Model Pricing

Pricing for MatterAI inference API models

Pricing and Comparison

Model	Input Price (per 1M tokens)	Output Price (per 1M tokens)	Context Window Size	Max Output Tokens
DeepSeek V4.1 Flash	$0.30	$1.20	1M tokens	64K
GLM 5.3	$1.40	$4.40	1M tokens	64K
GLM 5.3 Flash	$0.15	$0.50	1M tokens	64K
Gemini 3.8 Flash	$0.75	$3.75	1M tokens	64K

Prompt Caching

Cached input tokens are automatically discounted. Caching kicks in automatically for repeated prompt prefixes.

Model	Cached Input Price (per 1M tokens)
DeepSeek V4.1 Flash	$0.006
GLM 5.3	$0.14
GLM 5.3 Flash	$0.03
Gemini 3.8 Flash	$0.075

All models support tool calling, structured outputs, web search, and text + image input with text output. Automatic discounts apply to all models.