Overview
CREAO gives you access to multiple AI models from different providers. Choose the model that best fits your task — whether you need maximum intelligence, a large context window, or cost efficiency. Select a model from the model dropdown at the top of the chat interface. Your choice persists per thread, so you can use different models for different conversations.Model comparison
All models have full access to the same tools — code execution, web search, image generation, file handling, and all connected skills and integrations.
| Model | Provider | Context | Cache | Cost tier | Best for |
|---|---|---|---|---|---|
| Claude Opus 4.6 | Anthropic | 1M | Yes | Premium | Most complex reasoning tasks |
| Claude Sonnet 4.6 | Anthropic | 1M | Yes | Standard | Best balance of speed and intelligence |
| Claude Haiku 4.5 | Anthropic | 200K | Yes | Economy | Fast, cost-efficient tasks |
| Gemini 3.1 Pro | 1M | Yes | Standard | Advanced reasoning with multimodal input | |
| GPT-5.4 | OpenAI | 1M | Yes | Standard | Capable all-rounder with reasoning |
| MiniMax M2.7 | MiniMax | 196K | Yes | Economy | Agentic coding at very low cost |
| Grok 4.20 | xAI | 2M | Yes | Standard | Largest context window (2M tokens) |
Choosing a model
I want the best quality regardless of cost
I want the best quality regardless of cost
Choose Claude Opus 4.6 (requires a paid plan). It has the strongest reasoning and handles the most complex multi-step tasks.
I want a good balance of speed, quality, and cost
I want a good balance of speed, quality, and cost
Claude Sonnet 4.6 is the default and recommended for most users. It handles coding, analysis, and creative tasks well at moderate cost.
I want to minimize credit usage
I want to minimize credit usage
MiniMax M2.7 uses the fewest credits per message while scoring near Opus-level on coding benchmarks. Great for iterative coding sessions where you send many messages.
I'm working with a very large codebase or long document
I'm working with a very large codebase or long document
Grok 4.20 has a 2M token context window — twice as large as any other model. Use it when you need the agent to reason over large amounts of code or text in a single conversation.
I need fast responses for simple tasks
I need fast responses for simple tasks
Claude Haiku 4.5 is the fastest model. Use it for quick questions, formatting, or lightweight code generation where speed matters more than depth.
Prompt caching
Most models support prompt caching, which reduces cost and latency on follow-up messages in the same thread. When caching is active, repeated parts of the conversation (system prompt, earlier messages) are served from cache at a reduced rate. Caching happens automatically. You don’t need to configure anything.Credit costs
Credits are deducted based on actual token usage. The cost tier determines how many credits each message uses:| Cost tier | Credit usage per message | Models |
|---|---|---|
| Economy | ~0.1–1 credits | MiniMax M2.7, Claude Haiku 4.5 |
| Standard | ~1–6 credits | Claude Sonnet 4.6, GPT-5.4, Gemini 3.1 Pro, Grok 4.20 |
| Premium | ~5–20 credits | Claude Opus 4.6 |