Budget‑friendly APIs
Lowest headline prices for prototyping and high‑volume workloads.
- GPT‑4.1 Mini
- $0.15 / $0.60
- Gemini 2.0 Flash
- $0.10 / $0.40
Input / output prices per 1M tokens.
LLM pricing overview
High‑level pricing snapshot for a few popular models. For a more detailed table and filters, use the models page.
Balanced options
Good trade‑off between quality, latency, and cost.
See individual model pages for more details and benchmarks; numbers here are just a starting point.
How to read pricing
- Always estimate your monthly tokens, not just per‑request cost.
- Check if tools, images, or long context have extra pricing tiers.
- Review free tier and committed‑use discounts in provider docs.