Pro | OpenAI | 1.1M | ~1K | $2.00 | $12.00 |
| 33 | GPT-5.6 Terra Pro (batch) | OpenAI | 1.1M | ~1K | $1.00 | $6.00 |
| 34 | GPT-6 Astra | OpenAI | 1.1M | ~1K | $10.00 | $50.00 |
| 35 | GPT-6 Astra (batch) | OpenAI | 1.1M | ~1K | $5.00 | $25.00 |
| 36 | GPT-6 Astra Pro | OpenAI | 1.1M | ~1K | $10.00 | $50.00 |
| 37 | GPT-6 Astra Pro (batch) | OpenAI | 1.1M | ~1K | $5.00 | $25.00 |
| 38 | GPT-6 Luna | OpenAI | 1.1M | ~1K | $0.10 | $0.50 |
| 39 | GPT-6 Luna (batch) | OpenAI | 1.1M | ~1K | $0.05 | $0.25 |
| 40 | GPT-6 Luna Pro | OpenAI | 1.1M | ~1K | $0.10 | $0.50 |
| 41 | GPT-6 Luna Pro (batch) | OpenAI | 1.1M | ~1K | $0.05 | $0.25 |
| 42 | GPT-6 Sol | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 43 | GPT-6 Sol (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 44 | GPT-6 Sol Pro | OpenAI | 1.1M | ~1K | $2.00 | $10.00 |
| 45 | GPT-6 Sol Pro (batch) | OpenAI | 1.1M | ~1K | $1.00 | $5.00 |
| 46 | MiMo-V2.5 | Xiaomi | 1.1M | ~1K | $0.14 | $0.28 |
| 47 | MiMo-V2.5-Pro | Xiaomi | 1.1M | ~1K | $0.43 | $0.87 |
| 48 | LongCat 2.0 | Meituan | 1.0M | ~1K | $0.30 | $1.20 |
| 49 | DeepSeek Flash Latest | ~deepseek | 1.0M | ~1K | $0.04 | $0.49 |
| 50 | DeepSeek Pro Latest | ~deepseek | 1.0M | ~1K | $0.35 | $1.05 |
| 51 | DeepSeek V4 Flash 0423 | DeepSeek | 1.0M | ~1K | $0.05 | $0.10 |
| 52 | DeepSeek V4 Flash Vision Exp | DeepSeek | 1.0M | ~1K | $0.22 | $0.66 |
| 53 | DeepSeek V4 Pro 0423 | DeepSeek | 1.0M | ~1K | $0.82 | $1.64 |
| 54 | DeepSeek V4 Pro 0813 | DeepSeek | 1.0M | ~1K | $0.46 | $1.39 |
| 55 | DeepSeek V4.1 Flash | DeepSeek | 1.0M | ~1K | $0.30 | $1.20 |
| 56 | DeepSeek V4.1 Flash (batch) | DeepSeek | 1.0M | ~1K | $0.11 | $0.34 |
| 57 | Ember-1 | fireworks | 1.0M | ~1K | $3.00 | $15.00 |
| 58 | Gemini 2.5 Flash | 1.0M | ~1K | $0.30 | $2.50 | |
| 59 | Gemini 2.5 Flash (batch) | 1.0M | ~1K | $0.15 | $1.25 | |
| 60 | Gemini 2.5 Flash Lite | 1.0M | ~1K | $0.10 | $0.40 | |
| 61 | Gemini 2.5 Flash Lite (batch) | 1.0M | ~1K | $0.05 | $0.20 | |
| 62 | Gemini 2.5 Pro | 1.0M | ~1K | $1.25 | $10.00 | |
| 63 | Gemini 2.5 Pro (batch) | 1.0M | ~1K | $0.63 | $5.00 | |
| 64 | Gemini 2.5 Pro Preview 06-05 | 1.0M | ~1K | $1.25 | $10.00 | |
| 65 | Gemini 3 Flash Preview | 1.0M | ~1K | $0.50 | $3.00 | |
| 66 | Gemini 3 Flash Preview (batch) | 1.0M | ~1K | $0.25 | $1.50 | |
| 67 | Gemini 3.1 Flash Lite | 1.0M | ~1K | $0.25 | $1.50 | |
| 68 | Gemini 3.1 Flash Lite (batch) | 1.0M | ~1K | $0.13 | $0.75 | |
| 69 | Gemini 3.1 Flash Lite Preview | 1.0M | ~1K | $0.25 | $1.50 | |
| 70 | Gemini 3.1 Pro Preview | 1.0M | ~1K | $2.00 | $12.00 | |
| 71 | Gemini 3.1 Pro Preview (batch) | 1.0M | ~1K | $1.00 | $6.00 | |
| 72 | Gemini 3.1 Pro Preview Custom Tools | 1.0M | ~1K | $2.00 | $12.00 | |
| 73 | Gemini 3.5 Flash | 1.0M | ~1K | $1.50 | $9.00 | |
| 74 | Gemini 3.5 Flash (batch) | 1.0M | ~1K | $0.75 | $4.50 | |
| 75 | Gemini 3.5 Flash Lite | 1.0M | ~1K | $0.30 | $2.50 | |
| 76 | Gemini 3.5 Flash Lite (batch) | 1.0M | ~1K | $0.15 | $1.25 | |
| 77 | Gemini 3.6 Flash | 1.0M | ~1K | $0.75 | $3.75 | |
| 78 | Gemini 3.6 Flash (batch) | 1.0M | ~1K | $0.38 | $1.88 | |
| 79 | Gemini 3.7 Flash | 1.0M | ~1K | $0.75 | $3.75 | |
| 80 | Gemini 3.7 Flash (batch) | 1.0M | ~1K | $0.38 | $1.88 | |
