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。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 85001
llama-3-70b
Meta70 亿参数的 Meta Llama 3 模型，适用于多种对话应用。
Translation queued · Showing source text
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llama-3-8b
Meta7亿参数的最新Meta Llama 3模型。
Translation queued · Showing source text
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LLaMA-MoE-v1-3_0B-2_16
llama-moe❤️ This repo contains the model `LLaMA-MoE-v1-3.0B (2/16)`, which activates 2 out of 16 experts (3.0B parameters). This model is NOT fine-tuned by instruction pairs, so it may not be good enough to act like a chatbot. 📢 LLaMA-MoE is a series of Mixture-of-Expert (MoE) models based on LLaMA-2. You can find the code for training this model at this repo. 💎 This series of models are obtained by partitioning original LLaMA FFNs into experts and further continual pre-training. The total model size is only 6.7B parameters, which is very convenient for deployment and research usage. More details could be found at our technical report.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LLaMA-MoE-v1-3_5B-2_8
llama-moe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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tiny-random-Llama-3
llamafactory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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tiny-random-Llama-3-lora
llamafactory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。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tiny-random-Llama-3-valuehead
llamafactory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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tiny-random-Llama-4
llamafactory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。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tiny-random-qwen2.5
llamafactory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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tiny-random-qwen3
llamafactoryThe model is for debugging, which is a tiny but complete version of Qwen/Qwen3-4B-Instruct-2507: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗potion-multilingual-128M-nf4
llamaindex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。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗vdr-2b-multi-v1
llamaindexvdr-2b-multi-v1 is a multilingual embedding model designed for visual document retrieval across multiple languages and domains. It encodes document page screenshots into dense single-vector representations, this will effectively allow to search and query visually rich multilingual documents without the need for any OCR, data extraction pipelines, chunking... The model uses bf16 tensors and allocates ~4.4GB of VRAM when loaded. You can easily run inference and generate embeddings using 768 image patches and a batch size of 16 even on a cheap NVIDIA T4 GPU. This table reports the memory footprint (GB) under conditions of different batch sizes with HuggingFace Transformers and maximum 768 image patches. The model is based on MrLight/dse-qwen2-2b-mrl-v1 and it was trained on the new vdr-multilingual-train dataset that consinsists of 500k high quality, multilingual query image pairs. It was trained for 1 epoch using the DSE approach, with a batch size of 128 and hard-mined negatives.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗LlamaGuard-7b
llamas-community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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bakLlava-v1-hf
llava-hf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。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llama3-llava-next-8b-hf
llava-hf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。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llava-1.5-13b-hf
llava-hfBelow is the model card of Llava model 13b, which is copied from the original Llava model card that you can find here. Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: [](https://colab.research.google.com/drive/1qsl6cd2c8gGtEW1xV5io7S8NHh-Cp1TV?usp=sharing) **Model type:** LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llava-1.5-7b-hf
llava-hfBelow is the model card of Llava model 7b, which is copied from the original Llava model card that you can find here. Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: [](https://colab.research.google.com/drive/1qsl6cd2c8gGtEW1xV5io7S8NHh-Cp1TV?usp=sharing) Or check out our Spaces demo! [](https://huggingface.co/spaces/llava-hf/llava-4bit)
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llava-interleave-qwen-0.5b-hf
llava-hf**Model type:** LLaVA Interleave is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: Qwen/Qwen1.5-7B-Chat **Primary intended uses:** The primary use of LLaVA-Next Interleave is research on large multimodal models and chatbots. This is only for research exploration, and prohibited for commercial usage. **Primary intended users:** The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗llava-interleave-qwen-7b-hf
llava-hf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。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.