Blog

Bytez

✨ Access 40k+ open source and proprietary AI models through a standard API. Achieve GPU-backed performance at CPU pricing ✨

Overview

Retrieve a list of available models for various tasks. Use the query parameter `task` to filter by task type, e.g. `chat`.

Models

Install our API libraries and run inference in seconds

Quickstart

Get your API key and access `open source` and `closed-source` models through a standard format

API Keys

Download or Install Libraries to Access Bytez

Libraries

API Status

Generate images using Bytez API with `base64` or `URL` inputs.

Image Generation

Generate `text` and `vector` embeddings with the Bytez API.

Embeddings

Execute `code` or `actions` based on model-generated outputs

Function Calling

LangChain

An Overview of CRUD Operations & Unified Input Schemas for SOTA AI models

Retrieve a list of tasks supported by the platform.

Tasks

Retrieve a list of available model clusters.

Clusters

Send requests to any OpenAI model by specifying the `{model}` placeholder in the path.

OpenAI

Send requests to any Google model by specifying the `{model}` placeholder in the path.

Google

Send requests to any Cohere model by specifying the `{model}` placeholder in the path.

Cohere

Send requests to any Anthropic model by specifying the `{model}` placeholder in the path.

Anthropic

Send requests to any Mistral model by specifying the `{model}` placeholder in the path.

Mistral

Generate text using the Phi-3-mini-4k-instruct model.

Chat + Text

Analyze images using the Llama-3.2-11B-Vision-Instruct model.

Chat + Vision

Analyze audio using the Qwen2-Audio-7B-Instruct model.

Chat + Audio

Analyze video using the LLaVA-NeXT-Video-7B-hf model.

Chat + Video

Run the `camembert-base` model to predict masked tokens in the input text.

Fill Mask

Run the `mms-tts-eng` model to convert text into speech.

Text-to-Speech

Run the `musicgen-melody` model to convert text into audio.

Text-to-Audio

Run the `stable-diffusion-xl-base-1.0` model to generate images from text.

Text-to-Image

Run the `En-Fr_Translation_Model` to translate English text to French.

Translation

Run the `bart-base-cnn` model to summarize input text.

Summarization

Run the `specter2_base` model to extract features from input text.

Feature Extraction

Run the `distilbert-base-uncased-finetuned-sentiment-amazon` model to classify input text.

Text Classification

Run the `mn-xlm-roberta-base-named-entity` model to perform named entity recognition.

Token Classification

Run the `mt0-small` model to generate text-to-text transformations.

Text2Text Generation

Run the `gpt2` model to generate text from an input prompt.

Text Generation

Generate captions for images using the `caption-gen` model.

Image to Text

Classify images into categories using the `vit-base-cats-vs-dogs` model.

Image Classification

Perform image segmentation using the `deeplabv3-mobilevit-small` model.

Image Segmentation

Estimate depth in images using the `Depth-Anything-V2-Base-hf` model.

Depth Estimation

Detect objects in an image using the `aisak-detect` model.

Object Detection

Generate a mask for the given image using the `skinsam` model.

Mask Generation

Extract features from an image using the `dinov2-base` model.

Image Feature Extraction

Answer a question given a context using the `xlm-roberta-base-finetune-qa` model.

Question Answering

Answer a question based on the content of a document using the `CQI_Visual_Question_Awnser_PT_v0` model.

Document Question Answering

Answer a question based on an image using the `Vilt_fine_tune_2000` model.

Visual Question Answering

Detect objects in an image using the `owlv2-base-patch16-finetuned` model.

Zero Shot Object Detection

Classify images into candidate labels using the `clip-hugging-face-finetuned` model.

Zero Shot Image Classification

Classify text into candidate labels using the `DistilBERT_eco_ZeroShot` model.

Zero Shot Classification

Our pricing follows standard Cloud Compute costs you know and are familiar with

Pricing

Learn how to implement streaming with Bytez API

Streaming

The story, mission, and community behind Bytez

About

Solutions

Integrations & Roadmap

Bytez Platform

Discord

API Documentation

API Reference

Company

Support

Generate text with chat models using structured inputs and streaming.

Text

Use chat + vision models (`image-as-input`) to generate text-based responses.

Vision

Use chat + audio models (`audio-as-input`) to transcribe and analyze audio.

Audio

Use chat + video mpdels (`video-as-input`) to generate insightful responses.

Video

Audio Classification

Automatic Speech Recognition

Image-to-Text

Sentence Similarity

Text-to-Text Generation

Text-to-Video

Unconditional Image Generation

Video Classification

Create an auto-scaling cluster for the specified model.

Create Cluster

Use POST to run any open source model. This will automatically create an auto-scaling cluster of the model and run inference on that cluster.

Resources

Blog

Bytez Powers NeurIPS 2024