| 81 | Gemini 3.8 Flash | 1.0M | ~1K | $0.75 | $3.75 | |
| 82 | Gemini 3.8 Flash (batch) | 1.0M | ~1K | $0.38 | $1.88 | |
| 83 | Gemini Flash Latest | 1.0M | ~1K | $0.75 | $3.75 | |
| 84 | Gemini Pro Latest | 1.0M | ~1K | $2.00 | $12.00 | |
| 85 | GLM 5.2 | Zhipu AI | 1.0M | ~1K | $0.65 | $2.04 |
| 86 | GLM 5.3 (batch) | Zhipu AI | 1.0M | ~1K | $0.45 | $2.00 |
| 87 | GLM 5.3 Flash (batch) | Zhipu AI | 1.0M | ~1K | $0.06 | $0.20 |
| 88 | GLM 5.3 FlashX | Zhipu AI | 1.0M | ~1K | $0.37 | $1.25 |
| 89 | Hy4 preview | Tencent | 1.0M | ~1K | $0.83 | $2.50 |
| 90 | Inkling | thinkingmachines | 1.0M | ~1K | $1.00 | $4.05 |
| 91 | Inkling (free) | thinkingmachines | 1.0M | ~1K | Free | Free |
| 92 | Inkling Small | thinkingmachines | 1.0M | ~1K | $0.45 | $1.20 |
| 93 | Inkling Small (free) | thinkingmachines | 1.0M | ~1K | Free | Free |
| 94 | Kimi K3 | Moonshot AI | 1.0M | ~1K | $0.88 | $10.53 |
| 95 | Kimi K3 (batch) | Moonshot AI | 1.0M | ~1K | $2.28 | $11.40 |
| 96 | Kimi Latest | ~moonshotai | 1.0M | ~1K | $0.88 | $10.53 |
| 97 | Laguna S 2.1 | poolside | 1.0M | ~1K | $0.09 | $0.18 |
| 98 | Llama 4 Maverick | Meta | 1.0M | ~1K | $0.19 | $0.65 |
| 99 | Lyria 3 Clip Preview | 1.0M | ~1K | Free | Free | |
| 100 | Lyria 3 Pro Preview | 1.0M | ~1K | Free | Free | |
| 101 | MiMo-V2.6-Flash | Xiaomi | 1.0M | ~1K | $0.14 | $0.28 |
| 102 | MiMo-V2.6-Pro | Xiaomi | 1.0M | ~1K | $0.43 | $0.87 |
| 103 | MiMo-V2.6-Pro-UltraSpeed | Xiaomi | 1.0M | ~1K | $4.35 | $8.70 |
| 104 | MiniMax M3 | MiniMax | 1.0M | ~1K | $0.30 | $1.20 |
| 105 | Muse Spark 1.1 | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 106 | Muse Spark 1.2 | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 107 | Muse Spark 1.2 Contributor | meta | 1.0M | ~1K | $0.10 | $0.20 |
| 108 | Muse Spark 1.3 | meta | 1.0M | ~1K | $1.25 | $4.25 |
| 109 | Muse Spark 1.3 Contributor | meta | 1.0M | ~1K | $0.10 | $0.20 |
| 110 | Qwen3.8 2.4T A95B | Alibaba | 1.0M | ~1K | $2.00 | $6.00 |
| 111 | GPT-4.1 | OpenAI | 1.0M | ~1K | $2.00 | $8.00 |
| 112 | GPT-4.1 (batch) | OpenAI | 1.0M | ~1K | $1.00 | $4.00 |
| 113 | GPT-4.1 Mini | OpenAI | 1.0M | ~1K | $0.40 | $1.60 |
| 114 | GPT-4.1 Mini (batch) | OpenAI | 1.0M | ~1K | $0.20 | $0.80 |
| 115 | GPT-4.1 Nano | OpenAI | 1.0M | ~1K | $0.10 | $0.40 |
| 116 | GPT-4.1 Nano (batch) | OpenAI | 1.0M | ~1K | $0.05 | $0.20 |
| 117 | Palmyra X5 | Writer | 1.0M | ~1K | $0.60 | $6.00 |
| 118 | MiniMax-01 | MiniMax | 1.0M | ~1K | $0.20 | $1.10 |
| 119 | Claude Fable 5 | Anthropic | 1M | ~1K | $10.00 | $50.00 |
| 120 | Claude Fable 5 (batch) | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 121 | Claude Fable 5.1 | Anthropic | 1M | ~1K | $10.00 | $50.00 |
| 122 | Claude Fable 5.1 (batch) | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 123 | Claude Fable Latest | ~anthropic | 1M | ~1K | $10.00 | $50.00 |
| 124 | Claude Opus 4.6 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 125 | Claude Opus 4.6 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 126 | Claude Opus 4.7 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 127 | Claude Opus 4.7 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 128 | Claude Opus 4.8 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 129 | Claude Opus 4.8 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 130 | Claude Opus 5 | Anthropic | 1M | ~1K | $5.00 | $25.00 |
