Budget-friendly models
Lower-cost models suited to high-volume, latency-sensitive tasks like classification or short replies.
- GPT-5.6 Luna — Input / 1M tokens $0.200, Output / 1M tokens $1.20
- Claude Haiku 4.5 (latest) — Input / 1M tokens $1.00, Output / 1M tokens $5.00
- Gemini 3.5 Flash Lite — Input / 1M tokens $0.300, Output / 1M tokens $2.50