Skip to main content

AI Platforms and Models

Written by Peter Novosel

When creating powerful automations with SmartSuite's AI Workflow Agent, selecting the right AI model is essential for delivering fast, reliable, and cost-effective results. To make this process easier, SmartSuite now presents a curated list of supported AI platforms and models, designed to help users choose the best model for their specific use case. Instead of exposing a raw, confusing list from LiteLLM—which often includes unstable or preview-only models—we’ve added a clean, informative interface that highlights key model characteristics with consistency and clarity.

Each model in the list is presented in a grid format organized by provider (such as OpenAI, Gemini, Anthropic, Perplexity, xAI, and IBM). The grid provides the following information:

  • Model Name: The official identifier of the model you can select.

  • Description: A short, user-friendly summary explaining what the model is best suited for—whether that’s summarization, reasoning, image analysis, or fast response generation.

  • Price Indicator: A relative cost indicator using dollar signs ($ to $$$$) to reflect general affordability. A single dollar sign represents the most cost-effective models, while four dollar signs represent premium options.

  • PDF & Image Scanning Support: Icons show whether a model supports input analysis of PDFs or images. Tooltips clarify this further when hovering over the icons (e.g., “This model can scan images”).

This structured approach empowers users to confidently select models based on the needs of their automation, whether they require multimodal support, budget-conscious processing, or maximum performance. The curated list also supports future flexibility, allowing SmartSuite to quickly add, remove, or update model information as AI platforms evolve.

OPEN AI

Model

Short Description

Price

PDFs

Images

GPT-6 Astra

Flagship. OpenAI's most capable model for the hardest end-to-end work.

$$$$

✅

✅

GPT 6 Sol

Strong model for complex coding and agentic work.

$$$

✅

✅

GPT 6 Luna

Very low cost. High-volume routing and light extraction.

$

✅

✅

GPT-5.6 Sol

Strong general model for complex professional work.

$$$

TBC

✅

GPT-5.6 Terra

Price/performance workhorse for everyday tasks.

$$$

TBC

✅

GPT-5.6 Luna

Very low cost. Routing, tagging, light extraction.

$

TBC

✅

GPT 5.5

Previous flagship. High accuracy for complex reasoning and analysis.

$$$$

✅

✅

GPT 5.4

Balanced 5.4 model. Summaries, reports and structured output.

$$$

✅

✅

GPT-5.4 Mini

Small 5.4 model. Good price/performance for everyday automation tasks.

$$

✅

✅

GPT 4.1

Mature high-accuracy model. Reports, summaries, and long context.

$$$

✅

✅

GPT 4.1 Mini

Low-cost workhorse. Data tasks and light daily use.

$

✅

✅

GPT 4o Mini

Older low-cost multimodal model. Simple tasks at low cost.

$

✅

✅

GEMINI

Model

Description

Price

Scans PDFs

Images

Gemini 3.8 Flash

Flash model, 3.8 generation. Fast multimodal at low cost.

$$

✅

✅

Gemini 3.6 Flash

Flash model, 3.6 generation. Fast responses with strong multimodal support.

$$

✅

✅

Gemini 3.5 Flash

Mature flash model. Fast responses with strong multimodal support.

$$$

✅

✅

Gemini 3.5 Flash-Lite

Low-cost, fast. Replaces 3.1 Flash-Lite.

$$

✅

✅

Gemini 3.1 Pro

Pro model. High-end reasoning, long context and complex workflows.

$$$

✅

✅

Gemini 2.5 Pro

Mature pro model. Strong reasoning and long-context work.

$$$

✅

✅

Gemini 2.5 Flash

Fast, cost-efficient model. Great for summarization and multimodal tasks.

$$

✅

✅

Gemini 2.5 Flash Lite

Cheapest 2.5 option. High-throughput simple workflows.

$

✅

✅

ANTHROPIC

Model

Description

Price

Scan PDFs

Images

Claude Fable 5.1

Anthropic's most capable model. Demanding reasoning and long multi-step work.

$$$$

✅

✅

Claude Opus 5.5

Flagship Opus. Anthropic's recommended default for most workloads.

$$$$

✅

✅

Claude Opus 5

Previous flagship Opus. Complex analysis and long multi-step work.

$$$$

✅

✅

Claude Opus 4.8

Previous-generation Opus. Deep reasoning over complex documents and records.

$$$$

✅

✅

Claude Opus 4.7

Previous-generation Opus. Deep reasoning and multimodal workflows.

$$$$

✅

✅

Claude Opus 4.6

Previous-generation Opus. Complex analysis and tool use.

$$$$

✅

✅

Claude Sonnet 5

Balanced Sonnet. Speed and quality for everyday content and analysis.

$$$

✅

✅

Claude Sonnet 4.6

Previous-generation Sonnet. Efficient multimodal everyday work.

$$$

✅

✅

Claude Haiku 4.5

Small, fast Claude. High-volume tagging, extraction and summaries.

$$

✅

✅

PERPLEXITY

Model

Description

Price

Scan PDFs

Images

Sonar

Web-grounded answers with Perplexity's search.

$$

TBC

TBC

xAI

Model

Description

Price

Scan PDFs

Images

Grok 4.6

Top Grok model. 500K context, strong reasoning and vision.

$$

❌

✅

Grok 4.3

Mid-range Grok. Multimodal with strong reasoning and vision, 1M context.

$$

❌

✅

Grok 4.20 Reasoning

Reasoning model. Complex analysis with image support.

$$

❌

✅

Grok 4.20

Fast 4.20 model. Quick multimodal responses without deep reasoning.

$$

❌

✅

Grok Build

Build-focused model. Structured outputs and implementation tasks.

$

❌

✅

IBM

Model

Description

Price

PDFs

Images

Granite-3-2B

Lightweight instruct model with vision input

$$

✅

✅

Granite-3-8B

Mid-tier general-purpose multimodal LLM

$$

✅

✅

Llama-3-70B Vision

Vision-capable Llama model via IBM API

$$$

✅

✅

Related Articles
Did this answer your question?