| 131 | Claude Opus 5 (batch) | Anthropic | 1M | ~1K | $2.50 | $12.50 |
| 132 | Claude Opus 5.5 | Anthropic | 1M | ~1K | $4.00 | $20.00 |
| 133 | Claude Opus 5.5 (batch) | Anthropic | 1M | ~1K | $2.00 | $10.00 |
| 134 | Claude Opus Latest | ~anthropic | 1M | ~1K | $4.00 | $20.00 |
| 135 | Claude Sonnet 4.5 | Anthropic | 1M | ~1K | $3.00 | $15.00 |
| 136 | Claude Sonnet 4.5 (batch) | Anthropic | 1M | ~1K | $1.50 | $7.50 |
| 137 | Claude Sonnet 4.6 | Anthropic | 1M | ~1K | $3.00 | $15.00 |
| 138 | Claude Sonnet 4.6 (batch) | Anthropic | 1M | ~1K | $1.50 | $7.50 |
| 139 | Claude Sonnet 5 | Anthropic | 1M | ~1K | $2.00 | $10.00 |
| 140 | Claude Sonnet 5 (batch) | Anthropic | 1M | ~1K | $1.00 | $5.00 |
| 141 | Claude Sonnet Latest | ~anthropic | 1M | ~1K | $2.00 | $10.00 |
| 142 | Fugu Max | sakana | 1M | ~1K | $2.00 | $6.00 |
| 143 | Fugu Ultra | sakana | 1M | ~1K | $5.00 | $30.00 |
| 144 | Fugu Ultra v2 | sakana | 1M | ~1K | $5.00 | $30.00 |
| 145 | GLM 5.3 Prime | Zhipu AI | 1M | ~1K | $2.80 | $8.80 |
| 146 | Grok 4.3 | xAI | 1M | ~1K | $1.25 | $2.50 |
| 147 | Grok 4.3 (batch) | xAI | 1M | ~1K | $1.00 | $2.00 |
| 148 | MiniMax M1 | MiniMax | 1M | ~1K | $0.40 | $2.20 |
| 149 | Nemotron 3 Ultra (free) | NVIDIA | 1M | ~1K | Free | Free |
| 150 | Nemotron 3.5 Lightning (free) | NVIDIA | 1M | ~1K | Free | Free |
| 151 | Nova 2 Lite | Amazon | 1M | ~1K | $0.30 | $2.50 |
| 152 | Nova Premier 1.0 | Amazon | 1M | ~1K | $2.50 | $12.50 |
| 153 | Qwen Plus 0728 | Alibaba | 1M | ~1K | $0.26 | $0.78 |
| 154 | Qwen-Plus | Alibaba | 1M | ~1K | $0.26 | $0.78 |
| 155 | Qwen3 Coder Flash | Alibaba | 1M | ~1K | $0.20 | $0.97 |
| 156 | Qwen3 Coder Plus | Alibaba | 1M | ~1K | $0.65 | $3.25 |
| 157 | Qwen3.5 Plus 2026-02-15 | Alibaba | 1M | ~1K | $0.26 | $1.56 |
| 158 | Qwen3.5 Plus 2026-04-20 | Alibaba | 1M | ~1K | $0.30 | $1.80 |
| 159 | Qwen3.5-Flash | Alibaba | 1M | ~1K | $0.07 | $0.26 |
| 160 | Qwen3.6 Flash | Alibaba | 1M | ~1K | $0.19 | $1.13 |
| 161 | Qwen3.6 Plus | Alibaba | 1M | ~1K | $0.33 | $1.95 |
| 162 | Qwen3.7 Flash | Alibaba | 1M | ~1K | $0.03 | $0.13 |
| 163 | Qwen3.7 Max | Alibaba | 1M | ~1K | $1.48 | $4.42 |
| 164 | Qwen3.7 Plus | Alibaba | 1M | ~1K | $0.32 | $1.28 |
| 165 | Qwen3.8 27B | Alibaba | 1M | ~1K | $0.42 | $3.00 |
| 166 | Qwen3.8 Flash | Alibaba | 1M | ~1K | $0.15 | $0.47 |
| 167 | Qwen3.8 Max (0902) | Alibaba | 1M | ~1K | $2.00 | $6.00 |
| 168 | Qwen3.8 Max Prime | Alibaba | 1M | ~1K | $4.00 | $12.00 |
| 169 | Qwen3.8 Omni Flash | Alibaba | 1M | ~1K | $0.15 | $0.47 |
| 170 | Space Bunny Alpha | stealth | 1M | ~1K | Free | Free |
200K+ Tokens
(153 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 | Solar Mini 4 | Upstage | 524K | ~699 | $0.05 | $0.20 |
| 2 | Solar Pro 4 | Upstage | 524K | ~699 | $0.09 | $0.36 |
| 3 | Dots3-Note Preview (free) | dots-studio | 512K | ~683 | Free | Free |
| 4 | Grok 4.5 | xAI | 500K | ~667 | $2.00 | $6.00 |
| 5 | Grok 4.6 | xAI | 500K | ~667 | $2.00 | $6.00 |
| 6 | Grok 4.7 | xAI | 500K | ~667 | $1.60 | $4.80 |
| 7 | Grok Latest | ~x-ai | 500K | ~667 | $1.60 | $4.80 |
