GLM 4.6
Z.ai released 2025-09-30
$0.875 per million tokens, balanced
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +22.5 higher and costs 88% less ($0.105/M against $0.875/M) on this workload — and it does everything this model does.
Gemini 3.7 Flash is cheaper still (14% less) but drops 131K → 66K max output.
Every price dimension
| Input | $0.500/M |
|---|---|
| Output | $2.00/M |
| Cached input | $0.100/M |
Independent scores
| Intelligence | 29.3 |
|---|---|
| Coding | 45.8 |
| Agentic | 18.6 |
| LMArena Elo | 1439.8default |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Best rankings by task
- godotgamedev #13of 43 1180
- mobileapps #29of 56 1147
- androidnative #29of 54 1111
Capability
| Context window | 205K |
|---|---|
| Max output | 131K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Knowledge cutoff | 2025-03-31 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...