Grok 4.5 API pricing and code examples
Grok 4.5 is a xAI model you can call through LivRouter's OpenAI-compatible endpoint. There is no separate xAI account and no separate invoice: one LivRouter API key reaches Grok 4.5 alongside every other model on the platform, billed per token from prepaid credits.
Grok 4.5 API at a glance
Compare Grok 4.5 API pricing, model ID, and OpenAI-compatible examples through LivRouter.
- Model ID
- grok-4.5
- Provider
- xAI
- API format
- OpenAI-compatible
- Billing
- Per token from LivRouter credits
- Common integration focus
- xAI API integrations
Grok 4.5 pricing
Rates are in USD per 1M tokens. The reference row is the provider base rate recorded in LivRouter's catalog; the plan rows show the published rates for each eligible plan.
| Plan | Input / 1M | Output / 1M | Cached input / 1M |
|---|---|---|---|
| Reference (xAI) | $2.00 | $6.00 | $0.30 |
| Max Grok−84% | $0.32 | $0.96 | $0.048 |
| Pro Grok−77% | $0.46 | $1.38 | $0.069 |
Lowest listed LivRouter rate for Grok 4.5: $0.32 per 1M input tokens on the Max Grok plan — about 84% below the xAI reference rate. See every plan and rate.
Source: LivRouter model catalog. Catalog checked .
What does a Grok 4.5 request cost?
One million uncached input tokens plus 100,000 output tokens at the listed Max Grok rates cost $0.416. This example excludes subscription fees and assumes the selected plan is active. Actual charges depend on input, output, and cached-token usage.
Compare plan fees and credit allowancesCall Grok 4.5 with the OpenAI SDK
Grok 4.5 follows the OpenAI chat completions format, so existing OpenAI client code keeps working — change the base URL and the model name.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.livrouter.com/v1",
apiKey: process.env.LIVROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "grok-4.5",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Prefer plain HTTP? The same request over curl:
curl https://api.livrouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LIVROUTER_API_KEY" \
-d '{
"model": "grok-4.5",
"messages": [{"role": "user", "content": "Hello"}]
}'Frequently asked questions about Grok 4.5
How much does grok-4.5 cost through LivRouter?
grok-4.5 is metered per token. The xAI reference rate is $2.00 per 1M input tokens and $6.00 per 1M output tokens. On the Max Grok plan LivRouter charges $0.32 per 1M input tokens, about 84% below the xAI reference rate. Cached input is $0.048 per 1M tokens.
Can I call grok-4.5 with the OpenAI SDK?
Yes. grok-4.5 is reachable through the OpenAI-compatible endpoint at https://api.livrouter.com/v1. Keep your existing OpenAI client code and change the base URL and the model name to "grok-4.5".
Do I need a separate xAI account?
No. LivRouter routes the request for you. You only need a LivRouter API key and credits — no separate xAI subscription.
Is grok-4.5 available on the Start tier?
grok-4.5 is not part of the Start tier group. It is available on the paid plans listed above.