| 8 | GPT Chat Latest | OpenAI | 400K | ~533 | $5.00 | $30.00 |
| 9 | GPT Mini Latest | ~openai | 400K | ~533 | $0.75 | $4.50 |
| 10 | GPT-5 | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 11 | GPT-5 (batch) | OpenAI | 400K | ~533 | $0.63 | $5.00 |
| 12 | GPT-5 Image | OpenAI | 400K | ~533 | $10.00 | $10.00 |
| 13 | GPT-5 Image Mini | OpenAI | 400K | ~533 | $2.50 | $2.00 |
| 14 | GPT-5 Mini | OpenAI | 400K | ~533 | $0.25 | $2.00 |
| 15 | GPT-5 Mini (batch) | OpenAI | 400K | ~533 | $0.13 | $1.00 |
| 16 | GPT-5 Nano | OpenAI | 400K | ~533 | $0.05 | $0.40 |
| 17 | GPT-5 Nano (batch) | OpenAI | 400K | ~533 | $0.02 | $0.20 |
| 18 | GPT-5 Pro | OpenAI | 400K | ~533 | $15.00 | $120.00 |
| 19 | GPT-5 Pro (batch) | OpenAI | 400K | ~533 | $7.50 | $60.00 |
| 20 | GPT-5.1 | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 21 | GPT-5.1 (batch) | OpenAI | 400K | ~533 | $0.63 | $5.00 |
| 22 | GPT-5.1-Codex | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 23 | GPT-5.1-Codex-Max | OpenAI | 400K | ~533 | $1.25 | $10.00 |
| 24 | GPT-5.1-Codex-Mini | OpenAI | 400K | ~533 | $0.25 | $2.00 |
| 25 | GPT-5.2 | OpenAI | 400K | ~533 | $1.75 | $14.00 |
| 26 | GPT-5.2 (batch) | OpenAI | 400K | ~533 | $0.88 | $7.00 |
| 27 | GPT-5.2 Pro | OpenAI | 400K | ~533 | $21.00 | $168.00 |
| 28 | GPT-5.2 Pro (batch) | OpenAI | 400K | ~533 | $10.50 | $84.00 |
| 29 | GPT-5.2-Codex | OpenAI | 400K | ~533 | $1.75 | $14.00 |
| 30 | GPT-5.3-Codex | OpenAI | 400K | ~533 | $1.75 | $14.00 |
| 31 | GPT-5.4 Mini | OpenAI | 400K | ~533 | $0.75 | $4.50 |
| 32 | GPT-5.4 Mini (batch) | OpenAI | 400K | ~533 | $0.38 | $2.25 |
| 33 | GPT-5.4 Nano | OpenAI | 400K | ~533 | $0.20 | $1.25 |
| 34 | GPT-5.4 Nano (batch) | OpenAI | 400K | ~533 | $0.10 | $0.63 |
| 35 | Nova Lite 1.0 | Amazon | 300K | ~400 | $0.06 | $0.24 |
| 36 | Nova Pro 1.0 | Amazon | 300K | ~400 | $0.80 | $3.20 |
| 37 | GPT-5.4 Image 2 | OpenAI | 272K | ~363 | $8.00 | $15.00 |
| 38 | Aion 3.5 | aion-labs | 262K | ~350 | $3.00 | $6.00 |
| 39 | Aion 3.5 Mini | aion-labs | 262K | ~350 | $0.70 | $1.40 |
| 40 | Devstral 2 2512 | Mistral AI | 262K | ~350 | $0.40 | $2.00 |
| 41 | Falcon-H1-Arabic 34B Instruct | TII | 262K | ~350 | Free | Free |
| 42 | Falcon-H1-Arabic 7B Instruct | TII | 262K | ~350 | Free | Free |
| 43 | Gemma 4 26B A4B | 262K | ~350 | $0.09 | $0.30 | |
| 44 | Gemma 4 26B A4B (free) | 262K | ~350 | Free | Free | |
| 45 | Gemma 4 31B | 262K | ~350 | $0.09 | $0.34 | |
| 46 | Gemma 4 31B (free) | 262K | ~350 | Free | Free | |
| 47 | Hy3 | Tencent | 262K | ~350 | $0.13 | $0.53 |
| 48 | Hy3 preview | Tencent | 262K | ~350 | $0.18 | $0.60 |
| 49 | KAT-Coder-Pro V2.5 | Kuaishou | 262K | ~350 | $0.74 | $2.96 |
| 50 | Kimi K2 0905 | Moonshot AI | 262K | ~350 | $0.60 | $2.50 |
| 51 | Kimi K2 Thinking | Moonshot AI | 262K | ~350 | $0.60 | $2.50 |
| 52 | Kimi K2.5 | Moonshot AI | 262K | ~350 | $0.45 | $2.25 |
| 53 | Kimi K2.6 | Moonshot AI | 262K | ~350 | $0.95 | $4.00 |
| 54 | Kimi K2.7 Code | Moonshot AI | 262K | ~350 | $0.66 | $3.30 |
| 55 | Laguna S 2.1 (free) | poolside | 262K | ~350 | Free | Free |
| 56 | Laguna XS 2.1 | poolside | 262K | ~350 | $0.06 | $0.12 |
| 57 | Laguna XS 2.1 (free) | poolside | 262K | ~350 | Free | Free |
