The NVIDIA Llama 3.1 70B Instruct FP8 model is the quantized version of the Meta's Llama 3.1 70B Instruct model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Llama 3.1 70B Instruct FP8 model is quantized with TensorRT Model Optimizer. This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA (Meta-Llama-3.1-70B-Instruct) Model Card. **Input Type(s):** Text **Input Format(s):** String **Input Parameters:** Sequences **Other Properties Related to Input:** Context length up to 128K

译文排队中 · 当前显示来源原文

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Llama-3.1-8B-Instruct-FP8

NVIDIA

The NVIDIA Llama 3.1 8B Instruct FP8 model is the quantized version of the Meta's Llama 3.1 8B Instruct model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Llama 3.1 8B Instruct FP8 model is quantized with TensorRT Model Optimizer. This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA (Meta-Llama-3.1-8B-Instruct) Model Card. **Input Type(s):** Text **Input Format(s):** String **Input Parameters:** Sequences **Other Properties Related to Input:** Context length up to 128K

译文排队中 · 当前显示来源原文

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Llama-3.1-8B-Instruct-NVFP4

NVIDIA

The NVIDIA Llama 3.1 8B Instruct FP4 model is the quantized language model of the Meta's Llama 3.1 8B model, which is an auto-regressive language model. For more information, please check here. This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA (Llama-3.1-8B-Instruct) Model Card. GOVERNING TERMS: Use of this model is governed by the NVIDIA Open Model License. ADDITIONAL INFORMATION: Llama3 Community License Agreement. Built with Llama.

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Llama-3.1-8B-Medusa-FP8

NVIDIA

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Llama-3.1-Minitron-4B-Depth-Base

NVIDIA

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

NVIDIA

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct

NVIDIA

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基础资料已收录 · 缺失资料后续补充

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

NVIDIA

Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model (LLM) which is a derivative of nvidia/Llama-3.1-Minitron-4B-Width-Base, which is created from Llama 3.1 8B using our LLM compression technique and offers improvements in model accuracy and efficiency. It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. Llama-3.1-Nemotron-Nano-4B-v1.1 is a model which offers a great tradeoff between model accuracy and efficiency. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K. This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and RPO checkpoints

译文排队中 · 当前显示来源原文

文本生成

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

COST EXPLORER

好模型，也要算好成本。

费用分析

调整月度 Token 用量，直观比较不同模型的预估 API 开支。

每月输入 Token 10 M每月输出 Token 2 M1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价

使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。

MODEL HANDBOOK

读懂模型，再做选择

选型与常见问题

API 价格应该怎么比较？+

先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。

开放权重，就代表可以免费商用吗？+

不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。

排行榜第一，就是最适合我的模型吗？+

榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。

找到适合你的 AI 模型。

探索 AI 模型 1050

Llama-2-13B-DMC-8x

Llama-2-7B-DMC-4x

Llama-2-7B-DMC-8x

Llama-3.1-405B-Instruct-FP8

Llama-3.1-405B-Instruct-NVFP4

Llama-3.1-70B-Instruct-FP8

Llama-3.1-8B-Instruct-FP8

Llama-3.1-8B-Instruct-NVFP4

Llama-3.1-8B-Medusa-FP8

Llama-3.1-Minitron-4B-Depth-Base

Llama-3.1-Minitron-4B-Width-Base

llama-3.1-nemoguard-8b-content-safety

llama-3.1-nemoguard-8b-topic-control

Llama-3_1-Nemotron-51B-Instruct

Llama-3.1-Nemotron-70B-Instruct

Llama-3.1-Nemotron-70B-Instruct-HF

Llama-3.1-Nemotron-70B-Reward

Llama-3.1-Nemotron-70B-Reward-HF

Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct

Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct

Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct

Llama 3.1 Nemotron Instruct 70B

Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)

Llama-3.1-Nemotron-Nano-4B-v1.1

暂未找到匹配模型

好模型，也要算好成本。

读懂模型，再做选择

资讯看趋势，工具提效率，模型筑可能。