Skip to main content
Version: Next

Pricing

Privatemode uses usage-based pricing.

  • Chat model prices are shown per 1 million tokens.
  • Embedding model prices are shown per 1 million input tokens.
  • Speech-to-text model prices are shown per audio minute.
  • For monthly quotas and model-specific free tier multipliers, see Rate limits.

Chat completions

ModelInputOutputCached input
gpt-oss-120bEUR 0.43EUR 1.70EUR 0.04
Kimi-K2.5EUR 1.55EUR 7.74EUR 0.15
Gemma 3 27BEUR 0.77EUR 1.27EUR 0.08
Qwen3-Coder 30B-A3BEUR 0.43EUR 1.70EUR 0.04

Embeddings

ModelInput
Qwen3-Embedding 4BEUR 0.13

Speech-to-text

ModelAudio
Voxtral Mini 3BEUR 0.004
Whisper large-v3EUR 0.014