---
title: "Z.ai: GLM 4.7 — price, capability and what beats it · Undominated.ai"
canonical: https://undominated.ai/models/z-ai__glm-4.7/
description: "Z.ai: GLM 4.7: $0.400/M in, $1.75/M out. Independent capability scores, context-tier pricing, and the models that are both better and cheaper."
---

# Z.ai: GLM 4.7 — price, capability and what beats it · Undominated.ai

> Z.ai: GLM 4.7: $0.400/M in, $1.75/M out. Independent capability scores, context-tier pricing, and the models that are both better and cheaper.

[Leaderboard](/) / Z.ai

# GLM 4.7

Z.ai · released 2025-12-22

 $0.738 per million tokens, balanced Balanced Summarise Chat Code gen Agentic

## DeepSeek V4 Flash 0731 is both better and cheaper.

It scores **+17.3** higher and costs **86% less** ($0.105/M against $0.738/M) on this workload — and it does everything this model does.

[GPT-5.6 Luna](/models/openai__gpt-5.6-luna) is cheaper still (39% less) but drops 131K → 128K max output.

### Every price dimension

| Input | $0.400 /M |
| --- | --- |
| Output | $1.75 /M |
| Cached input | $0.080 /M |

### Independent scores

| Intelligence | 34.5 |
| --- | --- |
| Coding | 45.3 |
| Agentic | 26.2 |
| LMArena Elo | 1435.3 default |

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

 - asciiart #24 of 83 1193
- androidnative #27 of 54 1140
- mobileapps #28 of 56 1156
- godotgamedev #28 of 43 1058
- fullstack #32 of 59 1083

### Capability

| Context window | 205K |
| --- | --- |
| Max output | 131K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |

### Provenance

| Price source | openrouter.ai |
| --- | --- |
| Fetched | 2026-08-24 |
| Quality data | verified |

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...