GLM 4.7 vs Kimi K2.7 Code
Pricing, context window and real answers (August 2026)
GLM 4.7 (Z.ai) 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
 GLM 4.7 |  Kimi K2.7 Code | |
|---|---|---|
| Provider | Z.ai | Moonshot |
| Input (per 1M tokens) | ¥107.22 | ¥55 |
| Output (per 1M tokens) | ¥393.14 | ¥530 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥304 | ¥320 |
| Context window | 202,752 tokens | 262,144 tokens |
| Release date | 12/22/2025 | 6/12/2026 |
| Input modalities | text | text, image |
| Arena · overall | #79 · ELO 1,442 | Unranked |
| Arena · Japanese | Unranked | Unranked |
| Arena · coding | #87 · ELO 1,485 | Unranked |
Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.
Which should you pick?
- On price, GLM 4.7: ¥393.14 per 1M output tokens, 26% less than Kimi K2.7 Code.
- For long documents, Kimi K2.7 Code: a 262,144-token context window against 202,752 for GLM 4.7.
- 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, GLM 4.7 or Kimi K2.7 Code?
- Per 1M output tokens, GLM 4.7 is ¥393.14 and Kimi K2.7 Code is ¥530 on FastMetal (yen, before tax), so GLM 4.7 is cheaper.
- How do the context windows of GLM 4.7 and Kimi K2.7 Code compare?
- GLM 4.7 takes 202,752 tokens; Kimi K2.7 Code takes 262,144.
- Can I use GLM 4.7 and Kimi K2.7 Code with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "glm-4.7" 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 GLM 4.7 and Kimi K2.7 Code from the browser chat and the API. No monthly fee.