LLM APIs with the largest context windows (August 2026)
The models FastMetal serves, ordered by how many tokens one request can hold.
Ordered by context window: the number of tokens one request can hold.
| Links | |||||||
|---|---|---|---|---|---|---|---|
| 1 | GPT-5.6 Luna |  OpenAI | Unranked | ¥35.74 | ¥214.44 | 1,050,000 | Details |
| 2 | GPT-5.6 Sol | OpenAI | Unranked | ¥893.5 | ¥5,361 | 1,050,000 | DetailsCompare |
| 3 | GPT-5.6 Terra | OpenAI | Unranked | ¥357.4 | ¥2,144.4 | 1,050,000 | DetailsCompare |
| 4 | MiMo-V2.5 | Xiaomi | Unranked | ¥25.02 | ¥50.04 | 1,050,000 | Details |
| 5 | MiMo-V2.5-Pro | Xiaomi | Unranked | ¥77.73 | ¥155.47 | 1,050,000 | DetailsCompare |
| 6 | DeepSeek V4 Flash |  DeepSeek | Unranked | ¥16.08 | ¥32.17 | 1,048,576 | DetailsCompare |
| 7 | DeepSeek V4 Pro | DeepSeek | Unranked | ¥341.32 | ¥684.42 | 1,048,576 | DetailsCompare |
| 8 | Gemini 3.5 Flash |  Google | Unranked | ¥268.05 | ¥1,608.3 | 1,048,576 | DetailsCompare |
| 9 | Gemini 3.7 Flash | Google | Unranked | ¥134.03 | ¥670.13 | 1,048,576 | DetailsCompare |
| 10 | GLM 5.2 |  Z.ai | Unranked | ¥250.18 | ¥786.28 | 1,048,576 | DetailsCompare |
Click a column heading to re-sort; the table opens in this category's ranking order. Prices are yen per 1M tokens before tax; context is in tokens.
Frequently asked questions
- What is this ranking based on?
- Ordered by context window: the number of tokens one request can hold.
- How is pricing decided?
- Each model has a yen price per 1M tokens (before tax), 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.