Find LLM and Text2Image APIs to use for your next project
For developers seeking to use LLMs in a programmatic manner, they need to find API providers for various models. While OpenAI provides APIs for ChatGPT and GPT4 LLMs, there are many other providers of APIs for open source and other proprietary models.
For developers seeking to use LLMs in a programmatic manner, they need to find API providers for various models.
While OpenAI provides APIs for ChatGPT and GPT4 LLMs, there are many other providers of APIs for open source and other proprietary models.
There are many providers out there but in the video above, Harsh Singhal talks about the following providers.
TextSynth provides access to large language or text-to-image models such as Llama2, Falcon, GPT-J, GPT-NeoX, Flan-T5, M2M100, CodeGen, Stable Diffusion thru a REST API and a playground. They can be used for example for text completion, question answering, classification, chat, translation and image generation.
TextSynth employs custom inference code to get faster inference (hence lower costs) on standard GPUs and CPUs. The site was founded in 2020 and was among the first to give access to the GPT-2 language model.
The basic service is free but rate limited. Users wishing no limitation can pay a small amount per request (see their pricing). If you wish custom support, you can contact them at contact at textsynth dot com.
The creator of TextSynth is also the creator of ffmpeg and QEMU.
Anyscale Endpoints offers the best open-source large language models (LLMs) as fully managed API endpoints. This allows you to focus on building applications powered by LLMs without the need to worry about the underlying infrastructure.
- Ease of use: Our platform provides simple APIs to query and, soon, fine-tune LLMs.
- Fully managed: With features such as auto-scaling and pay-as-you-go, we keep the models up and running so you don't have to.
Their pricing is very attractive and for the Llama2 70B parameter model they charge 1$ for 1M tokens.
Together AI
Together AI empowers you to initiate inference VMs, supporting a diverse range of more than 50 models across chat, language, code, and image functionalities.
Their research team is behind innovations that enable distributed optimization, faster inference, and other boosts to performance.
They have also created RedPajama, a set of leading open-source foundation models and datasets, along with OpenChatKit and GPT-JT.
