glm-5
Developer: Zhipu AI
Also known as
GLM-5 by Zhipu AI is available through 84 API providers on LMSpeed. Compare API pricing from $0.0001 to $6241577.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 102 tok/s.
Compare GLM-5 API pricing across 83 providers. Input prices range from $0.0001 to $6241577.00 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 | Free | Free | — |
| OptAI | glm-5 | $0.0001 | $0.0001 | — |
| 91VIP | glm-5 | $0.0014 | $0.0033 | — |
| Futureppo | glm-5 | $0.0014 | $0.0033 | — |
| 素墨API | glm-5 | $0.010 | $0.010 | — |
| CookingAI | glm-5 | $0.010 | $0.010 | — |
| 紫脑喵 | glm-5 | $0.010 | $0.010 | — |
 ai.api.xn--fiqs8s | glm-5 | $0.030 | $0.030 | — |
 丸美小沐写作 | glm-5 | $0.030 | $0.030 | — |
 VVCode | glm-5 | $0.075 | $0.240 | — |
 GLM BigModel Relay | glm-5 | $0.100 | $0.320 | — |
 星见雅 API | GLM-5 | $0.100 | $0.100 | 23.1 t/s |
| 人人 API | glm-5 | $0.250 | $0.450 | — |
 小天公益站 | GLM-5 | $0.280 | $1.14 | — |
| 小天公益站 | glm-5 | $0.280 | $1.14 | — |
 UniAiX | glm-5 | $0.329 | $1.48 | — |
| SWT-API | glm-5 | $0.375 | $0.375 | — |
 OpenRouter Fans | Pro/zai-org/GLM-5 | $0.500 | $2.25 | — |
| EasyMore | glm-5 | $0.548 | $2.47 | — |
| OpenRouter Fans | z-ai/glm-5 | $0.580 | $2.60 | — |
Pricing data from provider public APIs
GLM-5 is free to use through 1 provider with no per-token charges. These providers offer free API credits or a free tier:
| Provider | Speed (t/s) |
|---|---|
| 我不是AI神 | — |
Compare speed and latency performance across all API providers.
Showing 1-14 of 14 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 Krioraglm-5 | 101.67 tok/s | 8.79s | 5 |
accounts/fireworks/models/glm-5 | 78.26 tok/s | 13.33s | 5 |
 glm-5 | 63.64 tok/s | 21.68s | 10 |
 ollama/glm-5 | 50.42 tok/s | 17.62s | 5 |
 Pro/zai-org/GLM-5 | 43.56 tok/s | 27.77s | 20 |
z-ai/glm-5 | 42.85 tok/s | 24.10s | 15 |
GLM-5 | 40.53 tok/s | 18.11s | 10 |
 glm-5 | 39.53 tok/s | 20.57s | 30 |
 glm-5 | 36.73 tok/s | 26.39s | 40 |
glm-5 | 36.15 tok/s | 21.94s | 5 |
 glm-5 | 34.70 tok/s | 23.13s | 10 |
glm-5 | 30.46 tok/s | 26.41s | 5 |
glm-5 | 29.62 tok/s | 47.00s | 5 |
 GLM-5 | 23.06 tok/s | 39.70s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/15/2026, 14:03 | z-ai/glm-5 | 35.80 tok/s | 34.25s |
| 04/15/2026, 14:03 | z-ai/glm-5 | 27.10 tok/s | 37.02s |
| 04/15/2026, 14:03 | z-ai/glm-5 | 30.37 tok/s | 35.07s |
| 04/15/2026, 14:03 | z-ai/glm-5 | 62.64 tok/s | 7.41s |
| 04/15/2026, 14:03 | z-ai/glm-5 | 42.82 tok/s | 20.17s |
| 04/13/2026, 09:22 | GLM-5 | 52.30 tok/s | 12.53s |
| 04/13/2026, 09:22 | GLM-5 | 30.17 tok/s | 47.93s |
| 04/13/2026, 09:22 | GLM-5 | 22.19 tok/s | 48.21s |
| 04/13/2026, 09:22 | GLM-5 | 3.34 tok/s | 43.34s |
| 04/13/2026, 09:22 | GLM-5 | 7.28 tok/s | 46.50s |
| 04/13/2026, 08:25 | glm-5 | 38.13 tok/s | 26.69s |
| 04/13/2026, 08:25 | glm-5 | 23.86 tok/s | 45.65s |
| 04/13/2026, 08:25 | glm-5 | 28.02 tok/s | 34.36s |
| 04/13/2026, 08:25 | glm-5 | 20.23 tok/s | 16.86s |
| 04/13/2026, 08:25 | glm-5 | 33.34 tok/s | 32.32s |
| 04/12/2026, 15:27 | z-ai/glm-5 | 49.40 tok/s | 13.14s |
| 04/12/2026, 15:27 | z-ai/glm-5 | 23.93 tok/s | 44.44s |
| 04/12/2026, 15:27 | z-ai/glm-5 | 26.82 tok/s | 33.79s |
| 04/12/2026, 15:27 | z-ai/glm-5 | 10.47 tok/s | 26.33s |
| 04/12/2026, 15:27 | z-ai/glm-5 | 66.27 tok/s | 13.76s |
