Model Selection
Aigentic supports 25 AI models from 7 providers, including free cloud models and local models via Ollama. This guide covers the Models page, all available models, and how to choose the right one.
The Models Page
Section titled “The Models Page”Open Models from the sidebar to access the model configuration page. It has two main sections:
Provider Cards
Section titled “Provider Cards”Models are organized into a grid of provider cards — one per provider. Each card shows:
- Provider name with a color-coded icon
- Model count (e.g., “4 models available”)
- “Free” badge on the NVIDIA NIM card
- Model dropdown — Select a model from this provider to see its details
- Model details panel — Shows the selected model’s tier badge, cost, “Recommended” badge (if applicable), and description
- Test Connection button — Verifies that the provider is reachable with your current credentials. Shows “Connected” or “Connection Failed.”
- Configure button — Navigates to the Credentials page to add or update your API key for this provider
Fallback Chain
Section titled “Fallback Chain”Below the provider cards, a Fallback Chain card lets you configure what happens when the primary model is unavailable:
- The chain shows numbered badges for each fallback model, connected by arrows
- Click X on any badge to remove it from the chain
- Use the Add model to chain dropdown to append a new fallback
- Click Save Changes (appears when you have unsaved changes) to persist your configuration
All Models at a Glance
Section titled “All Models at a Glance”Free Models (No API Key Required)
Section titled “Free Models (No API Key Required)”These models are available immediately — no API key, no signup, no cost.
| Model | Provider | Tier | Strengths |
|---|---|---|---|
| DeepSeek V3.2 | NVIDIA NIM | Powerful | 685B flagship. State-of-the-art open reasoning. |
| DeepSeek V3.1 Terminus | NVIDIA NIM | Balanced | 128K context, optimized for tool calling. |
| Kimi K2.5 | NVIDIA NIM | Powerful | 1T multimodal model. Reasoning and vision. |
| Kimi K2 Instruct | NVIDIA NIM | Balanced | MoE architecture, fast and efficient. |
| GLM-5 | NVIDIA NIM | Powerful | 744B MoE reasoning model. 205K context, tool calling. |
| GLM-4.7 Flash | Z.AI | Fast | Free, fast responses for simple tasks. |
Anthropic (API Key Required)
Section titled “Anthropic (API Key Required)”| Model | Tier | Cost | Strengths |
|---|---|---|---|
| Claude Opus 4.6 | Powerful | $5/1M tokens | Most capable. 1M context, adaptive thinking. |
| Claude Opus 4.5 | Powerful | $5/1M tokens | Previous-gen flagship. Strong reasoning and analysis. |
| Claude Sonnet 4 | Balanced | $3/1M tokens | Best balance of speed, quality, and cost. |
| Claude 3.5 Haiku | Fast | $0.25/1M tokens | Fast and affordable for simple tasks. |
API Key: console.anthropic.com
OpenAI (API Key Required)
Section titled “OpenAI (API Key Required)”| Model | Tier | Cost | Strengths |
|---|---|---|---|
| OpenAI o1 | Powerful | $15/1M tokens | Advanced reasoning for complex problems. |
| OpenAI o3 Mini | Balanced | $1.1/1M tokens | Compact reasoning model. |
| GPT-4o | Balanced | $2.5/1M tokens | General purpose, multimodal. |
| GPT-4o Mini | Fast | $0.15/1M tokens | Fast and cost-effective. |
API Key: platform.openai.com
xAI (API Key Required)
Section titled “xAI (API Key Required)”| Model | Tier | Cost | Strengths |
|---|---|---|---|
| Grok 4.1 Fast Reasoning | Balanced | $0.2/1M tokens | Fast reasoning with real-time knowledge. |
| Grok 3 Mini | Fast | $0.3/1M tokens | Lightweight and fast. |
API Key: console.x.ai
Z.AI (API Key Required for Premium)
Section titled “Z.AI (API Key Required for Premium)”| Model | Tier | Cost | Strengths |
|---|---|---|---|
| GLM-5 | Powerful | $1/1M tokens | Flagship reasoning and coding via Z.AI API. |
| GLM-4.7 | Balanced | $0.6/1M tokens | Strong all-rounder with 200K context. |
| GLM-4.7 Flash | Fast | Free | Free, fast responses for simple tasks. |
API Key: open.bigmodel.cn
MiniMax (API Key Required)
Section titled “MiniMax (API Key Required)”| Model | Tier | Cost | Strengths |
|---|---|---|---|
| MiniMax M2.5 | Powerful | $0.15/1M tokens | Near-SOTA coding and agents. 1/20th the cost of frontier. |
| MiniMax M2.5 Highspeed | Fast | $0.3/1M tokens | 2x faster throughput. Optimized for real-time agents. |
API Key: platform.minimaxi.com
Ollama (Local)
Section titled “Ollama (Local)”Local models run on your machine via Ollama. Free, no API key, no data leaves your device. Requires the desktop app with Ollama installed.
