The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-8x7B outperforms Llama 2 70B on most benchmarks we tested. For full details of this model please read our release blog post. This repo contains weights that are compatible with vLLM serving of the model as well as Hugging Face transformers library. It is based on the original Mixtral torrent release, but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
The performance of Pixtral-12B-2409 compared to multimodal models. All models were re-evaluated and benchmarked through the same evaluation pipeline. We recommend using Pixtral with the vLLM library to implement production-ready inference pipelines with Pixtral. After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can pass text and images or image urls to the model in *instruction-following* mode as follows:
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
**Shieldstral** is a compact **3B-parameter, policy-adaptive multimodal safety classifier**. Instead of predicting a fixed set of moderation categories, Shieldstral evaluates content against a safety policy expressed in **natural language** and returns a single continuous safety score. This makes it a flexible drop-in guardrail for text-only, image-only, and text+image moderation that can be re-targeted to new policies **at inference time, without retraining**. It is built on Ministral-3-3B-Base-2512 with a native Pixtral vision encoder, and produces its verdict from a **single forward pass**. Learn more in our blog post and technical report.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
Timestral is a **family of time series foundation models** for zero-shot forecasting, available in **5M**, **28M**, **123M**, and **209M** parameter versions. This repository contains the 123M checkpoint. >[!Note] > For more information about our Timestral family, go to the main model page: Timestral-209M. Timestral-209M achieves **state-of-the-art zero-shot accuracy** across three major forecasting benchmarks: GIFT-Eval, TIME, and fev-bench.
Timestral is a **family of time series foundation models** for zero-shot forecasting, available in **5M**, **28M**, **123M**, and **209M** parameter versions. This repository contains the 209M checkpoint. Timestral supports univariate and multivariate forecasting, past-only and known-future covariates, and probabilistic predictions across 21 quantiles. It accepts up to 32,768 historical time steps and forecasts up to 1,024 steps in a single forward pass. We’re releasing the source code in our GitHub repository to make it easy to run Timestral and reproduce our benchmark results.
Timestral is a **family of time series foundation models** for zero-shot forecasting, available in **5M**, **28M**, **123M**, and **209M** parameter versions. This repository contains the 28M checkpoint. >[!Note] > For more information about our Timestral family, go to the main model page: Timestral-209M. Timestral-209M achieves **state-of-the-art zero-shot accuracy** across three major forecasting benchmarks: GIFT-Eval, TIME, and fev-bench.
Timestral is a **family of time series foundation models** for zero-shot forecasting, available in **5M**, **28M**, **123M**, and **209M** parameter versions. This repository contains the 5M checkpoint. >[!Note] > For more information about our Timestral family, go to the main model page: Timestral-209M. Timestral-209M achieves **state-of-the-art zero-shot accuracy** across three major forecasting benchmarks: GIFT-Eval, TIME, and fev-bench.
Voxtral Mini is an enhancement of Ministral 3B, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Learn more about Voxtral in our blog post here and our research paper. Voxtral builds upon Ministral-3B with powerful audio understanding capabilities. - **Dedicated transcription mode**: Voxtral can operate in a pure speech transcription mode to maximize performance. By default, Voxtral automatically predicts the source audio language and transcribes the text accordingly - **Long-form context**: With a 32k token context length, Voxtral handles audios up to 30 minutes for transcription, or 40 minutes for understanding - **Built-in Q&A and summarization**: Supports asking questions directly through audio. Analyze audio and generate structured summaries without the need for separate ASR and language models - **Natively multilingual**: Automatic language detection and state-of-the-art performance in the world’s most widely used languages (English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian) - **Function-calling straight from voice**: Enables direct triggering of backend functions, workflows, or API calls based on spoken user intents - **Highly capable at text**: Retains the text understanding capabilities of its language model backbone, Ministral-3B
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
Voxtral Mini 4B Realtime 2602 is a **multilingual, realtime speech-transcription model** and among the first open-source solutions to achieve accuracy comparable to offline systems with a delay of ** = 3600 / 0.8 = 45000`. In theory, you should be able to record with no limit; in practice, pre-allocations of RoPE parameters among other things limits `--max-model-len`. For the best user experience, we recommend to simply instantiate vLLM with the default parameters which will automatically set a maximum model length of 131072 (~ca. 3h). - We strongly recommend using websockets to set up audio streaming sessions. For more info on how to do so, check Usage. - We recommend using a delay of 480ms as we found it to be the sweet spot of performance and low latency. If, however, you want to adapt the delay, you can change the `"transcription_delay_ms": 480` parameter in the tekken.json file to any multiple of 80ms between 80 and 1200, as well as 2400 as a standalone value. We compare Voxtral Mini 4B Realtime to similar models - both offline models and realtime. Voxtral Mini 4B Realtime is competitive to leading offline models and shows significant gains over existing open-source realtime solutions. > [!Warning] > Due to its novel architecture, Voxtral Realtime is currently only support in vLLM. We very much welcome community contributions > to add the architecture to Transformers and Llama.cpp.
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...
> [!WARNING] > This model checkpoint is provided as-is and might not be up-to-date. Please use the corresponding version from https://huggingface.co/mistralai org 1. Download original weights from https://models.mistralcdn.com/mistral-7b-v0-2/mistral-7B-v0.2.tar 2. Convert with https://github.com/huggingface/transformers/blob/main/src/transformers/models/mistral/convert_mistral_weights_to_hf.py 3. You may need to copy the tokenizer.model from Mistral-7B-Instruct-v0.2 repo.
Transformers compatible pixtral checkpoints. Make sure to install from source or wait for v4.45! You can also use a chat template to format your chat history for Pixtral. Make sure that the `images` argument to the `processor` contains the images in the order that they appear in the chat, so that the model understands where each image is supposed to go. ----------- From transformers>=v4.48, you can also pass image url or local path to the conversation history, and let the chat template handle the rest. Chat template will load the image for you and return inputs in `torch.Tensor` which you can pass directly to `model.generate()`.
Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository. Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Cost analysis
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD 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
Selection guide & FAQ
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.
