Grok 4.5
import { streamText } from 'ai'
const result = streamText({ model: 'xai/grok-4.5', prompt: 'Why is the sky blue?'})Playground
Try out Grok 4.5 by xAI. 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
Providers
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.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by xAI
| Model |
|---|
| 256K | 1.3s | 136tps | $1/M+1 more | $2/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +2 | | 05/20/2026 | ||||
| 1M | 1.1s | 84tps | $1.25/M+1 more | $2.50/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +3 |  | 04/30/2026 | ||||
| 2M | 0.5s | 150tps | $1.25/M+1 more | $2.50/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +3 | | 03/10/2026 | ||||
| 2M | 3.7s | 411tps | $1.25/M+1 more | $2.50/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +3 | | 03/10/2026 | ||||
| 1M | 1.3s | 182tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | +2 | | 11/19/2025 | ||||
| 1M | 0.4s | 174tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | +1 | | 11/19/2025 |
About Grok 4.5
Grok 4.5 was released July 8, 2026 as xAI'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. xAI 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. Try Grok 4.5 in the AI Gateway playground at https://ai-sdk.dev/playground/xai:grok-4.5.
What 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: xAI 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: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When 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
Conclusion
Grok 4.5 is xAI's reasoning model for real engineering work, with text and image input, three reasoning levels, and tools that cover search and code execution. Point xai/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.