Grok 4.5

by xAI

Zero data retention
x-ai/grok-4.5
Input
$2.80/1M tokens
Output
$8.40/1M tokens
Context
500Ktokens
Max output
450Ktokens
Knows to
-
Released
8 Jul 2026

About

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

Pricing

Input$2.80per 1M prompt tokens
Output$8.40per 1M generated tokens, reasoning included
Cached input$0.42per 1M tokens read back from the prompt cache
Input over 200K$5.60the whole prompt is billed at this rate once it passes the threshold
Output over 200K$16.80applies to replies to those prompts
Web search$0.0070per request that uses the provider’s built-in search

What a request costs

Typical requestEachPer 1,000
Short chat reply1,500 in · 400 out$0.0076$7.56
Question over a long document40,000 in · 800 out$0.119$118.72
Agent tool step20,000 in · 1,200 out$0.066$66.08
Very long prompt (over 200K)250,000 in · 1,500 out$1.43$1,425

At the developer-API rate, before any provider promotion or prompt-cache saving. In the app, the model picker shows what a message costs on your plan before you send it.

Benchmarks

Coding72.4#29 of 167
Agentic41.2#36 of 137

Head-to-head rankings

  1. #6Game devAgent arenaElo 118256% wins
  2. #10SlidesAgent arenaElo 110153% wins
  3. #11Android appsAgent arenaElo 123263% wins
  4. #11Full stackAgent arenaElo 123360% wins
  5. #11Godot gamesAgent arenaElo 122958% wins
  6. #15codetovideoAgent arenaElo 115447% wins
  7. #16Mobile appsAgent arenaElo 121452% wins
  8. #16ASCII artModel arenaElo 125554% wins
  9. #17blender3dAgent arenaElo 105345% wins
  10. #21Web appsAgent arenaElo 120253% wins

Scores from Artificial Analysis; bars are scaled to the best model on our list. Rankings from Design Arena head-to-head votes. Published by OpenRouter alongside its catalogue.

Call it from code

OpenAI-compatible: point any OpenAI SDK at https://api.privateer.pro/v1 and set model. Keys are created in the app under Settings.

cURL
curl https://api.privateer.pro/v1/chat/completions \
  -H "Authorization: Bearer $PRIVATEER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.5",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.privateer.pro/v1",
    api_key=os.environ["PRIVATEER_API_KEY"],
)
reply = client.chat.completions.create(
    model="x-ai/grok-4.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)
JavaScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.privateer.pro/v1",
  apiKey: process.env.PRIVATEER_API_KEY,
});
const reply = await client.chat.completions.create({
  model: "x-ai/grok-4.5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);

Parameters this model accepts

include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

API reference → · How API billing works →

Prices are USD at the developer-API rate, as of 9 Nov 2026, rebuilt daily from the providers’ live catalogues. ← All models