Skip to main content

LLM Providers

Deeployd supports multiple LLM providers out of the box, enabling you to choose the best model for each use case. All providers use a unified interface, making it easy to switch between models or use different providers for different agents.

Supported Providers

ProviderEnvironment VariableOfficial SDK
Anthropic (Claude)ANTHROPIC_API_KEY@anthropic-ai/sdk
OpenAI (GPT)OPENAI_API_KEYopenai
Google (Gemini)GOOGLE_API_KEYGoogle AI
MistralMISTRAL_API_KEYMistral AI
GroqGROQ_API_KEYGroq

Configuration

Set the environment variables for the providers you want to use:

# Required: At least one provider
ANTHROPIC_API_KEY=sk-ant-...

# Optional: Additional providers
OPENAI_API_KEY=sk-...
GOOGLE_API_KEY=AIza...
MISTRAL_API_KEY=...
GROQ_API_KEY=gsk_...
Multi-Provider Strategy

You don't need to configure all providers. Deeployd will automatically detect which providers are available based on the API keys present in your environment.

Available Models

Anthropic (Claude)

Model IDNameContextMax OutputInput CostOutput Cost
claude-opus-4-5-20251101Claude Opus 4.5200K32K$0.005/1K$0.025/1K
claude-sonnet-4-5-20250929Claude Sonnet 4.5200K16K$0.003/1K$0.015/1K
claude-haiku-4-5-20251015Claude Haiku 4.5200K8K$0.001/1K$0.005/1K
claude-3-5-sonnet-20241022Claude 3.5 Sonnet200K8K$0.003/1K$0.015/1K
claude-3-5-haiku-20241022Claude 3.5 Haiku200K8K$0.001/1K$0.005/1K

OpenAI (GPT)

Model IDNameContextMax OutputInput CostOutput Cost
gpt-4oGPT-4o128K16K$0.0025/1K$0.01/1K
gpt-4o-miniGPT-4o Mini128K16K$0.00015/1K$0.0006/1K
gpt-4-turboGPT-4 Turbo128K4K$0.01/1K$0.03/1K
o1-previewo1 Preview128K32K$0.015/1K$0.06/1K
o1-minio1 Mini128K65K$0.003/1K$0.012/1K

Google (Gemini)

Model IDNameContextMax OutputInput CostOutput Cost
gemini-2.0-flashGemini 2.0 Flash1M8K$0.000075/1K$0.0003/1K
gemini-1.5-proGemini 1.5 Pro2M8K$0.00125/1K$0.005/1K
gemini-1.5-flashGemini 1.5 Flash1M8K$0.000075/1K$0.0003/1K

Mistral

Model IDNameContextMax OutputInput CostOutput Cost
mistral-large-latestMistral Large128K8K$0.002/1K$0.006/1K
mistral-medium-latestMistral Medium32K8K$0.0027/1K$0.0081/1K
mistral-small-latestMistral Small32K8K$0.0002/1K$0.0006/1K
codestral-latestCodestral32K8K$0.001/1K$0.003/1K

Groq (Fast Inference)

Model IDNameContextMax OutputInput CostOutput Cost
llama-3.3-70b-versatileLlama 3.3 70B128K32K$0.00059/1K$0.00079/1K
llama-3.1-70b-versatileLlama 3.1 70B128K32K$0.00059/1K$0.00079/1K
llama-3.1-8b-instantLlama 3.1 8B128K8K$0.00005/1K$0.00008/1K
mixtral-8x7b-32768Mixtral 8x7B32K8K$0.00024/1K$0.00024/1K

Using Models in Agents

When creating an agent, specify the model ID:

const agent = await deeployd.agents.create({
name: 'My Agent',
model: 'claude-sonnet-4-5-20250929', // or 'gpt-4o', 'gemini-1.5-pro', etc.
systemPrompt: 'You are a helpful assistant.',
});

Model Selection Best Practices

By Use Case

Use CaseRecommended Models
Complex reasoningclaude-opus-4-5, gpt-4o, o1-preview
General tasksclaude-sonnet-4-5, gpt-4o, gemini-1.5-pro
Fast responsesclaude-haiku-4-5, gpt-4o-mini, gemini-2.0-flash
Code generationclaude-sonnet-4-5, codestral-latest, gpt-4o
Long contextgemini-1.5-pro (2M), claude-* (200K)
Cost-sensitivegpt-4o-mini, gemini-2.0-flash, llama-3.1-8b-instant
Ultra-fast inferenceGroq models (llama-*, mixtral-*)

Model Capabilities

CapabilityClaudeGPTGeminiMistralGroq
Tool UseYesYesYesYesYes
VisionYesYesYesNoNo
StreamingYesYesYesYesYes
JSON ModeYesYesYesYesYes

Model Orchestration

Deeployd includes intelligent model orchestration that can automatically:

  • Route tasks to the most appropriate model based on complexity
  • Fallback to alternative providers if one is unavailable
  • Track performance across models for cost optimization
import { getModelOrchestrator } from '@deeployd/sdk';

const orchestrator = getModelOrchestrator();

// Automatic routing based on task type
const result = await orchestrator.execute({
taskType: 'code-generation',
messages: [{ role: 'user', content: 'Write a sorting function' }],
});

Cost Management

Deeployd tracks token usage and costs across all providers. View cost breakdowns in the dashboard or via API:

const usage = await deeployd.usage.get({
startDate: '2025-01-01',
endDate: '2025-01-31',
});

console.log(usage.byModel); // Cost breakdown by model
console.log(usage.byAgent); // Cost breakdown by agent

Getting API Keys

ProviderGet Your Key
Anthropicconsole.anthropic.com
OpenAIplatform.openai.com/api-keys
Googleaistudio.google.com
Mistralconsole.mistral.ai
Groqconsole.groq.com