Models

5 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
Kimi (latest)	privatemode-ai	256,000	Input $1.79 per 1M tokens low Input (cached read) $0.1733 per 1M tokens low Output $8.94 per 1M tokens low
Voxtral Mini 3B	privatemode-ai	32,000	Input $0.00462 per 1M tokens low Output $0.00 per 1M tokens low
Qwen3-Embedding 4B	privatemode-ai	32,000	Input $0.1502 per 1M tokens low Output $0.00 per 1M tokens low
GLM (latest)	privatemode-ai	1,000,000	Input $1.79 per 1M tokens low Input (cached read) $0.1733 per 1M tokens low Output $6.63 per 1M tokens low
GLM Flash (latest)	privatemode-ai	1,000,000	Input $0.2311 per 1M tokens low Input (cached read) $0.0578 per 1M tokens low Output $0.7511 per 1M tokens low