AMOD Product Information

AMOD — AI models on demand is a platform that lets you deploy and scale state-of-the-art Large Language Models (LLMs) quickly for business use. It supports multiple model families (e.g., Meta Llama, Anthropic Claude, Amazon Titan, Mistral, Mixtral, etc.), diverse API schemas, and on-demand deployment with auto-scaling. The service emphasizes easy integration, flexible schemas, and access to both active-offerings and on-prem options through a transparent pricing structure.


How AMOD Works

  1. Choose from available models. Access multiple versions of leading LLMs (e.g., Meta Llama, Anthropic Claude, Amazon Titan, and more).
  2. Choose API schema. Select the desired API schema for your integrations; each model endpoint can use any supported schema.
  3. Deploy and connect. Deploy a model, then connect to it via a live endpoint that scales automatically. Documentation is available to assist migration and integration.

Models and Capabilities

  • Llama 3.2 (3B) — Instruct Text: 131k context window; text generation, code generation, rich text formatting, multilingual support, on-device processing, private and secure, edge deployment, low latency.
  • Llama 3 (70B) — Instruct Text: 128k; strong instruction following, advanced reasoning, multilingual translation.
  • Amazon Titan Text G1 Express — Text: 8k; text generation, code generation, instruction following.
  • Mistral Large (24.02) — Text: 32k; complex reasoning & analysis, text generation, RAG, agents.
  • Mixtral 8x7B — Instruct Text: 32k; complex reasoning & analysis, text generation.
  • Anthropic Claude 3 (Haiku) — Text & Vision: 200k; image-to-text, conversation, chat-optimized.
  • Anthropic Claude 3.5 (Sonnet) — Text & Vision: 200k; image-to-text, conversation, chat-optimized.
  • Other supported models include Meta Llama 3, Claude 3, Haiku, Claude 3.5, Sonnet, Amazon Titan, Mistral, and custom models.

Pricing is tiered with transparency and flexibility across Hobbyist, Pro, and Enterprise plans, including options for unlimited deployments and on-prem/offline use where applicable.


Pricing Plans (Overview)

  • Hobbyist: From $19.99/month; try free for 14 days. Access to select models.
  • Pro: From $49.99/month; access to a broader set of models, including more capable variants.
  • Enterprise: Local, offline, on-prem options; contact sales for custom arrangements.

Secure payments are processed via Stripe. The platform emphasizes scalable deployments and cost-conscious choices through a clear cost comparison.


How It Works (Summary)

  • Select model(s) and API schema.
  • Deploy to a live endpoint with automatic scaling.
  • Use the deployed model for your applications via standard API calls.

Core Features

  • Access to multiple leading LLM families (Meta Llama, Anthropic Claude, Amazon Titan, Mistral, Mixtral, etc.)
  • Flexible API schema selection per model endpoint
  • Quick deployment with auto-scaling endpoints
  • Broad model capabilities (text, code, reasoning, vision/text combos)
  • On-prem/offline available for Enterprise deployments
  • Transparent monthly pricing with free trial options
  • Support for custom models and migrations from other providers