Llama-3.1 系列
由 Meta 提供 · 共 17 个变体
| 模型 | 变体 | 定位 | 上下文 | 速度(t/s) | 输入价格/M | 输出价格/M | 思考 | 能力 |
|---|---|---|---|---|---|---|---|---|
| llama-3.1-405b-instruct — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| Llama-3.1-8B-Instruct — 免费对话模型 | 标准 | - | 131.1K | - | ¥0.0000 | ¥0.0000 | - | |
| Llama 3.1 70B Versatile — 极速推理模型 | 标准 | Groq LPU 极速推理，Meta开源模型 | 131.1K | 250~250 | $0.5900 | $0.7900 | - | |
| Llama 3.1 8B Instant — 超高速推理模型 | 标准 | Groq LPU 极速推理，Meta开源模型 | 131.1K | 840~840 | $0.0500 | $0.0800 | - | |
| Meta-Llama-3.1-8B-Instruct-Turbo — 开源对话模型 | 标准 | - | 131.1K | - | $0.1800 | $0.1800 | - | |
| Meta-Llama-3.1-70B-Instruct-Turbo — 开源对话模型 | 标准 | - | 131.1K | - | $0.8800 | $0.8800 | - | |
| Meta-Llama-3.1-405B-Instruct-Turbo — 开源对话模型 | 标准 | - | 131.1K | - | $3.5000 | $3.5000 | - | |
| llama-3.1-8b-instruct — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-70b-instruct — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemotron-safety-guard-8b-v3 — NVIDIA Build | 标准 | Free Endpoint | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemotron-70b-reward — NVIDIA Build | 标准 | Free Endpoint | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemoguard-8b-content-safety — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemoguard-8b-topic-control — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemotron-nano-8b-v1 — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemotron-ultra-253b-v1 — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemotron-nano-4b-v1.1 — NVIDIA Build | 标准 | Downloadable | - | - | $0.0000 | $0.0000 | - | |
| llama-3.1-nemotron-nano-vl-8b-v1 — NVIDIA Build | Vision | Downloadable | - | - | $0.0000 | $0.0000 | - |