| 58 | Ling 3.0 Flash | inclusionai | 262K | ~350 | $0.02 | $0.06 |
| 59 | Ling 3.0 Flash Fin | inclusionai | 262K | ~350 | $0.06 | $0.18 |
| 60 | Ling 3.0 Flash Fin (free) | inclusionai | 262K | ~350 | Free | Free |
| 61 | Ling 3.0 Flash Sante (free) | inclusionai | 262K | ~350 | Free | Free |
| 62 | Ling 3.0 Flash VL | inclusionai | 262K | ~350 | $0.06 | $0.18 |
| 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 | Ministral 3 8B 2512 (batch) | Mistral AI | 262K | ~350 | $0.07 | $0.07 |
| 66 | Mistral Large 3 2512 | Mistral AI | 262K | ~350 | $0.50 | $1.50 |
| 67 | Mistral Large 3 2512 (batch) | Mistral AI | 262K | ~350 | $0.25 | $0.75 |
| 68 | Mistral Medium 3.5 | Mistral AI | 262K | ~350 | $1.50 | $7.50 |
| 69 | Mistral Medium 3.5 (batch) | Mistral AI | 262K | ~350 | $0.75 | $3.75 |
| 70 | Mistral Small 4 | Mistral AI | 262K | ~350 | $0.15 | $0.60 |
| 71 | Mistral Small 4 (batch) | Mistral AI | 262K | ~350 | $0.07 | $0.30 |
| 72 | Nemotron 3 Nano 30B A3B | NVIDIA | 262K | ~350 | $0.05 | $0.20 |
| 73 | Nemotron 3 Super | NVIDIA | 262K | ~350 | $0.08 | $0.45 |
| 74 | Nemotron 3 Super (free) | NVIDIA | 262K | ~350 | Free | Free |
| 75 | Nemotron 3 Ultra | NVIDIA | 262K | ~350 | $0.60 | $2.40 |
| 76 | Nemotron 3.5 Lightning | NVIDIA | 262K | ~350 | $0.08 | $0.20 |
| 77 | Pareto | unbiased | 262K | ~350 | $2.50 | $7.50 |
| 78 | Qwen3 235B A22B Instruct 2507 | Alibaba | 262K | ~350 | $0.09 | $0.35 |
| 79 | Qwen3 30B A3B Instruct 2507 | Alibaba | 262K | ~350 | $0.10 | $0.30 |
| 80 | Qwen3 Coder 30B A3B Instruct | Alibaba | 262K | ~350 | $0.07 | $0.28 |
| 81 | Qwen3 Coder 480B A35B | Alibaba | 262K | ~350 | $0.30 | $1.00 |
| 82 | Qwen3 Coder Next | Alibaba | 262K | ~350 | $0.12 | $0.80 |
| 83 | Qwen3 Max | Alibaba | 262K | ~350 | $0.78 | $3.90 |
| 84 | Qwen3 Max Thinking | Alibaba | 262K | ~350 | $0.78 | $3.90 |
| 85 | Qwen3 Next 80B A3B Instruct | Alibaba | 262K | ~350 | $0.10 | $1.10 |
| 86 | Qwen3 Next 80B A3B Thinking | Alibaba | 262K | ~350 | $0.15 | $1.20 |
| 87 | Qwen3 VL 235B A22B Instruct | Alibaba | 262K | ~350 | $0.21 | $1.90 |
| 88 | Qwen3 VL 30B A3B Instruct | Alibaba | 262K | ~350 | $0.15 | $0.60 |
| 89 | Qwen3 VL 30B A3B Thinking | Alibaba | 262K | ~350 | $0.20 | $2.40 |
| 90 | Qwen3 VL 8B Instruct | Alibaba | 262K | ~350 | $0.12 | $0.45 |
| 91 | Qwen3.5 397B A17B | Alibaba | 262K | ~350 | $0.55 | $3.50 |
| 92 | Qwen3.5-122B-A10B | Alibaba | 262K | ~350 | $0.26 | $2.08 |
| 93 | Qwen3.5-27B | Alibaba | 262K | ~350 | $0.20 | $1.56 |
| 94 | Qwen3.5-35B-A3B | Alibaba | 262K | ~350 | $0.31 | $1.25 |
| 95 | Qwen3.5-9B | Alibaba | 262K | ~350 | $0.10 | $0.15 |
| 96 | Qwen3.6 27B | Alibaba | 262K | ~350 | $0.32 | $2.70 |
| 97 | Qwen3.6 35B A3B | Alibaba | 262K | ~350 | $0.15 | $1.00 |
| 98 | Qwen3.6 Max Preview | Alibaba | 262K | ~350 | $1.03 | $6.16 |
| 99 | Qwen3.8 27B (free) | Alibaba | 262K | ~350 | Free | Free |
| 100 | Sakana Namazu | sakana | 262K | ~350 | $0.95 | $4.00 |
| 101 | Seed 1.6 | ByteDance | 262K | ~350 | $0.25 | $2.00 |
| 102 | Seed 1.6 Flash | ByteDance | 262K | ~350 | $0.07 | $0.30 |
| 103 | Seed 2.1 Turbo | ByteDance | 262K | ~350 | $0.50 | $2.50 |
| 104 | Seed-2.0-Code | ByteDance | 262K | ~350 | $0.50 | $3.00 |
