gpt-4o-mini
Developer: OpenAI
Also known as
GPT-4o Mini by OpenAI is available through 79 API providers on LMSpeed. Compare API pricing from $0.0008 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 133 tok/s.
Compare GPT-4o Mini API pricing across 79 providers. Input prices range from $0.0008 to $75.00 per million input. SWT-API offers the lowest rate at $0.0008/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| SWT-API | gpt-4o-mini | $0.0008 | $0.0030 | — |
| LLM API | gpt-4o-mini-free | $0.010 | $0.010 | — |
| 碳硅生命体 | gpt-4o-mini | $0.018 | $0.072 | — |
 OAPI UK | gpt-4o-mini | $0.075 | $0.300 | — |
| GankInterview LLM | gpt-4o-mini | $0.075 | $0.300 | — |
 ModelPool | gpt-4o-mini | $0.090 | $0.360 | — |
| 10dian-API | gpt-4o-mini | $0.100 | $0.200 | 128.3 t/s |
| 10dian-API | gpt-4o-mini-2024-07-18 | $0.100 | $0.100 | 132.7 t/s |
 KKSJ-AI | gpt-4o-mini | $0.135 | $0.540 | — |
| KKSJ-AI | gpt-4o-mini-2024-07-18 | $0.135 | $0.540 | — |
 OpenRouter Fans | openai/gpt-4o-mini | $0.140 | $0.540 | — |
| Seamee API | openai/gpt-4o-mini | $0.150 | $0.595 | — |
| AAAI | gpt-4o-mini | $0.150 | $0.600 | — |
| AAAI | gpt-4o-mini-2024-07-18 | $0.150 | $0.600 | — |
 SanShui API | gpt-4o-mini | $0.150 | $0.600 | — |
| SanShui API | gpt-4o-mini-2024-07-18 | $0.150 | $0.600 | — |
 柏拉图AI | gpt-4o-mini | $0.150 | $0.600 | — |
| 柏拉图AI | gpt-4o-mini-2024-07-18 | $0.150 | $0.600 | — |
 UnifyLLM | gpt-4o-mini | $0.150 | $0.600 | — |
| UnifyLLM | gpt-4o-mini-2024-07-18 | $0.150 | $0.600 | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
Showing 1-12 of 12 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
10dian-API gpt-4o-mini-2024-07-18 | 132.67 tok/s | 1.17s | 5 |
 AZ Rixgpt-4o-mini-2024-07-18 | 130.72 tok/s | 0.60s | 5 |
gpt-4o-mini | 128.27 tok/s | 1.11s | 10 |
 gpt-4o-mini | 101.71 tok/s | 0.68s | 5 |
GPT-4o-mini | 95.24 tok/s | 4.75s | 5 |
gpt-4o-mini | 94.27 tok/s | 1.92s | 5 |
 gpt-4o-mini | 83.33 tok/s | 1.34s | 2 |
 gpt-4o-mini | 80.53 tok/s | 2.59s | 158 |
 gpt-4o-mini | 79.05 tok/s | 13.67s | 10 |
 gpt-4o-mini | 78.22 tok/s | 1.05s | 5 |
gpt-4o-mini-2024-07-18 | 73.54 tok/s | 10.04s | 5 |
gpt-4o-mini-2024-07-18 | 51.82 tok/s | 19.51s | 10 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/11/2026, 02:05 | gpt-4o-mini-2024-07-18 | 6.54 tok/s | 32.09s |
| 04/11/2026, 02:05 | gpt-4o-mini-2024-07-18 | 18.39 tok/s | 31.52s |
| 04/11/2026, 02:05 | gpt-4o-mini-2024-07-18 | 17.91 tok/s | 31.71s |
| 04/11/2026, 02:05 | gpt-4o-mini-2024-07-18 | 143.21 tok/s | 1.06s |
| 04/11/2026, 02:05 | gpt-4o-mini-2024-07-18 | 16.35 tok/s | 31.87s |
| 04/01/2026, 14:01 | gpt-4o-mini-2024-07-18 | 9.08 tok/s | 31.43s |
| 04/01/2026, 14:01 | gpt-4o-mini-2024-07-18 | 102.56 tok/s | 1.79s |
| 04/01/2026, 14:01 | gpt-4o-mini-2024-07-18 | 106.51 tok/s | 1.09s |
| 04/01/2026, 14:01 | gpt-4o-mini-2024-07-18 | 3.20 tok/s | 31.25s |
| 04/01/2026, 14:01 | gpt-4o-mini-2024-07-18 | 94.46 tok/s | 1.29s |
| 03/30/2026, 08:46 | gpt-4o-mini | 8.97 tok/s | 31.97s |
| 03/30/2026, 08:46 | gpt-4o-mini | 97.80 tok/s | 31.94s |
| 03/30/2026, 08:46 | gpt-4o-mini | 18.30 tok/s | 31.23s |
| 03/30/2026, 08:46 | gpt-4o-mini | 116.51 tok/s | 1.62s |
| 03/30/2026, 08:46 | gpt-4o-mini | 97.22 tok/s | 2.69s |
| 03/18/2026, 08:57 | gpt-4o-mini | 108.46 tok/s | 1.73s |
| 03/18/2026, 08:57 | gpt-4o-mini | 99.74 tok/s | 31.50s |
| 03/18/2026, 08:57 | gpt-4o-mini | 75.85 tok/s | 1.41s |
| 03/18/2026, 08:57 | gpt-4o-mini | 76.68 tok/s | 1.51s |
| 03/18/2026, 08:57 | gpt-4o-mini | 90.97 tok/s | 1.14s |
