LLMs with a 1 million token context window
ScaleDown: Summarize is the cheapest option at $0.040 per million input tokens. A million tokens is roughly 750,000 words - an entire codebase or a shelf of documents in a single prompt. These are the models that offer it, and what that window costs.
130 models qualify
Ranked by blended cost - input weighted 75%, output 25%.
| # | Model | Blended / 1M | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|---|---|
| 1 | Jev Router TypeSafe | $-1000000.0000 | $-1000000.0000 | $-1000000.0000 | 1M | ReasoningToolsVision |
| 2 | Switchyard NVIDIA | $-1000000.0000 | $-1000000.0000 | $-1000000.0000 | 1M | |
| 3 | Auto Router (Beta) OpenRouter | $-1000000.0000 | $-1000000.0000 | $-1000000.0000 | 2M | ReasoningToolsVision |
| 4 | Fusion OpenRouter | $-1000000.0000 | $-1000000.0000 | $-1000000.0000 | 1M | |
| 5 | Pareto Code Router OpenRouter | $-1000000.0000 | $-1000000.0000 | $-1000000.0000 | 2M | ReasoningTools |
| 6 | Auto Router OpenRouter | $-1000000.0000 | $-1000000.0000 | $-1000000.0000 | 2M | ReasoningToolsVision |
| 7 | Lyria 3 Pro Preview | Free | Free | Free | 1.0M | Free tierVision |
| 8 | Lyria 3 Clip Preview | Free | Free | Free | 1.0M | Free tierVision |
| 9 | Summarize ScaleDown | $0.030 | $0.040 | Free | 1M | Vision |
| 10 | Extract ScaleDown | $0.030 | $0.040 | Free | 1M | Vision |
| 11 | GLM 5.3 Flash Z.ai | $0.053 | $0.046 | $0.074 | 1.0M | ReasoningToolsVisionOpen weights |
| 12 | Qwen3.7 Flash Qwen | $0.055 | $0.030 | $0.130 | 1M | ReasoningToolsVision |
| 13 | Ling 3.1 Flash inclusionAI | $0.112 | $0.075 | $0.225 | 1M | ReasoningTools |
| 14 | Laguna S 2.1 Poolside | $0.113 | $0.090 | $0.180 | 1.0M | Free tierReasoningToolsOpen weights |
| 15 | DeepSeek V4 Flash 0423 DeepSeek | $0.114 | $0.091 | $0.182 | 1.0M | ReasoningToolsOpen weights |
| 16 | Qwen3.5-Flash Qwen | $0.114 | $0.065 | $0.260 | 1M | ReasoningToolsVision |
| 17 | $0.125 | $0.100 | $0.200 | 1.0M | ReasoningToolsVision | |
| 18 | $0.125 | $0.100 | $0.200 | 1.0M | ReasoningToolsVision | |
| 19 | DeepSeek V4 Flash 0731 DeepSeek | $0.149 | $0.119 | $0.238 | 1.0M | ReasoningToolsOpen weights |
| 20 | Llama 4 Scout Meta Llama | $0.150 | $0.100 | $0.300 | 1.3M | ToolsVisionOpen weights |
| 21 | DeepSeek V4.1 Flash DeepSeek | $0.159 | $0.045 | $0.500 | 1.0M | ReasoningToolsVisionOpen weights |
| 22 | Mercury 3 Inception | $0.162 | $0.100 | $0.350 | 1M | ReasoningTools |
| 23 | Gemini 2.5 Flash Lite | $0.175 | $0.100 | $0.400 | 1.0M | ReasoningToolsVision |
| 24 | GPT-4.1 Nano OpenAI | $0.175 | $0.100 | $0.400 | 1.0M | ToolsVision |
| 25 | MiMo-V2.6-Flash Xiaomi | $0.175 | $0.140 | $0.280 | 1.1M | ReasoningToolsVisionOpen weights |
Frequently asked
What is the cheapest LLM for million-token context?
ScaleDown: Summarize at $0.040 per million input tokens and Free per million output tokens, with a 1M token context window.
How many models qualify for million-token context?
130 of the 359 models tracked here meet the criteria for this list.
How much do prices vary within this category?
By roughly 2,300×, from Summarize at the bottom to GPT-5.4 Pro at the top.