| 105 | Seed-2.0-Lite | ByteDance | 262K | ~350 | $0.25 | $2.00 |
| 106 | Seed-2.0-Mini | ByteDance | 262K | ~350 | $0.10 | $0.40 |
| 107 | Step 3.5 Flash | StepFun | 262K | ~350 | $0.10 | $0.30 |
| 108 | Step 3.7 Flash | StepFun | 262K | ~350 | $0.20 | $1.15 |
| 109 | Ternary Bonsai 2 27B | prism-ml | 262K | ~350 | $0.07 | $0.50 |
| 110 | Trinity Large Thinking | arcee-ai | 262K | ~350 | $0.25 | $0.80 |
| 111 | Mercury 2.5 | Inception | 260K | ~347 | $0.04 | $0.15 |
| 112 | Codestral 2508 | Mistral AI | 256K | ~341 | $0.30 | $0.90 |
| 113 | Codestral 2508 (batch) | Mistral AI | 256K | ~341 | $0.15 | $0.45 |
| 114 | Command A | Cohere | 256K | ~341 | $2.50 | $10.00 |
| 115 | Grok Build 0.1 | xAI | 256K | ~341 | $1.00 | $2.00 |
| 116 | Mistral Small 3.2 24B | Mistral AI | 256K | ~341 | $0.09 | $0.25 |
| 117 | Nemotron 3 Nano Omni (free) | NVIDIA | 256K | ~341 | Free | Free |
| 118 | North Mini Code (free) | Cohere | 256K | ~341 | Free | Free |
| 119 | GLM 4.6 | Zhipu AI | 205K | ~273 | $0.43 | $1.75 |
| 120 | GLM 4.7 | Zhipu AI | 205K | ~273 | $0.60 | $2.20 |
| 121 | GLM 5 | Zhipu AI | 205K | ~273 | $0.60 | $1.92 |
| 122 | GLM 5.1 | Zhipu AI | 205K | ~273 | $0.96 | $3.03 |
| 123 | MiniMax M2 | MiniMax | 205K | ~273 | $0.30 | $1.20 |
| 124 | MiniMax M2.1 | MiniMax | 205K | ~273 | $0.30 | $1.20 |
| 125 | MiniMax M2.5 | MiniMax | 205K | ~273 | $0.27 | $1.08 |
| 126 | MiniMax M2.7 | MiniMax | 205K | ~273 | $0.30 | $1.20 |
| 127 | GLM 5 Turbo | Zhipu AI | 203K | ~270 | $1.20 | $4.00 |
| 128 | GLM 5V Turbo | Zhipu AI | 203K | ~270 | $1.20 | $4.00 |
| 129 | Claude 3 Haiku | Anthropic | 200K | ~267 | $0.25 | $1.25 |
| 130 | Claude Haiku 4.5 | Anthropic | 200K | ~267 | $1.00 | $5.00 |
| 131 | Claude Haiku 4.5 (batch) | Anthropic | 200K | ~267 | $0.50 | $2.50 |
| 132 | Claude Haiku Latest | ~anthropic | 200K | ~267 | $1.00 | $5.00 |
| 133 | Claude Opus 4.1 | Anthropic | 200K | ~267 | $15.00 | $75.00 |
| 134 | Claude Opus 4.1 (batch) | Anthropic | 200K | ~267 | $7.50 | $37.50 |
| 135 | Claude Opus 4.5 | Anthropic | 200K | ~267 | $5.00 | $25.00 |
| 136 | Claude Opus 4.5 (batch) | Anthropic | 200K | ~267 | $2.50 | $12.50 |
| 137 | Claude Sonnet 4 | Anthropic | 200K | ~267 | $3.00 | $15.00 |
| 138 | Composer 2 | Cursor | 200K | ~267 | $0.50 | $2.50 |
| 139 | Composer 2 Fast | Cursor | 200K | ~267 | $1.50 | $7.50 |
| 140 | GLM 4.7 Flash | Zhipu AI | 200K | ~267 | $0.06 | $0.40 |
| 141 | o1 | OpenAI | 200K | ~267 | $15.00 | $60.00 |
| 142 | o1-pro | OpenAI | 200K | ~267 | $150.00 | $600.00 |
| 143 | o3 | OpenAI | 200K | ~267 | $2.00 | $8.00 |
| 144 | o3 (batch) | OpenAI | 200K | ~267 | $1.00 | $4.00 |
| 145 | o3 Mini | OpenAI | 200K | ~267 | $1.10 | $4.40 |
| 146 | o3 Mini (batch) | OpenAI | 200K | ~267 | $0.55 | $2.20 |
| 147 | o3 Mini High | OpenAI | 200K | ~267 | $1.10 | $4.40 |
| 148 | o3 Pro | OpenAI | 200K | ~267 | $20.00 | $80.00 |
| 149 | o4 Mini | OpenAI | 200K | ~267 | $1.10 | $4.40 |
| 150 | o4 Mini (batch) | OpenAI | 200K | ~267 | $0.55 | $2.20 |
| 151 | o4 Mini High | OpenAI | 200K | ~267 | $1.10 | $4.40 |
| 152 | Sonar Pro | Perplexity | 200K | ~267 | $3.00 | $15.00 |
| 153 | Sonar Pro Search | Perplexity | 200K | ~267 | $3.00 | $15.00 |
128K Tokens
