N1N provides API access to a wide range of AI models including GPT-4, Claude 3, Gemini, and others for text, image, and video generation.
Performance Stats
Avg Speed
97.63t/s
Latency
5.41s
Total Tests
155
Models
24
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gemini-2.5-flash-lite | 297.64 t/s | 0.52s | 5 |
| gemini-2.5-flash | 274.40 t/s | 8.21s | 5 |
| gemini-3-flash-preview | 161.17 t/s | 9.29s | 15 |
| gemini-2.0-flash | 140.17 t/s | 0.86s | 15 |
| grok-4.1-fast | 105.67 t/s | 2.73s | 10 |
| gemini-2.5-pro | 105.53 t/s | 16.40s | 5 |
| gemini-3-pro-preview | 102.23 t/s | 14.82s | 15 |
| claude-haiku-4-5-20251001 | 102.03 t/s | 1.41s | 5 |
| glm-4-flash | 78.17 t/s | 1.57s | 20 |
| gpt-4.1-mini | 65.96 t/s | 1.06s | 5 |
| gpt-5.2 | 58.71 t/s | 1.63s | 10 |
| glm-4.6 | 56.02 t/s | 1.36s | 5 |
| glm-4.6 | 56.02 t/s | 1.36s | 5 |
| claude-opus-4-5-20251101 | 52.49 t/s | 2.37s | 5 |
| qwen2.5-vl-72b-instruct | 43.29 t/s | 1.03s | 5 |
| qwen2.5-vl-72b-instruct | 43.29 t/s | 1.03s | 5 |
| qwen2.5-vl-72b-instruct | 43.29 t/s | 1.03s | 5 |
| deepseek-v3.2 | 36.61 t/s | 1.52s | 15 |
| deepseek-v3.2 | 36.61 t/s | 1.52s | 15 |
| grok-4.1 | 28.12 t/s | 1.99s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Feb 13, 06:45 PM | gemini-3-pro-preview | 95.22 t/s | 12.73s |
| Feb 13, 06:33 PM | qwen2.5-72b-instruct | 22.88 t/s | 1.08s |
| Feb 13, 06:32 PM | glm-4-flash | 236.43 t/s | 1.07s |
| Feb 7, 11:30 AM | glm-4-flash | 25.50 t/s | 1.59s |
| Feb 7, 11:25 AM | gemini-2.5-pro | 105.53 t/s | 16.40s |
| Feb 7, 11:13 AM | glm-4-flash | 30.55 t/s | 1.52s |
| Feb 7, 10:56 AM | gemini-2.5-flash | 274.40 t/s | 8.21s |
| Feb 7, 10:53 AM | deepseek-v3.2 | 34.24 t/s | 1.22s |
| Jan 30, 07:34 PM | gpt-5.2 | 56.26 t/s | 1.75s |
| Jan 30, 07:24 PM | glm-4.6 | 56.02 t/s | 1.36s |