Skip to content
LLMs

LLMs with a 1 million token context window

Qwen: Qwen3.7 Flash is the cheapest option at $0.030 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.

99 models qualify

Ranked by blended cost - input weighted 75%, output 25%.

Language models with price per million tokens and context window
#ModelBlended / 1MInput / 1MOutput / 1MContextCapabilities
1$-1000000.0000$-1000000.0000$-1000000.00002M
ReasoningToolsVision
2
OpenRouter logo
Fusion

OpenRouter

$-1000000.0000$-1000000.0000$-1000000.00001M
3$-1000000.0000$-1000000.0000$-1000000.00002M
4
OpenRouter logo
Auto Router

OpenRouter

$-1000000.0000$-1000000.0000$-1000000.00002M
ReasoningToolsVision
5FreeFreeFree1.0M
Free tierVision
6FreeFreeFree1.0M
Free tierVision
7$0.055$0.030$0.1301M
ReasoningToolsVision
8$0.075$0.060$0.1201.3M
ReasoningToolsOpen weights
9$0.107$0.086$0.1711.0M
ReasoningToolsOpen weights
10
Poolside logo
Laguna S 2.1

Poolside

$0.113$0.090$0.1801.0M
Free tierReasoningToolsOpen weights
11$0.114$0.065$0.2601M
ReasoningToolsVision
12$0.125$0.100$0.2001.0M
ReasoningToolsVision
13$0.125$0.100$0.2001.0M
ReasoningToolsVision
14
Meta Llama logo
Llama 4 Scout

Meta Llama

$0.150$0.100$0.3001.3M
ToolsVisionOpen weights
15$0.175$0.100$0.4001.0M
ReasoningToolsVision
16$0.175$0.100$0.4001.0M
ToolsVision
17
Xiaomi logo
MiMo-V2.5

Xiaomi

$0.175$0.140$0.2801.1M
ReasoningToolsVisionOpen weights
18$0.230$0.150$0.4701M
ReasoningToolsVisionOpen weights
19$0.237$0.150$0.5001.3M
ReasoningToolsVisionOpen weights
20$0.262$0.150$0.6001.0M
ReasoningToolsVisionOpen weights
21$0.324$0.200$0.6961.0M
ToolsVisionOpen weights
22$0.330$0.220$0.6601.0M
ReasoningToolsVisionOpen weights
23$0.390$0.195$0.9751M
Tools
24$0.390$0.260$0.7801M
Tools
25$0.390$0.260$0.7801M
Tools

Frequently asked

What is the cheapest LLM for million-token context?

Qwen: Qwen3.7 Flash at $0.030 per million input tokens and $0.130 per million output tokens, with a 1M token context window.

How many models qualify for million-token context?

99 of the 340 models tracked here meet the criteria for this list.

How much do prices vary within this category?

By roughly 1,200×, from Qwen3.7 Flash at the bottom to GPT-5.4 Pro at the top.