FlowStack supports multiple AI providers and models, giving you flexibility to choose the right model for your use case and budget.
Supported Providers
OpenAI
| Model | Best For | Context Window |
|---|
| GPT-4o | Complex reasoning, multi-modal (text + images) | 128K tokens |
| GPT-4o Mini | Fast, cost-effective general tasks | 128K tokens |
| GPT-4 Turbo | Advanced reasoning with large context | 128K tokens |
| GPT-3.5 Turbo | Simple tasks, high throughput | 16K tokens |
Anthropic
| Model | Best For | Context Window |
|---|
| Claude 3.5 Sonnet | Best balance of speed and intelligence | 200K tokens |
| Claude 3 Opus | Most capable, complex analysis | 200K tokens |
| Claude 3 Haiku | Fastest, simple tasks | 200K tokens |
Google
| Model | Best For | Context Window |
|---|
| Gemini 1.5 Pro | Long-context reasoning, multi-modal | 1M tokens |
| Gemini 1.5 Flash | Fast inference, cost-effective | 1M tokens |
Groq
| Model | Best For | Context Window |
|---|
| Llama 3.1 70B | Open-source, fast inference | 128K tokens |
| Llama 3.1 8B | Ultra-fast, simple tasks | 128K tokens |
| Mixtral 8x7B | Balanced performance | 32K tokens |
Mistral
| Model | Best For | Context Window |
|---|
| Mistral Large | Complex reasoning | 128K tokens |
| Mistral Medium | Balanced performance | 32K tokens |
| Mistral Small | Cost-effective | 32K tokens |
Configuring a Provider
- Go to AI Studio → Settings (or configure inline when creating an agent)
- Select your provider
- Enter your API key
- The key is encrypted and stored securely (AES-256)
Choosing a Model
| Priority | Recommended Model |
|---|
| Best quality | GPT-4o or Claude 3.5 Sonnet |
| Fastest response | Groq Llama 3.1 8B or Gemini Flash |
| Lowest cost | GPT-4o Mini or Claude 3 Haiku |
| Longest context | Gemini 1.5 Pro (1M tokens) |
| Best for code | Claude 3.5 Sonnet or GPT-4o |
| Open-source | Groq Llama 3.1 70B |
Using Models in Workflows
In the Workflow Builder, use the Chat Model node:
- Add a Chat Model node to your workflow
- Select the provider and model
- Configure the connection (API key)
- Set parameters:
- Temperature — 0 (deterministic) to 1 (creative)
- Max Tokens — Maximum response length
- Top P — Nucleus sampling threshold
- Connect it to an AI Agent node or use it standalone for text generation