Back to Knowledge Directory
AI Models
Groq
LPU-accelerated inference engine delivering sub-100ms token latency for open-weight LLMs.
Available API Actions (1)
Structured function definitions and payload specifications for AI agent tool execution.
POSTchat_completion
Run ultra-low-latency inference against Llama, Mixtral, or Gemma models.
PARAMETERS SCHEMA
| Param Name | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | llama-3.3-70b-versatile |
| messages | array | Yes | Conversation messages |
Related AI Models Integrations
OpenAI API
Access GPT-4o, o3-mini, embeddings, and vision models for multi-step reasoning and function calling.
Anthropic Claude
Claude 3.5 Sonnet & Claude 3 Opus models optimized for complex code execution, analysis, and tool use.
OpenRouter
Unified API gateway to query 200+ AI models (DeepSeek R1, Llama 3, Claude, Mistral) with auto-fallback.