Model Providers (Cloud)

ADK-Rust supports multiple cloud LLM providers through the adk-model crate. All providers implement the Llm trait, making them interchangeable in your agents.

Overview

┌─────────────────────────────────────────────────────────────────────┐
│                     Cloud Model Providers                           │
├─────────────────────────────────────────────────────────────────────┤
│                                                                     │
│   • Gemini (Google)    ⭐ Default    - Multimodal, large context    │
│   • OpenAI (GPT-4o)    🔥 Popular    - Best ecosystem               │
│   • Anthropic (Claude) 🧠 Smart      - Best reasoning               │
│   • DeepSeek           💭 Thinking   - Chain-of-thought, cheap      │
│   • Groq               ⚡ Ultra-Fast  - Fastest inference           │
│                                                                     │
│   For local/offline models, see:                                    │
│   • Ollama     → ollama.md                                          │
│   • mistral.rs → mistralrs.md                                       │
│                                                                     │
└─────────────────────────────────────────────────────────────────────┘

Quick Comparison

---

Step 1: Installation

Add the providers you need to your Cargo.toml:

[dependencies]
# Pick one or more providers:
adk-model = { version = "0.2", features = ["gemini"] }        # Google Gemini (default)
adk-model = { version = "0.2", features = ["openai"] }        # OpenAI GPT-4o
adk-model = { version = "0.2", features = ["anthropic"] }     # Anthropic Claude
adk-model = { version = "0.2", features = ["deepseek"] }      # DeepSeek
adk-model = { version = "0.2", features = ["groq"] }          # Groq (ultra-fast)

# Or all cloud providers at once:
adk-model = { version = "0.2", features = ["all-providers"] }

Step 2: Set Your API Key

export GOOGLE_API_KEY="your-key"      # Gemini
export OPENAI_API_KEY="your-key"      # OpenAI
export ANTHROPIC_API_KEY="your-key"   # Anthropic
export DEEPSEEK_API_KEY="your-key"    # DeepSeek
export GROQ_API_KEY="your-key"        # Groq

---

Gemini (Google) ⭐ Default

Best for: General purpose, multimodal tasks, large documents

Key highlights:

• 🖼️ Native multimodal (images, video, audio, PDF)
• 📚 Up to 2M token context window
• 💰 Competitive pricing
• ⚡ Fast inference

Complete Working Example

use adk_rust::prelude::*;
use adk_rust::Launcher;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    
    let api_key = std::env::var("GOOGLE_API_KEY")?;
    let model = GeminiModel::new(&api_key, "gemini-2.0-flash")?;

    let agent = LlmAgentBuilder::new("gemini_assistant")
        .description("Gemini-powered assistant")
        .instruction("You are a helpful assistant powered by Google Gemini. Be concise.")
        .model(Arc::new(model))
        .build()?;

    Launcher::new(Arc::new(agent)).run().await?;
    Ok(())
}

Available Models

Example Output

👤 User: What's in this image? [uploads photo of a cat]

🤖 Gemini: I can see a fluffy orange tabby cat sitting on a windowsill. 
The cat appears to be looking outside, with sunlight illuminating its fur. 
It has green eyes and distinctive striped markings typical of tabby cats.

---

OpenAI (GPT-4o) 🔥 Popular

Best for: Production apps, reliable performance, broad capabilities

Key highlights:

• 🏆 Industry standard
• 🔧 Excellent tool/function calling
• 📖 Best documentation & ecosystem
• 🎯 Consistent, predictable outputs

Complete Working Example

use adk_rust::prelude::*;
use adk_rust::Launcher;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    
    let api_key = std::env::var("OPENAI_API_KEY")?;
    let model = OpenAIClient::new(OpenAIConfig::new(&api_key, "gpt-4o"))?;

    let agent = LlmAgentBuilder::new("openai_assistant")
        .description("OpenAI-powered assistant")
        .instruction("You are a helpful assistant powered by OpenAI GPT-4o. Be concise.")
        .model(Arc::new(model))
        .build()?;

    Launcher::new(Arc::new(agent)).run().await?;
    Ok(())
}

Available Models

Example Output

👤 User: Write a haiku about Rust programming

🤖 GPT-4o: Memory so safe,
Ownership guards every byte—
Compiler, my friend.

