Open Router logoOpen Router

    openai/gpt-5.4-mini

    open_router/openai/gpt-5.4-mini

    ChatVisionToolsSystem prompt
    Use this model

    Context

    400K

    Max output

    128K

    Input / 1M

    $0.75

    Output / 1M

    $4.50

    Cached / 1M

    $0.075

    Cutoff

    Aug 2025

    About this model

    GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.

    Best suited for

    • Designed for production environments that require a balance of capability and efficiency

    Capabilities

    Vision

    Accepts images alongside text in the same message.

    Tools

    Native function calling, so agents can invoke your endpoints.

    System prompt

    Honours a dedicated system role, separate from the user turn.

    Supported parameters

    creativity_level
    max_tokens
    probability_cutoff
    tools
    tool_choice
    response_type
    parallel_tool_calls

    Use this model

    OpenAI-SDK compatible, with gateway fallback and routing across providers.

    Other Open Router models

    ModelContextMax outputInputOutputCapabilities
    apodex/apodex-1.1-mini:free

    Chat

    262K128KFreeFreeVision, Files, Tools, System prompt, Reasoning
    x-ai/grok-4.5

    Chat

    500K450K$2.00$6.00Vision, Files, Tools, System prompt
    moonshotai/kimi-k3

    Chat

    1.0M944K$0.70$15.00Vision, Files, Tools, System prompt
    anthropic/claude-opus-4.8

    Chat

    1M128K$5.00$25.00Vision, Files, Tools, System prompt, Reasoning
    google/gemini-3-flash-preview

    Chat

    1.0M66K$0.50$3.00Vision, Tools, System prompt

    Pricing & provider details

    Open Router logo

    Open Router

    open_router/openai/gpt-5.4-mini

    Input · per 1M
    $0.75
    Output · per 1M
    $4.50
    Cached input · per 1M
    $0.075
    Context window
    400,000 tokens
    Max output
    128,000 tokens
    Knowledge cutoff
    Aug 2025
    Auto-router
    Not supported

    Start building today

    Route openai/gpt-5.4-mini — and every other model in the catalogue — through one endpoint, with failover built in.