# Dynamic AI Model Manager

AI Agent SDK supports multiple AI model providers. Below are the currently available `llm_config` provider options:

* OpenAI
* Anthropic
* Mistral
* Fireworks
* GoogleGenAI
* Grok
* Groq
* VertexAI
* AWS Bedrock

### Provider Enum

Here is an example to access the Crypto.com AI Agent SDK Provider enums:

<pre class="language-python"><code class="lang-python">from crypto_com_agent_client.lib.enums.provider_enum import Provider

for provider in Provider:
    print(provider.name, provider.value)
    
# Output:
<strong># OpenAI OpenAI
</strong># Anthropic Anthropic
# Mistral Mistral
# Fireworks Fireworks
# GoogleGenAI GoogleGenAI
# Grok Grok
# Groq Groq
# VertexAI VertexAI
# Bedrock Bedrock
</code></pre>

### Example: Using Crypto.com AI Agent with Gemini

Here is an example to use the Crypto.com AI Agent with Google's Gemini model for Cronos chain interactions:

```javascript
from crypto_com_agent_client import Agent, SQLitePlugin
from crypto_com_agent_client.lib.enums.provider_enum import Provider

# Initialize the agent
agent = Agent.init(
   llm_config={
       "provider": Provider.GoogleGenAI,
       "model": "gemini-2.0-flash",
       "provider-api-key": "your-api-key",
       "temperature": "float-controlling-output-randomness",
       "transfer-limit": -1,  # -1 means no limit (unlimited), 0 disables transfers completely, any positive number (e.g. 5) allows exactly that transfer amount
   },
   blockchain_config={
        "api-key": "your-crypto.com-developer-platform-api-key",
        "private-key": "your-private-key",
        "sso-wallet-url": "your-sso-wallet-url",
        "timeout": "timeout-in-seconds-for-API-calls-default-20s")
   },
   plugins={
       "storage": SQLitePlugin(db_path="agent_state.db"),
       "instructions": "You are an assistant that always provides useful responses."
   },
)


# Interaction
response = agent.interact("Get latest block height")
print(response)

```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-agent-sdk-docs.crypto.com/crypto.com-ai-agent-sdk/core-concepts-overview/dynamic-ai-model-manager.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.