Kimi K2.7 Code vs GLM 5.2 — which open model is the better coding workhorse. Below is the full side-by-side: specifications, API pricing, context window, local hardware requirements, and a clear, data-driven recommendation on which to pick.
| Spec | Kimi K2.7 Code | GLM 5.2 |
|---|---|---|
| Developer | Moonshot AI | Zhipu AI |
| Type | LLM (coding, MoE) | LLM (coding/agentic, MoE) |
| Parameters | 1T total / 32B active (MoE) | 744B total / ~40B active (MoE) |
| Context window | 256K | 1M |
| Modality | Text → Text | Text → Text |
| License | Modified MIT (open) | MIT (open) |
| Open weights | ✅ Yes | ✅ Yes |
| Input price ($/1M) | $0.6 | $1.4 |
| Output price ($/1M) | $2.5 | $4.4 |
| VRAM (4-bit) | ~500 GB | ~370 GB |
| Min GPU (local) | Multi-GPU server | Multi-GPU server (e.g. 5× H100 80GB) |
| Released | 2026-06 | 2026-06 |
Key differences
- Cost: Kimi K2.7 Code is 100% cheaper than GLM 5.2 on a blended-token basis.
- Context: GLM 5.2 wins on context window (1M vs 256K) — better for long documents, large codebases and big RAG inputs.
- Openness: both are open-weight, so either can be self-hosted or fine-tuned. Compare their VRAM needs above to see what your GPU can run.
- Run Kimi K2.7 Code locally: ~~500 GB at 4-bit (min Multi-GPU server).
- Run GLM 5.2 locally: ~~370 GB at 4-bit (min Multi-GPU server (e.g. 5× H100 80GB)).
Which should you choose?
Choose Kimi K2.7 Code if you want the lower per-token cost for high-volume workloads.
Choose GLM 5.2 if you need the larger context window.
→ Estimate real costs in the API cost calculator · check local hardware in the VRAM calculator · browse all 30+ models.
All specs and prices are pulled live from our AI models database and kept current. Compare either model against others, or estimate your own monthly spend with the free calculators above.