Cheapest LLMs with a 200K+ context window
ScaleDown: Summarize is the cheapest option at $0.040 per million input tokens. Large context windows are the single most expensive thing to buy in an LLM. These models offer at least 200,000 tokens without frontier pricing.
247 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 | Flint (free) Recursive | Free | Free | Free | 262K | Free tierReasoningToolsOpen weights |
| 8 | Xing4.0 29B A4B (free) XingChen | Free | Free | Free | 262K | Free tierReasoningToolsOpen weights |
| 9 | Dots3-Note Preview (free) Dots Studio | Free | Free | Free | 512K | Free tierReasoningToolsVision |
| 10 | North Mini Code (free) Cohere | Free | Free | Free | 256K | Free tierReasoningToolsOpen weights |
| 11 | Free | Free | Free | 256K | Free tierReasoningToolsVisionOpen weights | |
| 12 | Lyria 3 Pro Preview | Free | Free | Free | 1.0M | Free tierVision |
| 13 | Lyria 3 Clip Preview | Free | Free | Free | 1.0M | Free tierVision |
| 14 | Free Models Router OpenRouter | Free | Free | Free | 200K | Free tierReasoningToolsVision |
| 15 | Summarize ScaleDown | $0.030 | $0.040 | Free | 1M | Vision |
| 16 | Extract ScaleDown | $0.030 | $0.040 | Free | 1M | Vision |
| 17 | Ling 3.0 Flash inclusionAI | $0.032 | $0.021 | $0.063 | 262K | ReasoningToolsOpen weights |
| 18 | Nex-N2.5-Mini Nex AGI | $0.044 | $0.025 | $0.100 | 262K | ReasoningVisionOpen weights |
| 19 | GLM 5.3 Flash Z.ai | $0.053 | $0.046 | $0.074 | 1.0M | ReasoningToolsVisionOpen weights |
| 20 | Qwen3.7 Flash Qwen | $0.055 | $0.030 | $0.130 | 1M | ReasoningToolsVision |
| 21 | Mercury 2.5 Inception | $0.068 | $0.040 | $0.150 | 260K | ReasoningTools |
| 22 | Laguna XS 2.1 Poolside | $0.075 | $0.060 | $0.120 | 262K | Free tierReasoningToolsOpen weights |
| 23 | Solar Mini 4 Upstage | $0.087 | $0.050 | $0.200 | 524K | ReasoningTools |
| 24 | Ternary Bonsai 2 9B PrismML | $0.092 | $0.080 | $0.130 | 262K | ReasoningToolsVisionOpen weights |
| 25 | Nemotron 3.5 Lightning NVIDIA | $0.103 | $0.070 | $0.200 | 262K | Free tierReasoningToolsOpen weights |
Frequently asked
What is the cheapest LLM for long-document work?
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 long-document work?
247 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.