llama-3-1-swallow-instruct-v0-1
Developer: Meta
Also known as
Llama 3.1 Swallow Instruct V0.1 by Meta is available through 24 API providers on LMSpeed. Compare API pricing from $0.010 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 19 tok/s.
Compare speed and latency performance across all API providers.
Showing 1-1 of 1 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.04 tok/s | 0.49s | 10 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/01/2026, 08:12 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.05 tok/s | 0.62s |
| 04/01/2026, 08:12 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.06 tok/s | 0.47s |
| 04/01/2026, 08:12 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.05 tok/s | 0.45s |
| 04/01/2026, 08:12 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.06 tok/s | 0.48s |
| 04/01/2026, 08:12 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.06 tok/s | 0.47s |
| 03/31/2026, 10:09 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.03 tok/s | 0.59s |
| 03/31/2026, 10:09 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.04 tok/s | 0.45s |
| 03/31/2026, 10:09 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.04 tok/s | 0.44s |
| 03/31/2026, 10:09 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 18.98 tok/s | 0.47s |
| 03/31/2026, 10:09 | institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1 | 19.04 tok/s | 0.46s |