llama-4-scout
Developer: Meta
Also known as
Llama 4 Scout by Meta is available through 20 API providers on LMSpeed. Compare API pricing from $0.0002 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 75 tok/s.
Compare Llama 4 Scout API pricing across 20 providers. Input prices range from $0.0002 to $75.00 per million input. 91VIP offers the lowest rate at $0.0002/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 91VIP | llama-4-scout | $0.0002 | $0.0000 | — |
| Futureppo | llama-4-scout | $0.0002 | $0.0000 | — |
| 素墨API | llama-4-scout | $0.010 | $0.010 | — |
 HotaruAPI | llama-4-scout | $0.080 | $0.300 | — |
| Seamee API | llama-4-scout | $0.080 | $0.300 | — |
 OpenRouter Fans | meta-llama/llama-4-scout | $0.080 | $0.300 | — |
| Seamee API | meta-llama/llama-4-scout | $0.085 | $0.460 | — |
| AAAI | llama-4-scout | $0.200 | $0.630 | — |
 V-API | llama-4-scout | $0.200 | $0.630 | — |
| 钱多多 API | llama-4-scout | $0.280 | $0.882 | — |
 柏拉图AI | llama-4-scout | $0.300 | $0.945 | — |
 毫秒API | llama-4-scout | $0.300 | $0.945 | — |
| llama-4-scout | $0.300 | $0.945 | — | |
| SWT-API | llama-4-scout | $0.375 | $0.375 | — |
| 钱多多 API | meta-llama/llama-4-scout | $1.00 | $3.00 | — |
| Synapse | llama-4-scout | $1.00 | $1.00 | — |
 艾可API | meta-llama/llama-4-scout | $2.50 | $10.00 | — |
 天絮 API | meta/llama-4-scout | $75.00 | $75.00 | — |
 IXIOCCAPI | meta-llama/llama-4-scout | $75.00 | $75.00 | — |
| Llama-4-Scout | $75.00 | $75.00 | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
Showing 1-1 of 1 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
meta/llama-4-scout | 75.00 tok/s | 1.62s | 10 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/23/2025, 09:52 | meta/llama-4-scout | 74.98 tok/s | 1.70s |
| 04/23/2025, 09:52 | meta/llama-4-scout | 70.62 tok/s | 1.75s |
| 04/23/2025, 09:52 |
meta/llama-4-scout |
71.32 tok/s |
1.98s |
| 04/23/2025, 09:52 | meta/llama-4-scout | 77.48 tok/s | 1.64s |
| 04/23/2025, 09:52 | meta/llama-4-scout | 76.67 tok/s | 1.69s |
| 04/07/2025, 09:11 | meta/llama-4-scout | 74.55 tok/s | 1.70s |
| 04/07/2025, 09:11 | meta/llama-4-scout | 73.30 tok/s | 1.52s |
| 04/07/2025, 09:11 | meta/llama-4-scout | 72.12 tok/s | 1.46s |
| 04/07/2025, 09:11 | meta/llama-4-scout | 82.21 tok/s | 1.53s |
| 04/07/2025, 09:11 | meta/llama-4-scout | 76.72 tok/s | 1.24s |
