Refuseless API pricing

Hosted5 language models

As of Oct 27, 2026, Refuseless lists 5 language models through its API. Its cheapest language model is DeepSeek V4.1 Flash Fast at $0.05 input / $0.15 output per million tokens.

Language models (5)

Prices per million tokens.

Model	Input	Output	Cached input	Context
DeepSeek V4.1 Flash Fast refuseless/deepseek-v4.1-flash-fast	$0.05	$0.15	$0.003	1.05M
MiniMax M3.1 Flash refuseless/minimax-m3.1-flash	$0.05	$0.25	$0.002	1.05M
DeepSeek V4.1 Flash Abliterated refuseless/deepseek-v4.1-flash-abliterated	$0.22	$0.75	$0.045	1.05M
GLM 5.3 Abliterated refuseless/glm-5.3-abliterated	$1.25	$2.25	$0.25	1.05M
GLM 5.3 Flash Abliterated refuseless/glm-5.3-flash-abliterated	$0.25	$0.80	$0.15	1.05M

DeepSeek V4.1 Flash Fast
refuseless/deepseek-v4.1-flash-fast
Input
$0.05
Output
$0.15
Context
1.05M
MiniMax M3.1 Flash
refuseless/minimax-m3.1-flash
Input
$0.05
Output
$0.25
Context
1.05M
DeepSeek V4.1 Flash Abliterated
refuseless/deepseek-v4.1-flash-abliterated
Input
$0.22
Output
$0.75
Context
1.05M
GLM 5.3 Abliterated
refuseless/glm-5.3-abliterated
Input
$1.25
Output
$2.25
Context
1.05M
GLM 5.3 Flash Abliterated
refuseless/glm-5.3-flash-abliterated
Input
$0.25
Output
$0.80
Context
1.05M