Grok 4.3
Grok 4.3 is a SpaceXAI reasoning model with an improved architecture and a December 2025 knowledge cutoff, matching the scale of Grok 4.20 within a context window of 1M tokens. Your use is subject to SpaceXAI's Terms & Privacy Policies.
View API reference- Input and output price
- Prices from: Input $1.25, Output $2.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'spacexai/grok-4.3', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Grok 4.3 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 4.3
Grok 4.3
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 4.3 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-4.3', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Grok 4.3 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-4.3', 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-4.3. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Grok 4.3 supports up to 1,000,000 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 1M-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-4.3', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['xai', 'vertex'], }, }, });
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-4.3', 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-4.3', 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-4.3', 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-4.3', 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 | |||||||
| 500K | $2/M+1 more | $6/M+1 more | Read$0.30/M | $5/K | +3 | | 07/08/2026 | |||||||
| 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 | — | +2 | | 11/19/2025 | |||||||
| 1M | $0.20/M | $0.50/M | Read$0.05/M | — | +1 | | 11/19/2025 |
Copy link to headingAbout Grok 4.3
Grok 4.3 was released April 30, 2026 as SpaceXAI's next reasoning model in the Grok family. It matches the scale of Grok 4.20 while refining the underlying architecture, and ships with a December 2025 knowledge cutoff so factual recall is closer to current events than earlier Grok generations.
The model targets reasoning-heavy workloads: mathematical problem solving, code analysis, multi-step planning, and tasks where structured thinking improves answer quality. It supports tool use, vision input, file input, and web search, which makes it suitable for agentic systems that combine reasoning with external context. Implicit caching helps keep costs predictable on repeated prefixes within the context window of 1M tokens.
Grok 4.3 produces up to 1M tokens per response, which leaves room for long reasoning traces alongside the final answer. See the pricing panel on this page for current input and output rates.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Grok 4.3 produces extended reasoning output, which increases token consumption per response. Budget output tokens generously and plan for the reasoning overhead when estimating cost.
- Configuration: The December 2025 knowledge cutoff is newer than earlier Grok models, but Grok 4.3 still benefits from web search or retrieval augmentation for facts that change after that date. See live metrics on this page for current throughput.
- Zero Data Retention: Zero Data Retention is available for this model. It 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 4.3
Best for
- Reasoning-Heavy Workloads: Mathematical problem solving, multi-step planning, and analytical tasks that benefit from chain-of-thought
- Long-Context Analysis: Document synthesis, codebase review, and research tasks that fit inside 1M tokens of context
- Tool-Using Agents: Workflows that combine reasoning with web search, file input, and external tool calls
- Vision And Multimodal Tasks: Pipelines that mix text reasoning with image understanding
- Recent-Knowledge Questions: Tasks where the December 2025 knowledge cutoff reduces the need for retrieval
Consider alternatives when
- Latency-Sensitive Endpoints: Grok 4 Fast variants return direct answers with lower reasoning overhead
- High-Volume Classification: Smaller Grok models like Grok 3 Mini Fast cost less per token for simple tasks
- Coding-Specific Pipelines: Grok Code Fast 1 is tuned for fast code generation at lower cost
- Multi-Agent Orchestration: The Grok 4.20 Multi-Agent variant is purpose-built for agent collaboration patterns
Copy link to headingConclusion
Grok 4.3 is SpaceXAI's refined reasoning model at the Grok 4.20 scale, with a December 2025 knowledge cutoff and support for tool use, vision, and web search. Teams that need deep reasoning across long contexts and recent world knowledge should evaluate Grok 4.3 against the Grok 4 Fast variants for cost and latency tradeoffs.
Copy link to headingFrequently Asked Questions
What is the knowledge cutoff for Grok 4.3?
Grok 4.3 has a December 2025 knowledge cutoff. Pair it with web search or retrieval for facts that change after that date.
How does Grok 4.3 compare to Grok 4.20?
Grok 4.3 matches the scale of Grok 4.20 and refines the underlying architecture. It also carries a newer December 2025 knowledge cutoff.
What is the context window for Grok 4.3?
The context window is 1M tokens, with up to 1M tokens per response.
What capabilities does Grok 4.3 support?
Grok 4.3 supports reasoning, tool use, implicit caching, file input, vision, and web search through AI Gateway.
What does Grok 4.3 cost?
See the pricing section on this page for today's rates. AI Gateway exposes each provider's pricing for Grok 4.3.
How do I authenticate with Grok 4.3 through Vercel AI Gateway?
Use your Vercel AI Gateway API key with
spacexai/grok-4.3as the model identifier. AI Gateway handles provider routing automatically.Does Vercel AI Gateway support Zero Data Retention for Grok 4.3?
Yes, Zero Data Retention is 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.