Grok 4.5
Grok 4.5 is a SpaceXAI reasoning model built for coding, agentic tasks, and knowledge work, accepting text and image input with selectable low, medium, and high reasoning levels.
View API reference- Input and output price
- Input $2, Output $6, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'spacexai/grok-4.5', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Grok 4.5 by SpaceXAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Grok 4.5
Grok 4.5
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Grok 4.5 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Grok 4.5 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. spacexai/grok-4.5. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Grok 4.5 supports up to 500,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 500K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK xai provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['xai'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'spacexai/grok-4.5', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by SpaceXAI
| Model |
|---|
| 500K | $2/M+1 more | $6/M+1 more | Read$0.50/M | $5/K | +1 | | 08/12/2026 | |||||||
| 1M | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +3 |  | 04/30/2026 | |||||||
| 2M | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +2 | | 03/10/2026 | |||||||
| 2M | $1.25/M+1 more | $2.50/M+1 more | Read$0.20/M | $5/K | +3 | | 03/10/2026 | |||||||
| 1M | $0.20/M | $0.50/M | Read$0.05/M | — | +1 | | 11/19/2025 | |||||||
| 1M | $0.20/M | $0.50/M | Read$0.05/M | — | +2 | | 11/19/2025 |
Copy link to headingAbout Grok 4.5
Grok 4.5 was released July 8, 2026 as SpaceXAI's reasoning model for coding, agentic tasks, and knowledge work. Grok 4.5 accepts text and image input, returns text, and works within a context window of 500K tokens. SpaceXAI lists a knowledge cutoff of February 1, 2026.
Reasoning depth is a per-request setting. Grok 4.5 supports low, medium, and high levels and defaults to high. Use low for latency-sensitive agent steps and simple tool calls, medium for data analysis and long-context reasoning, and high for competition-level math, multi-step logic, and hard engineering problems. Reasoning can't be switched off.
Tool support covers function calling, structured outputs, web search, X search, and code execution, so an agent can look something up or run code before it answers. Long agent loops also benefit from context compaction, which trims earlier turns so a session keeps running past the raw window.
You can integrate Grok 4.5 through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Routing rules move traffic from another Grok model to Grok 4.5 without changing application code.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Reasoning stays on for every Grok 4.5 request, so responses include thinking tokens even at the low level. Budget output tokens with that in mind and set the level per request instead of leaving everything at the default high.
- Configuration: SpaceXAI bills prompts at or above 200K tokens at a higher rate, and that rate applies to every token in the request rather than only the tokens past the threshold. Check the pricing panel on this page before you send very long prompts. The knowledge cutoff of February 1, 2026 also means Grok 4.5 needs web search or retrieval for anything more recent.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Grok 4.5
Best for
- Agentic Coding Tasks: Multi-step software engineering with function calling and code execution
- Adjustable Reasoning Depth: Low, medium, and high levels tuned per request
- Technical Knowledge Work: Science, engineering, and math problems that reward deeper thinking
- Vision-Assisted Development: Screenshots, diagrams, and design references alongside text prompts
- Search-Backed Answers: Web search and X search cover ground past the knowledge cutoff
Consider alternatives when
- Reasoning-Free Responses: Grok 4.1 Fast Non-Reasoning answers without spending thinking tokens
- High-Volume Simple Calls: Grok 3 Mini Fast costs less per token on straightforward tasks
- Fast Code Generation: Grok Code Fast 1 is tuned for quick code edits at lower cost
- Multi-Agent Orchestration: Grok 4.20 Multi-Agent spreads one request across collaborating agents
Copy link to headingConclusion
Grok 4.5 is SpaceXAI's reasoning model for real engineering work, with text and image input, three reasoning levels, and tools that cover search and code execution. Point spacexai/grok-4.5 at AI Gateway to route requests behind one API key, and set the reasoning level per request to balance depth against cost.
Copy link to headingFrequently Asked Questions
What is Grok 4.5 built for?
Coding, agentic tasks, and knowledge work. SpaceXAI targets Grok 4.5 at real engineering problems across science, engineering, and math.
How do I control reasoning depth on Grok 4.5?
Set the reasoning level to low, medium, or high on each request. Grok 4.5 defaults to high, and reasoning can't be disabled. Low suits latency-sensitive agent steps and simple tool calls, medium suits data analysis and long-context reasoning, and high suits multi-step logic and competition-level math.
Does Grok 4.5 accept image input?
Yes. Grok 4.5 accepts text and image input and returns text. Use a dedicated image model when you need generated images as output.
What is the context window for Grok 4.5?
The context window is 500K tokens, with up to 500K tokens per response.
What is the knowledge cutoff for Grok 4.5?
February 1, 2026. Pair Grok 4.5 with web search or retrieval for facts that changed after that date.
What tools does Grok 4.5 support?
Function calling, structured outputs, web search, X search, and code execution. Long agent loops can also use context compaction to trim earlier turns and keep a session running.
Can I move traffic to Grok 4.5 without changing my code?
Yes. Add an AI Gateway routing rule that rewrites requests from another Grok model to
spacexai/grok-4.5. Your application keeps sending the old model identifier.How do I authenticate with Grok 4.5 through Vercel AI Gateway?
Use your Vercel AI Gateway API key with
spacexai/grok-4.5as the model identifier. AI Gateway handles provider routing automatically.What does Grok 4.5 cost?
See the pricing section on this page for today's rates. AI Gateway reflects each provider's pricing for Grok 4.5 with no markup.
Does Vercel AI Gateway support Zero Data Retention for Grok 4.5?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.