gpt-oss-120b vs Kimi K2.7 Code
Pricing, context window and real answers (August 2026)
gpt-oss-120b (OpenAI) and Kimi K2.7 Code (Moonshot), compared as you can actually call them on FastMetal. Both are served from the same OpenAI-compatible endpoint and API key; switching is a change to the model string.
Specs and pricing
 gpt-oss-120b |  Kimi K2.7 Code | |
|---|---|---|
| Provider | OpenAI | Moonshot |
| Input (per 1M tokens) | ¥16 | ¥55 |
| Output (per 1M tokens) | ¥79 | ¥530 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥56 | ¥320 |
| Context window | 131,072 tokens | 262,144 tokens |
| Release date | 8/5/2025 | 6/12/2026 |
| Input modalities | text | text, image |
| Arena · overall | #196 · ELO 1,352 | Unranked |
| Arena · Japanese | #133 · ELO 1,328 | Unranked |
| Arena · coding | #203 · ELO 1,391 | Unranked |
Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.
Which should you pick?
- On price, gpt-oss-120b: ¥79 per 1M output tokens, 85% less than Kimi K2.7 Code.
- For long documents, Kimi K2.7 Code: a 262,144-token context window against 131,072 for gpt-oss-120b.
- If in doubt, try both on the same key. Switching is a change to the model string, and each is billed at its own rate.
Frequently asked questions
- Which is cheaper, gpt-oss-120b or Kimi K2.7 Code?
- Per 1M output tokens, gpt-oss-120b is ¥79 and Kimi K2.7 Code is ¥530 on FastMetal (yen, before tax), so gpt-oss-120b is cheaper.
- How do the context windows of gpt-oss-120b and Kimi K2.7 Code compare?
- gpt-oss-120b takes 131,072 tokens; Kimi K2.7 Code takes 262,144.
- Can I use gpt-oss-120b and Kimi K2.7 Code with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "gpt-oss-120b" or "japan-kimi-k2.7-code" as the model. Each is billed at its own rate from the same prepaid balance.
Try both on one API key
Create an account and add credit to call gpt-oss-120b and Kimi K2.7 Code from the browser chat and the API. No monthly fee.