---

Anthropic (Claude) 🧠 Smart

Best for: Complex reasoning, safety-critical apps, long documents

Key highlights:

• 🧠 Exceptional reasoning ability
• 🛡️ Most safety-focused
• 📚 200K token context
• ✍️ Excellent writing quality

Complete Working Example

use adk_rust::prelude::*;
use adk_rust::Launcher;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    
    let api_key = std::env::var("ANTHROPIC_API_KEY")?;
    let model = AnthropicClient::new(AnthropicConfig::new(&api_key, "claude-sonnet-4-20250514"))?;

    let agent = LlmAgentBuilder::new("anthropic_assistant")
        .description("Anthropic-powered assistant")
        .instruction("You are a helpful assistant powered by Anthropic Claude. Be concise and thoughtful.")
        .model(Arc::new(model))
        .build()?;

    Launcher::new(Arc::new(agent)).run().await?;
    Ok(())
}

Available Models

Example Output

👤 User: Explain quantum entanglement to a 10-year-old

🤖 Claude: Imagine you have two magic coins. When you flip them, they always 
land the same way - both heads or both tails - even if one coin is on Earth 
and the other is on the Moon! Scientists call this "entanglement." The coins 
are connected in a special way that we can't see, like invisible best friends 
who always make the same choice at the exact same time.

---

DeepSeek 💭 Thinking

Best for: Complex problem-solving, math, coding, reasoning tasks

Key highlights:

• 💭 Thinking mode - shows chain-of-thought reasoning
• 💰 Very cost-effective (10x cheaper than GPT-4)
• 🔄 Context caching for repeated prefixes
• 🧮 Strong at math and coding

Complete Working Example

use adk_rust::prelude::*;
use adk_rust::Launcher;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    
    let api_key = std::env::var("DEEPSEEK_API_KEY")?;
    
    // Standard chat model
    let model = DeepSeekClient::chat(&api_key)?;
    
    // OR: Reasoning model with thinking mode
    // let model = DeepSeekClient::reasoner(&api_key)?;

    let agent = LlmAgentBuilder::new("deepseek_assistant")
        .description("DeepSeek-powered assistant")
        .instruction("You are a helpful assistant powered by DeepSeek. Be concise.")
        .model(Arc::new(model))
        .build()?;

    Launcher::new(Arc::new(agent)).run().await?;
    Ok(())
}

Available Models

Example Output (Reasoner with Thinking Mode)

👤 User: What's 17 × 23?

🤖 DeepSeek: <thinking>
Let me break this down:
17 × 23 = 17 × (20 + 3)
       = 17 × 20 + 17 × 3
       = 340 + 51
       = 391
</thinking>

The answer is 391.

---

Groq ⚡ Ultra-Fast

Best for: Real-time applications, chatbots, speed-critical tasks

Key highlights:

• ⚡ Fastest inference - 10x faster than competitors
• 🔧 LPU (Language Processing Unit) technology
• 💰 Competitive pricing
• 🦙 Runs LLaMA, Mixtral, Gemma models

Complete Working Example

use adk_rust::prelude::*;
use adk_rust::Launcher;
use std::sync::Arc;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    dotenvy::dotenv().ok();
    
    let api_key = std::env::var("GROQ_API_KEY")?;
    let model = GroqClient::llama70b(&api_key)?;

    let agent = LlmAgentBuilder::new("groq_assistant")
        .description("Groq-powered assistant")
        .instruction("You are a helpful assistant powered by Groq. Be concise and fast.")
        .model(Arc::new(model))
        .build()?;

    Launcher::new(Arc::new(agent)).run().await?;
    Ok(())
}

Available Models

Example Output

👤 User: Quick! Name 5 programming languages

🤖 Groq (in 0.2 seconds): 
1. Rust
2. Python
3. JavaScript
4. Go
5. TypeScript

---

Switching Providers

All providers implement the same Llm trait, so switching is easy:

use adk_agent::LlmAgentBuilder;
use std::sync::Arc;

// Just change the model - everything else stays the same!
let model: Arc<dyn adk_core::Llm> = Arc::new(
    // Pick one:
    // GeminiModel::new(&api_key, "gemini-2.0-flash")?
    // OpenAIClient::new(OpenAIConfig::new(&api_key, "gpt-4o"))?
    // AnthropicClient::new(AnthropicConfig::new(&api_key, "claude-sonnet-4-20250514"))?
    // DeepSeekClient::chat(&api_key)?
    // GroqClient::llama70b(&api_key)?
);

let agent = LlmAgentBuilder::new("assistant")
    .instruction("You are a helpful assistant.")
    .model(model)
    .build()?;

---

Examples

# Gemini (default)
cargo run --example quickstart

# OpenAI
cargo run --example openai_basic --features openai

# Anthropic
cargo run --example anthropic_basic --features anthropic

# DeepSeek
cargo run --example deepseek_basic --features deepseek
cargo run --example deepseek_reasoner --features deepseek  # Thinking mode

# Groq
cargo run --example groq_basic --features groq

---

Related

• Ollama (Local) - Run models locally with Ollama
• Local Models (mistral.rs) - Native Rust inference
• LlmAgent - Using models with agents
• Function Tools - Adding tools to agents

---

Previous: ← Realtime Agents | Next: Ollama (Local) →