IA

Inworld Compute

Infrastructure service

by Inworld AI

Dedicated NVIDIA B200 GPUs for high-volume realtime workloads such as LLM inference, dedicated TTS serving and custom model hosting, with Kubernetes access or Inworld-managed deployment, and deployed models routable through Inworld Router.

Find alternatives to Inworld Compute

What it does

• Model inference

Features 6

• Dedicated deploymentsReserved capacity and your own model ID with no queueing behind other customers.
• Bring your own modelUpload weights or point to a repo and run the model on the same engine and API as Inworld's.
• Fine-tuning on your trafficFine-tunes open models on a customer's production conversations.
• Drafts tuned on your trafficDraft models trained on a customer's own requests to speed up decoding.
• Kernels and enginesOptimizes the attention step, KV-cache router or serving backend for the customer's model.
• Regions and dataHosting in US, Europe, India or Asia Pacific, with zero data retention on hosted models.

Sources

Pricing

Official documentation · 11 Oct 2026

"From $5 per GPU hour"; example "B200 x4 ... $5/GPU/hr". No free allowance.

Description

Official documentation · 11 Oct 2026

"Dedicated NVIDIA B200 GPUs for custom, high-volume realtime workloads. Run any model with Kubernetes access or let us handle deployment. Integrates with Realtime TTS, STT, Router, and Realtime API." "Dedicated GPU capacity for LLM inference, dedicated TTS serving, custom model hosting"; "Deploy a model and it appears in Inworld Router".

What it does

Official documentation · 11 Oct 2026

Serving models on dedicated GPUs.

Sold within

Official documentation · 11 Oct 2026

The page carries its own rate ("From $5 per GPU hour") and is bought on its own; it integrates with, but does not require, the other Inworld products.

Name

Official documentation · 11 Oct 2026

Page heading "Inworld Compute"; "Why Inworld Compute".

URL

Official documentation · 11 Oct 2026

Product page "GPU Compute: NVIDIA B200 GPUs Available Now".

Deployment

Official documentation · 11 Oct 2026

Dedicated GPUs operated by Inworld for one customer, with "Kubernetes access" or managed deployment.

Interfaces

Official documentation · 11 Oct 2026

Kubernetes access to the GPUs, or a managed deployment served at "api.inworld.ai/v1/chat/completions".

Intended for

Official documentation · 11 Oct 2026

Teams with "custom, high-volume realtime workloads".

Also from Inworld AI

• Realtime TTS API service

  Text-to-speech API (Realtime TTS-2 and TTS-2 Flash) with voice cloning and voice design, billed per million characters.

• Realtime STT API service

  Speech-to-text API (Inworld STT-1) that transcribes streaming or complete audio in 30+ languages with turn detection, returning voice-profile signals for emotion, vocal style, accent, age and pitch alongside the transcript.

• Realtime API API service

  Speech-to-speech voice-agent API in which one WebSocket session runs Inworld speech recognition with voice profiling, a chosen LLM from 100+ with tool calling and turn detection, and Realtime TTS-2 voice output.

• Realtime Router Platform

  OpenAI-compatible LLM gateway that sends each request to one of 100+ models from OpenAI, Anthropic, Google and others by rules on user attributes, context, A/B splits or cost, with failover and provider rates passed through at zero markup.

• Inworld Inference Model API

  Inworld Inference provides API access to text, image, video and decision models.

Open Inworld AI in the directory

Something wrong here? Send a correction — quote this product id: inworld-compute.