Claude Opus 5 vs Kimi K2.7 Code
Pricing, context window and real answers (August 2026)
Claude Opus 5 (Anthropic) 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
| Provider | Anthropic | Moonshot |
|---|---|---|
| Input (per 1M tokens) | ¥893.5 | ¥55 |
| Output (per 1M tokens) | ¥4,467.5 | ¥530 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥3,127 | ¥320 |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Release date | 7/24/2026 | 6/12/2026 |
| Input modalities | text, image, file | text, image |
| Arena · overall | #7 · ELO 1,492 | Unranked |
| Arena · Japanese | #8 · ELO 1,495 | Unranked |
| Arena · coding | #8 · ELO 1,533 | Unranked |
Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.
Which should you pick?
- On price, Kimi K2.7 Code: ¥530 per 1M output tokens, 88% less than Claude Opus 5.
- For long documents, Claude Opus 5: a 1,000,000-token context window against 262,144 for Kimi K2.7 Code.
- 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, Claude Opus 5 or Kimi K2.7 Code?
- Per 1M output tokens, Claude Opus 5 is ¥4,467.5 and Kimi K2.7 Code is ¥530 on FastMetal (yen, before tax), so Kimi K2.7 Code is cheaper.
- How do the context windows of Claude Opus 5 and Kimi K2.7 Code compare?
- Claude Opus 5 takes 1,000,000 tokens; Kimi K2.7 Code takes 262,144.
- Can I use Claude Opus 5 and Kimi K2.7 Code with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "anthropic-claude-opus-5" 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 Claude Opus 5 and Kimi K2.7 Code from the browser chat and the API. No monthly fee.