Legacy mappings retire on 2026-11-07. Use Azure with the AI Foundry deployment type.
Azure AI Foundry (Legacy) API
Legacy Azure Model Inference API. Use Azure with the AI Foundry deployment type.
Data & Privacy
HQ:US
Safety identifier:Not forwarded
API Training:No
Prompt Logging:No
Retention:0 days
GDPR:Compliant
SOC2:Type II Certified
ISO 27001:Certified
Available Models
Grok 4.3
xaiScheduled for Deactivation
grok-4-3Streaming
Tools
Reasoning
Azure AI Foundry (Legacy)
Context: 20k
Deactivating on Nov 7, 2026
Input
$1.25
/M tokens
Cached
$0.2
/M tokens
Output
$2.5
/M tokens
Grok 4.1 Fast Reasoning
xaiScheduled for Deactivation
grok-4-1-fast-reasoningStreaming
Vision
Tools
Reasoning
JSON Output
Azure AI Foundry (Legacy)
Context: 128k
Deactivating on Nov 7, 2026
Input
$0.2
/M tokens
Cached
—
/M tokens
Output
$0.5
/M tokens
Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to grok-4-3. On pay-as-you-go keys, azure-ai-foundry/grok-4-3 pins every request to Azure AI Foundry (Legacy); DevPass coding plans do not support provider pinning. You do not need a separate Azure AI Foundry (Legacy) account or SDK.