GLM-5.1
- Context
- 200K
- 128K max output
- Input price
- $1.40
- per 1M tokens · Z.ai API
- Output price
- $4.40
- per 1M tokens
- Epoch Capabilities Index
- 149.9
- #43 of 71 listed
- LMArena Text
- 1,465
- #29 of 79 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $1.40 / 1M tokens |
| Output | Standard | $4.40 / 1M tokens |
| Cache read | Standard | $0.26 / 1M tokens |
| Cache write | Standard | Free / 1M tokens |
SiliconFlow (opens in a new tab) Pro/zai-org/GLM-5.1 | ||
| Input | Standard | ¥6.00 / 1M tokens |
| Prompts over 32K tokens | ¥8.00 / 1M tokens | |
| Output | Standard | ¥24.00 / 1M tokens |
| Prompts over 32K tokens | ¥28.00 / 1M tokens | |
| Cache read | Standard | ¥1.30 / 1M tokens |
| Prompts over 32K tokens | ¥2.00 / 1M tokens | |
| Input | Standard | ¥6.00 / 1M tokens |
| Prompts over 32K tokens | ¥8.00 / 1M tokens | |
| Output | Standard | ¥24.00 / 1M tokens |
| Prompts over 32K tokens | ¥28.00 / 1M tokens | |
| Cache read | Standard | ¥1.30 / 1M tokens |
| Prompts over 32K tokens | ¥2.00 / 1M tokens | |
Changes
All changes →- 3 new prices on SiliconFlow, China Input ¥6.00 · Output ¥24.00 · Cache read ¥1.30
Vendor-reported scores
Published by Zhipu AI, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| Humanity's Last Exam | text-only subset, no tools | 31% |
| text-only subset, with tools | 52.3% | |
| AIME 2026 | — | 95.3% |
| GPQA Diamond | — | 86.2% |
| SWE-bench Pro | — | 58.4% |
| Terminal-Bench 2.0 | Terminus-2 harness | 63.5% |
| Claude Code harness | 69% | |
| BrowseComp | without context management | 68% |
| with context management | 79.3% | |
| MCP-Atlas | public set | 71.8% |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 149.9
#43 of 71 listed models · CI 147.9–151.6
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text 1,465
#29 of 79 listed models · CI 1,461–1,469 · 56,463 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- Epoch AI · FrontierMath Tiers 1–3 36.8%
#44 of 56 listed models · ±2.86
Also listed: reasoning off 24.9%
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · GPQA Diamond 89.9%
#30 of 64 listed models · ±2.15
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- Epoch AI · SWE-bench Verified 74.2%
#15 of 23 listed models · ±1.99
Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made
- LMArena Text · Chinese 1,515
#28 of 79 listed models · CI 1,505–1,526 · 3,907 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,513
#33 of 79 listed models · CI 1,507–1,519 · 15,660 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made