Arcee AI API pricing

Official6 language models

As of Oct 14, 2026, Arcee AI lists 6 language models through its API. Its cheapest language model is Trinity Large Thinking at $0.25 input / $0.80 output per million tokens.

Language models (6)

Prices per million tokens.

Model	Input	Output	Cached input	Context
DeepSeek V4 Pro deepseek/deepseek-v4-pro	$1.74	$3.48	$0.20	512K
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813	$1.32	$3.96	$0.044	1.05M
GLM 5.2 zai-org/glm-5.2	$1.40	$4.40	$0.26	262K
Inkling Small thinkingmachines/inkling-small	$0.50	$1.20	$0.10	262K
Kimi K3 moonshotai/kimi-k3	$3.00	$15.00	$0.30	1.05M
Trinity Large Thinking trinity-large-thinking	$0.25	$0.80	$0.06	262K

DeepSeek V4 Pro
deepseek/deepseek-v4-pro
Input
$1.74
Output
$3.48
Context
512K
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
Input
$1.32
Output
$3.96
Context
1.05M
GLM 5.2
zai-org/glm-5.2
Input
$1.40
Output
$4.40
Context
262K
Inkling Small
thinkingmachines/inkling-small
Input
$0.50
Output
$1.20
Context
262K
Kimi K3
moonshotai/kimi-k3
Input
$3.00
Output
$15.00
Context
1.05M
Trinity Large Thinking
trinity-large-thinking
Input
$0.25
Output
$0.80
Context
262K

Prices in USD from LiteLLM and models.dev, checked daily; confirm on Arcee AI's pricing page before you rely on a number.