GPT-5.4 Mini (Azure)

Soracom Flux AI actions added Azure OpenAI (GPT-5.4-mini) to its list of selectable AI models, placing this compact-tier variant alongside its larger sibling Azure OpenAI (GPT-5.4) within the same integration update. The naming pattern suggests a smaller, efficiency-oriented sibling in the same generation, intended for lighter workloads where lower latency or cost per call matters more than maximum capability.

No technical documentation, benchmark results, or architecture details for this exact model variant were supplied in the available evidence. The only confirmation of its existence and availability comes from the Soracom product changelog noting it as a newly supported option for AI-powered analysis inside Flux automation workflows, making it suitable for teams already operating IoT automation pipelines on the Soracom platform.

LLM Gatewayazure/gpt-5.4-minigpt-mini

Open provider page Provider docs

Quick Info

Provider: LLM Gateway
Model key: azure/gpt-5.4-mini
Release date: Mar 17, 2026
Last updated: Mar 17, 2026
Knowledge cutoff: 2025-08-31
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.75
Output token cost: $4.50

Limits

Input tokens: 272,000 tokens
Output tokens: 128,000 tokens
Context window: 400,000 tokens

Transparent token rates

Compare GPT-5.4 Mini (Azure) pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GPT-5.4 Mini (Azure)

LLM Gateway

CoverageRelease Notes

SORACOM's first-party changelog adds Azure OpenAI (GPT-5.4-mini) to the list of selectable AI models in Soracom Flux AI actions, alongside Azure OpenAI (GPT-5.4) and other newly available models. This confirms the Azure-hosted GPT-5.4 Mini variant exists as an Azure OpenAI offering and is reachable by developers integr For developers building on SORACOM Flux, the addition of Azure OpenAI (GPT-5.4-mini) broadens the set of Azure OpenAI models usable in Flux's AI actions, enabling selection of a smaller, likely lower-latency or lower-cost Azure OpenAI option within IoT/edge agent pipelines. The changelog entry itself is thin on further