glm-5-1
Developer: Zhipu AI
Also known as
GLM-5.1 by Zhipu AI is available through 46 API providers on LMSpeed. Compare API pricing from $0.0001 to $31207884.00 per million input tokens across providers. Free API access is offered by 2 providers. In speed benchmarks, the fastest provider reaches 62 tok/s.
Compare GLM-5.1 API pricing across 44 providers. Input prices range from $0.0001 to $31207884.00 per million input. OptAI offers the lowest rate at $0.0001/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 我不是AI神 | glm-5.1 | Free | Free | — |
| MapleLeaf API | glm-5.1 | Free | Free | — |
| OptAI | glm-5.1 | $0.0001 | $0.0001 | — |
| 91VIP | glm-5.1 | $0.0014 | $0.0044 | — |
| Futureppo | glm-5.1 | $0.0014 | $0.0044 | — |
| 素墨API | cb/glm-5.1 | $0.010 | $0.010 | 41.3 t/s |
 GLM BigModel Relay | glm-5.1 | $0.088 | $0.351 | — |
 星见雅 API | GLM-5.1 | $0.100 | $0.100 | — |
 VVCode | glm-5.1 | $0.140 | $0.440 | 41.2 t/s |
 ai.api.xn--fiqs8s | glm-5.1 | $0.150 | $0.150 | — |
 丸美小沐写作 | glm-5.1 | $0.150 | $0.150 | — |
| uglycat | glm-5.1 | $0.200 | $0.200 | — |
| 人人 API | glm-5.1 | $0.250 | $0.600 | — |
 小天公益站 | glm-5.1 | $0.350 | $1.20 | — |
 UniAiX | glm-5.1 | $0.493 | $1.97 | — |
 OpenRouter Fans | Pro/zai-org/GLM-5.1 | $0.840 | $3.36 | — |
| Synapse | glm-5.1 | $1.00 | $1.00 | — |
| VSLLM | Pro/zai-org/GLM-5.1 | $1.10 | $5.72 | — |
| ChatST API | glm-5.1 | $1.40 | $4.40 | — |
| E-larex's AI Proxy | GLM-5.1 | $1.40 | $4.40 | — |
Pricing data from provider public APIs
GLM-5.1 is free to use through 2 providers with no per-token charges. These providers offer free API credits or a free tier:
| Provider | Speed (t/s) |
|---|---|
| 我不是AI神 | — |
| MapleLeaf API | — |
Compare speed and latency performance across all API providers.
Showing 1-7 of 7 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 Ollamaglm-5.1:cloud | 61.57 tok/s | 25.98s | 15 |
 OpenRouterz-ai/glm-5.1 | 58.08 tok/s | 14.05s | 15 |
cb/glm-5.1 | 41.30 tok/s | 7.76s | 5 |
 glm-5.1 | 41.16 tok/s | 4.21s | 5 |
 glm-5.1 | 32.26 tok/s | 19.08s | 30 |
 z-ai/glm-5.1 | 31.15 tok/s | 16.62s | 5 |
glm-5.1 | 27.37 tok/s | 3.83s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/13/2026, 14:24 | glm-5.1:cloud | 5.75 tok/s | 102.89s |
| 04/13/2026, 14:24 | glm-5.1:cloud | 7.78 tok/s | 90.60s |
| 04/13/2026, 14:24 | glm-5.1:cloud | 44.37 tok/s | 6.78s |
| 04/13/2026, 14:24 | glm-5.1:cloud | 52.90 tok/s | 1.52s |
| 04/13/2026, 14:24 | glm-5.1:cloud | 93.64 tok/s | 10.79s |
| 04/13/2026, 14:20 | glm-5.1:cloud | 8.79 tok/s | 64.67s |
| 04/13/2026, 14:20 | glm-5.1:cloud | 43.34 tok/s | 1.11s |
| 04/13/2026, 14:20 | glm-5.1:cloud | 96.39 tok/s | 23.19s |
| 04/13/2026, 14:20 | glm-5.1:cloud | 5.44 tok/s | 33.23s |
| 04/13/2026, 14:20 | glm-5.1:cloud | 94.99 tok/s | 6.89s |
| 04/13/2026, 14:12 | glm-5.1:cloud | 78.30 tok/s | 7.73s |
| 04/13/2026, 14:12 | glm-5.1:cloud | 80.04 tok/s | 1.80s |
| 04/13/2026, 14:12 | glm-5.1:cloud | 107.22 tok/s | 15.06s |
| 04/13/2026, 14:12 | glm-5.1:cloud | 95.12 tok/s | 9.95s |
| 04/13/2026, 14:12 | glm-5.1:cloud | 109.45 tok/s | 13.51s |
| 04/13/2026, 03:04 | z-ai/glm-5.1 | 72.07 tok/s | 14.98s |
| 04/13/2026, 03:04 | z-ai/glm-5.1 | 70.67 tok/s | 0.63s |
| 04/13/2026, 03:04 | z-ai/glm-5.1 | 56.48 tok/s | 12.05s |
| 04/13/2026, 03:04 | z-ai/glm-5.1 | 63.51 tok/s | 13.84s |
| 04/13/2026, 03:04 | z-ai/glm-5.1 | 52.32 tok/s | 19.14s |