(79 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 | $0.25 | $1.00 |
| 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 | $0.27 | $0.40 |
| 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 | Gemma 3 12B | 131K | ~175 | $0.05 | $0.15 | |
| 15 | Gemma 3 27B | 131K | ~175 | $0.08 | $0.45 | |
| 16 | Gemma 3 4B | 131K | ~175 | $0.05 | $0.10 | |
| 17 | GLM 4.5 | Zhipu AI | 131K | ~175 | $0.60 | $2.20 |
| 18 | GLM 4.5 Air | Zhipu AI | 131K | ~175 | $0.13 | $0.85 |
| 19 | GLM 4.6V | Zhipu AI | 131K | ~175 | $0.30 | $0.90 |
| 20 | gpt-oss-120b | OpenAI | 131K | ~175 | $0.15 | $0.60 |
| 21 | gpt-oss-120b (batch) | OpenAI | 131K | ~175 | $0.03 | $0.14 |
| 22 | gpt-oss-20b | OpenAI | 131K | ~175 | $0.02 | $0.09 |
| 23 | gpt-oss-20b (batch) | OpenAI | 131K | ~175 | $0.02 | $0.11 |
| 24 | gpt-oss-safeguard-20b | OpenAI | 131K | ~175 | $0.07 | $0.30 |
| 25 | Granite 4.2 8B | IBM | 131K | ~175 | $0.06 | $0.25 |
| 26 | Hunyuan A13B Instruct | Tencent | 131K | ~175 | $0.14 | $0.57 |
| 27 | Kimi K2 0711 | Moonshot AI | 131K | ~175 | $0.57 | $2.30 |
| 28 | Llama 3.1 70B Instruct | Meta | 131K | ~175 | $0.40 | $0.40 |
| 29 | Llama 3.1 8B Instruct | Meta | 131K | ~175 | $0.05 | $0.08 |
| 30 | Llama 3.2 3B Instruct | Meta | 131K | ~175 | $0.05 | $0.33 |
| 31 | Llama 3.3 70B Instruct | Meta | 131K | ~175 | $0.10 | $0.32 |
| 32 | Ministral 3 3B 2512 | Mistral AI | 131K | ~175 | $0.10 | $0.10 |
| 33 | Mistral Large 2407 | Mistral AI | 131K | ~175 | $2.00 | $6.00 |
| 34 | Mistral Medium 3 | Mistral AI | 131K | ~175 | $0.40 | $2.00 |
| 35 | Mistral Medium 3.1 | Mistral AI | 131K | ~175 | $0.40 | $2.00 |
| 36 | Mistral Medium 3.1 (batch) | Mistral AI | 131K | ~175 | $0.20 | $1.00 |
| 37 | Mistral Nemo | Mistral AI | 131K | ~175 | $0.02 | $0.03 |
| 38 | Muse Glimmer 30B | meta | 131K | ~175 | $0.30 | $1.20 |
| 39 | Nano Banana 2 (Gemini 3.1 Flash Image) | 131K | ~175 | $0.50 | $3.00 | |
| 40 | Nano Banana Pro (Gemini 3 Pro Image) | 131K | ~175 | $2.00 | $12.00 | |
| 41 | Nemotron 3.5 Content Safety | NVIDIA | 131K | ~175 | $0.20 | $0.20 |
| 42 | Qwen3 14B | Alibaba | 131K | ~175 | $0.12 | $0.24 |
| 43 | Qwen3 235B A22B | Alibaba | 131K | ~175 | $0.45 | $1.82 |
| 44 | Qwen3 235B A22B Thinking 2507 | Alibaba | 131K | ~175 | $0.23 | $2.30 |
| 45 | Qwen3 30B A3B | Alibaba | 131K | ~175 | $0.12 | $0.50 |
| 46 | Qwen3 32B | Alibaba | 131K | ~175 | $0.08 | $0.28 |
| 47 | Qwen3 8B | Alibaba | 131K | ~175 | $0.12 | $0.45 |
| 48 | Qwen3 VL 235B A22B Thinking | Alibaba | 131K | ~175 | $0.40 | $4.00 |
| 49 | Qwen3 VL 32B Instruct | Alibaba | 131K | ~175 | $0.10 | $0.42 |
| 50 | Qwen3 VL 8B Thinking | Alibaba | 131K | ~175 | $0.18 | $2.10 |
| 51 | Solar Pro 3 | Upstage | 131K | ~175 | $0.15 | $0.60 |
| 52 | Granite 4.0 Micro | IBM | 131K | ~175 | $0.02 | $0.11 |
| 53 | Command R (08-2024) | Cohere | 128K | ~171 | $0.15 | $0.60 |
| 54 | Command R+ (08-2024) | Cohere | 128K | ~171 | $2.50 | $10.00 |
| 55 | Command R7B (12-2024) | Cohere | 128K | ~171 | $0.04 | $0.15 |
| 56 | GPT Audio | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 57 | GPT Audio Mini | OpenAI | 128K | ~171 | $0.60 | $2.40 |
| 58 | GPT-4 Turbo | OpenAI | 128K | ~171 | $10.00 | $30.00 |
| 59 | GPT-4 Turbo (batch) | OpenAI | 128K | ~171 | $5.00 | $15.00 |
