Skip to content
LLMs

Cheapest reasoning LLMs

inclusionAI: Ling 3.0 Flash is the cheapest option at $0.021 per million input tokens. Reasoning models emit far more output tokens than they take in, so output price dominates the bill. These are ranked with that weighting in mind.

218 models qualify

Ranked by output price, because reasoning models bill mostly on tokens they generate.

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
Auto Router

OpenRouter

$-1000000.0000$-1000000.0000$-1000000.00002M
ReasoningToolsVision
3FreeFreeFree262K
Free tierReasoningToolsVisionOpen weights
4FreeFreeFree262K
Free tierReasoningToolsVisionOpen weights
5FreeFreeFree262K
Free tierReasoningTools
6FreeFreeFree512K
Free tierReasoningToolsVision
7FreeFreeFree66K
Free tierReasoningToolsOpen weights
8FreeFreeFree256K
Free tierReasoningToolsOpen weights
9FreeFreeFree256K
Free tierReasoningToolsVisionOpen weights
10FreeFreeFree200K
Free tierReasoningToolsVision
11
inclusionAI logo
Ling 3.0 Flash

inclusionAI

$0.032$0.021$0.063262K
ReasoningToolsOpen weights
12$0.075$0.060$0.1201.3M
ReasoningToolsOpen weights
13$0.075$0.060$0.120262K
Free tierReasoningToolsOpen weights
14$0.055$0.030$0.1301M
ReasoningToolsVision
15$0.055$0.030$0.130131K
ReasoningToolsOpen weights
16
Inception logo
Mercury 2.5

Inception

$0.068$0.040$0.150260K
ReasoningTools
17$0.112$0.100$0.150262K
ReasoningToolsVisionOpen weights
18$0.070$0.037$0.170131K
ReasoningToolsOpen weights
19$0.107$0.086$0.1711.0M
ReasoningToolsOpen weights
20$0.090$0.060$0.180131K
Free tierReasoningToolsVisionOpen weights
21$0.090$0.060$0.180262K
Free tierReasoningTools
22
Poolside logo
Laguna S 2.1

Poolside

$0.113$0.090$0.1801.0M
Free tierReasoningToolsOpen weights
23$0.125$0.100$0.2001.0M
ReasoningToolsVision
24$0.125$0.100$0.2001.0M
ReasoningToolsVision
25$0.110$0.080$0.200262K
Free tierReasoningToolsOpen weights

Frequently asked

What is the cheapest LLM for step-by-step reasoning?

inclusionAI: Ling 3.0 Flash at $0.021 per million input tokens and $0.063 per million output tokens, with a 262K token context window.

How many models qualify for step-by-step reasoning?

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

How much do prices vary within this category?

By roughly 8,300×, from Ling 3.0 Flash at the bottom to o1-pro at the top.