Cheapest LLM APIs (October 2026)
The paid models FastMetal serves, ordered by price per 1M output tokens.
Ordered by price per 1M output tokens, then input price. Free-tier models are excluded.
| Links | ||||||
|---|---|---|---|---|---|---|
| 1 | Llama 3.1 8B Instruct |  Meta | $0.0211 | $0.0422 | 131,072 | DetailsCompare |
| 2 | Voxtral Mini 3B |  Mistral | $0.0528 | $0.0528 | 32,768 | Details |
| 3 | gpt-oss-20b |  OpenAI | $0.0317 | $0.1477 | 131,072 | DetailsCompare |
| 4 | Mercury 2.5 | Inception | $0.044 | $0.165 | 260,000 | DetailsCompare |
| 5 | Ling 3.0 Flash VL | inclusionAI | $0.0633 | $0.1899 | 131,072 | Details |
| 6 | DeepSeek V4 Flash |  DeepSeek | $0.095 | $0.1899 | 1,048,576 | DetailsCompare |
| 7 | Muse Spark 1.3 Contributor | Meta | $0.11 | $0.22 | 1,048,576 | DetailsCompare |
| 8 | Solar Mini 4 | Upstage | $0.055 | $0.22 | 524,288 | DetailsCompare |
| 9 | MiMo-V2.5 | Xiaomi | $0.1477 | $0.2954 | 1,050,000 | DetailsCompare |
| 10 | deepseek-v4-flash-0731 | DeepSeek | $0.1477 | $0.2954 | — | Details |
Click a column heading to re-sort; the table opens in this category's ranking order. Prices are per 1M tokens, before tax; context is in tokens.
Frequently asked questions
- What is this ranking based on?
- Ordered by price per 1M output tokens, then input price. Free-tier models are excluded.
- How is pricing decided?
- Each model has a price per 1M tokens (before tax) — in yen, or in US dollars on a US-dollar account — drawn from a prepaid balance as you use it. There is no subscription or monthly fee.
- Can I use the top models with one API key?
- Yes. Every model on this page is served from FastMetal's OpenAI-compatible endpoint under one API key; switching is a change to the model string.
Every model above runs on one API key
Create an account and add credit to call these models from the browser chat and the API. No monthly fee.