| Model | Tier | Strengths |
|---|---|---|
| Llama 3.3 | Balanced | Latest Llama, runs locally. Free, no API key needed. |
| Llama 3 | Balanced | Run locally, no API key needed. |
| Mistral | Fast | Fast local model. |
| Code Llama | Balanced | Optimized for coding tasks. |
| Phi-4 | Fast | Compact but capable. |
Model Tiers
Section titled “Model Tiers”Every model belongs to one of three tiers, shown as color-coded badges in the UI:
| Tier | Color | Best For |
|---|---|---|
| Fast | Green | Quick responses, simple tasks, high-volume workloads |
| Balanced | Blue | General purpose, coding, analysis — best speed-to-quality ratio |
| Powerful | Purple | Complex reasoning, creative work, research, deep analysis |
Choosing a Model
Section titled “Choosing a Model”For Getting Started (Free)
Section titled “For Getting Started (Free)”Recommended: DeepSeek V3.2 or Kimi K2.5 (NVIDIA NIM)
Start with free models to explore the platform. These are powerful models with no API key required.
For General Purpose Agents
Section titled “For General Purpose Agents”Recommended: Claude Sonnet 4 or GPT-4o
Best balance of speed, capability, and cost. They handle a wide range of tasks well.
For Complex Reasoning and Research
Section titled “For Complex Reasoning and Research”Recommended: Claude Opus 4.6 or GLM-5
When your agent needs deep analysis, synthesis, or nuanced output.
For Coding Agents
Section titled “For Coding Agents”Recommended: Claude Sonnet 4 or MiniMax M2.5
Claude Sonnet 4 excels at code generation and review. MiniMax M2.5 offers near-SOTA coding performance at a fraction of the cost.
For High-Volume / Low-Cost
Section titled “For High-Volume / Low-Cost”Recommended: MiniMax M2.5 ($0.15/1M) or GPT-4o Mini ($0.15/1M)
Best cost-per-token for agents processing high volumes of messages.
Changing Models
Section titled “Changing Models”There are two ways to change which model an agent uses:
Per-Agent (from the Agents page)
Section titled “Per-Agent (from the Agents page)”- On the Agents page, click the model name (with ✎ icon) on the agent card.
- Select a new model from the dropdown.
- Click Save.
The new model takes effect on the next message. Conversation history is preserved.
Default Model (from the Models page)
Section titled “Default Model (from the Models page)”- Open Models from the sidebar.
- Select a model from any provider card dropdown.
- Click Save Changes.
This sets the default model for new agents and the primary model for the platform.
Cost Management Tips
Section titled “Cost Management Tips”- Start with free models — Use NVIDIA NIM or GLM-4.7 Flash while developing and refining your agents.
- Configure fallbacks — Set up a fallback chain on the Models page so agents automatically switch to an alternative if the primary model is unavailable.
- Monitor usage — The analytics dashboard tracks token consumption per agent.
- Match model to task — Not every agent needs the most powerful model. A simple Q&A bot works well with a fast-tier model.
- Use MiniMax M2.5 for cost-effective power — At $0.15/1M tokens, it offers near-frontier performance at 1/20th the price.