18-04-2024 New Gen LLM APIs Launch

We’re thrilled to share a major upgrade to our text generation LLM APIs! ⚡️

We've optimised our LLM serving engine to achieve upto 98% cost effectiveness 🤯 compared to our previous APIs and are excited to release early access to this new innovative LLM API service in Beta!

With our new serving engine, you can expect:
✅ Synchronous responses, ensuring quick and efficient interactions.
✅ Fully compatible with OpenAI formats.
✅ 100% transparent token-based pricing.

Here’s a list of supported models in the new API service:

  1. TinyLlama/TinyLlama-1.1B-Chat-v1.0
  2. Microsoft/phi-2
  3. HuggingFaceH4/zephyr-7b-beta
  4. Mistralai/Mistral-7B-Instruct-v0.2

More models coming soon 🚀

Read in detail about the New-Gen LLM API service here:

Resources to get started:

- Apply for beta access (ignore if already done):

- Try out new LLM APIs: