Grok logoGrok

    grok-4.20-0309-reasoning

    grok/grok-4.20-0309-reasoning

    ChatVisionToolsSystem promptReasoning
    Use this model

    Context

    1M

    Max output

    64K

    Input / 1M

    $1.25

    Output / 1M

    $2.50

    Cached / 1M

    $0.20

    Cutoff

    unknown

    About this model

    Grok 4.20 (grok-4.20-0309-reasoning) is a high-performance xAI model with industry-leading speed, agentic tool calling, and a low hallucination rate with strict prompt adherence.

    Best suited for

    • Agentic tool calling
    • Long-horizon reasoning
    • Low-hallucination document understanding

    Built-in tools

    Gtwy web search

    Hosted by the gateway — enable them per request without wiring your own endpoint.

    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.

    Reasoning

    Emits a separate thinking pass before the answer.

    Supported parameters

    creativity_level

    Controls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.

    max_tokensMax Tokens Limit

    Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

    parallel_tool_calls

    Enables parallel execution of tools, allowing multiple tools to run simultaneously.

    reasoning

    Grok 4.20 always reasons before responding; effort level is not user-configurable per official docs.

    response_type

    Defines the format or type of the generated response.

    stream

    Sends the response in real-time as it's being generated.

    tool_choice

    Decides whether to use tools or just the model for generating responses.

    tools

    Lists tool definitions or capabilities available to the model.

    Use this model

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

    Other Grok models

    ModelContextMax outputInputOutputCapabilities
    grok-4.7

    Chat

    500K64K$2.00$6.00Vision, Files, Tools, System prompt, Reasoning
    grok-build-0.1

    Chat

    256K64K$1.00$2.00Vision, Tools, System prompt, Reasoning
    grok-4.20-multi-agent-0309

    Chat

    1M64K$1.25$2.50Vision, Tools, System prompt, Reasoning
    grok-4.20-0309-non-reasoning

    Chat

    1M64K$1.25$2.50Vision, Tools, System prompt
    grok-4.6

    Chat

    500K64K$2.00$6.00Vision, Files, Tools, System prompt, Reasoning
    grok-4.3

    Chat

    1M64K$1.25$2.50Vision, Tools, System prompt, Reasoning
    grok-4.5

    Chat

    500K64K$2.00$6.00Vision, Tools, System prompt, Reasoning

    Pricing & provider details

    Grok logo

    Grok

    grok/grok-4.20-0309-reasoning

    Input · per 1M
    $1.25
    Output · per 1M
    $2.50
    Cached input · per 1M
    $0.20
    Context window
    1,000,000 tokens
    Max output
    64,000 tokens
    Knowledge cutoff
    unknown
    Auto-router
    Not supported

    Start building today

    Route grok-4.20-0309-reasoning — and every other model in the catalogue — through one endpoint, with failover built in.