| 60 | GPT-4o | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 61 | GPT-4o (2024-05-13) | OpenAI | 128K | ~171 | $5.00 | $15.00 |
| 62 | GPT-4o (2024-08-06) | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 63 | GPT-4o (2024-11-20) | OpenAI | 128K | ~171 | $2.50 | $10.00 |
| 64 | GPT-4o (batch) | OpenAI | 128K | ~171 | $1.25 | $5.00 |
| 65 | GPT-4o-mini | OpenAI | 128K | ~171 | $0.15 | $0.60 |
| 66 | GPT-4o-mini (2024-07-18) | OpenAI | 128K | ~171 | $0.15 | $0.60 |
| 67 | GPT-4o-mini (batch) | OpenAI | 128K | ~171 | $0.07 | $0.30 |
| 68 | GPT-5.2 Chat | OpenAI | 128K | ~171 | $1.75 | $14.00 |
| 69 | Mercury 2 | Inception | 128K | ~171 | $0.25 | $0.75 |
| 70 | Mistral Large | Mistral AI | 128K | ~171 | $2.00 | $6.00 |
| 71 | Mistral Small 3.1 24B | Mistral AI | 128K | ~171 | $0.35 | $0.55 |
| 72 | Nemotron 3.5 Content Safety (free) | NVIDIA | 128K | ~171 | Free | Free |
| 73 | Nova Micro 1.0 | Amazon | 128K | ~171 | $0.04 | $0.14 |
| 74 | Qwen2.5 VL 72B Instruct | Alibaba | 128K | ~171 | $0.80 | $1.00 |
| 75 | Schematron V2 Small | inference-net | 128K | ~171 | $0.05 | $0.23 |
| 76 | Schematron V2 Turbo | inference-net | 128K | ~171 | $0.03 | $0.15 |
| 77 | Sonar Deep Research | Perplexity | 128K | ~171 | $2.00 | $8.00 |
| 78 | Sonar Reasoning Pro | Perplexity | 128K | ~171 | $2.00 | $8.00 |
| 79 | 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 | ERNIE 4.5 VL 424B A47B | Baidu | 123K | ~164 | $0.42 | $1.25 |
| 3 | Qwen3 30B A3B Thinking 2507 | Alibaba | 82K | ~109 | $0.20 | $2.40 |
| 4 | GLM 4.5V | Zhipu AI | 66K | ~87 | $0.60 | $1.80 |
| 5 | LFM2.5-2.6B (free) | Liquid AI | 66K | ~87 | Free | Free |
| 6 | MiniMax M2-her | MiniMax | 66K | ~87 | $0.30 | $1.20 |
| 7 | Mixtral 8x22B Instruct | Mistral AI | 66K | ~87 | $2.00 | $6.00 |
| 8 | Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 66K | ~87 | $0.50 | $3.00 | |
| 9 | Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 66K | ~87 | $0.25 | $1.50 | |
| 10 | Nano Banana Pro (Gemini 3 Pro Image Preview) | 66K | ~87 | $2.00 | $12.00 | |
| 11 | Reka Flash 3 | rekaai | 66K | ~87 | $0.10 | $0.20 |
| 12 | WizardLM-2 8x22B | Microsoft | 66K | ~87 | $0.62 | $0.62 |
| 13 | R1 | DeepSeek | 64K | ~85 | $0.70 | $2.50 |
| 14 | Llama 3.2 1B Instruct | Meta | 60K | ~80 | $0.03 | $0.20 |
| 15 | Falcon Arabic 7B Instruct | TII | 33K | ~44 | Free | Free |
| 16 | Falcon Mamba 7B Instruct | TII | 33K | ~44 | Free | Free |
| 17 | Falcon3 10B Instruct | TII | 33K | ~44 | Free | Free |
| 18 | Falcon3 7B Instruct | TII | 33K | ~44 | Free | Free |
| 19 | GLM 5.2 (free) | Zhipu AI | 33K | ~44 | Free | Free |
| 20 | Mistral Small 3 | Mistral AI | 33K | ~44 | $0.05 | $0.08 |
| 21 | Nano Banana (Gemini 2.5 Flash Image) | 33K | ~44 | $0.30 | $2.50 | |
| 22 | Perceptron Mk1 | perceptron | 33K | ~44 | $0.15 | $1.50 |
| 23 | Qwen2.5 72B Instruct | Alibaba | 33K | ~44 | $0.36 | $0.40 |
| 24 | Qwen2.5 7B Instruct | Alibaba | 33K | ~44 | $0.10 | $0.20 |
| 25 | Qwen2.5 Coder 32B Instruct | Alibaba | 33K | ~44 | $0.66 | $1.00 |
| 26 | Saba | Mistral AI | 33K | ~44 | $0.20 | $0.60 |
| 27 | Voxtral Small 24B 2507 | Mistral AI | 33K | ~44 | $0.10 | $0.30 |
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.