Grok

grok-4.5

grok/grok-4.5

ChatVisionToolsSystem promptReasoning

Use this model

Context

500K

Max output

64K

Input / 1M

$2.00

Output / 1M

$6.00

Cached / 1M

$0.30

Cutoff

Feb 2026

About this model

Grok 4.5 is xAI's flagship model for code and everything else: agentic tool calling, minimal hallucinations, and configurable reasoning. Accepts text and image input with a 500,000-token context window. Requests exceeding the 200K context window are billed at a higher rate. Aliases: grok-4.5-latest, grok-build-latest.

Best suited for

Agentic software engineering and coding workflows
Agentic tool calling and multi-step workflow automation
Structured outputs and function calling
Long-context document and codebase analysis (up to 500K tokens)
Vision tasks with image input
Science, engineering, and math reasoning

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.

tools

Lists tool definitions or capabilities available to the model.

tool_choice

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

response_type

Defines the format or type of the generated response.

parallel_tool_calls

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

reasoning

Controls the level of reasoning used by the model. Grok 4.5 supports configurable reasoning effort via the reasoning_effort parameter.

stream

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

Use this model

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

Other Grok models

Model	Context	Max output	Input	Output	Capabilities
grok-4.7 Chat	500K	64K	$2.00	$6.00	Vision, Files, Tools, System prompt, Reasoning
grok-build-0.1 Chat	256K	64K	$1.00	$2.00	Vision, Tools, System prompt, Reasoning
grok-4.20-multi-agent-0309 Chat	1M	64K	$1.25	$2.50	Vision, Tools, System prompt, Reasoning
grok-4.20-0309-non-reasoning Chat	1M	64K	$1.25	$2.50	Vision, Tools, System prompt
grok-4.6 Chat	500K	64K	$2.00	$6.00	Vision, Files, Tools, System prompt, Reasoning
grok-4.20-0309-reasoning Chat	1M	64K	$1.25	$2.50	Vision, Tools, System prompt, Reasoning
grok-4.3 Chat	1M	64K	$1.25	$2.50	Vision, Tools, System prompt, Reasoning

Pricing & provider details

Grok

grok/grok-4.5

Input · per 1M: $2.00
Output · per 1M: $6.00
Cached input · per 1M: $0.30
Context window: 500,000 tokens
Max output: 64,000 tokens
Knowledge cutoff: Feb 2026
Auto-router: Not supported

Start building today

Route grok-4.5 — and every other model in the catalogue — through one endpoint, with failover built in.

Get started freeAll models