Grok 3
xAI's flagship model. Strong at reasoning, coding, and real-time knowledge with web search capabilities.
Grok 3 is text & chat AI model from xAI, priced at €30.00 per 1M input tokens with a 131.1K tokens context window.
0.7
Examples
See what Grok 3 can generate
What are the latest developments in quantum computing and which companies are leading the field?
The quantum computing landscape is rapidly evolving. IBM continues pushing superconducting qubit technology with their Heron processors, while Google's Willow chip demonstrated error correction below the fault-tolerance threshold. Quantinuum (Honeywell + Cambridge Quantum) leads in trapped-ion systems with high gate fidelity. Microsoft is betting on topological qubits for better stability, and startups like PsiQuantum are pursuing photonic approaches. The field is shifting from 'quantum supremacy' demos toward practical quantum advantage—with near-term applications emerging in drug discovery, materials science, and financial optimization.
Present both sides of the debate: Should social media platforms be regulated as public utilities?
For regulation: Social media platforms have become essential public infrastructure—billions rely on them for news, communication, and commerce. Their monopolistic network effects make meaningful competition nearly impossible, similar to telephone or electric utilities. Regulation could ensure fair access, content moderation transparency, data portability, and algorithmic accountability. Against regulation: Utility classification would stifle innovation by imposing rigid operational frameworks on rapidly evolving technology. Private companies have First Amendment rights to moderate content. Heavy regulation could entrench incumbents by making compliance costs prohibitive for startups. Market forces and user choice, not government oversight, should drive platform behavior. The EU's Digital Services Act offers a middle path—targeted obligations without full utility designation.
Pricing
API Integration
Use our OpenAI-compatible API to integrate Grok 3 into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("grok-3", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("grok-3", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("grok-3", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — xAI's Grok 3
xAI was founded by Elon Musk in March 2023 alongside engineers and researchers recruited from DeepMind, OpenAI, Google Research, Microsoft Research and Tesla, including Igor Babuschkin, Tony Wu, Christian Szegedy, Jimmy Ba and Yuhuai Wu. The lab's stated mission is to 'understand the true nature of the universe' and to build maximally truth-seeking AI. xAI's flagship product is Grok, an LLM-based assistant integrated into the X (formerly Twitter) platform; Grok 1 was released as open weights under Apache 2.0 in November 2023 with 314B parameters in a Mixture-of-Experts configuration. Grok 1.5 introduced long context (128K) and vision, Grok 2 launched in mid-2024, and Grok 3 was unveiled in February 2025 trained on the Colossus supercluster of ~100,000-200,000 NVIDIA H100 GPUs in Memphis, Tennessee. xAI raised $6 billion in May 2024 at a $24 billion valuation and another reported $6 billion later in 2024, with investors including Andreessen Horowitz, Sequoia and Saudi Arabian funds. The company also operates the Grok API and integrates Grok into the Premium+ tier of X.
Visit xAI →Grok 3 was unveiled by xAI on 17 February 2025. It is a decoder-only Transformer trained on the company's Colossus supercluster in Memphis, which xAI reports as the largest single training cluster in the world at launch (~100,000 NVIDIA H100 GPUs at first, scaling to ~200,000). The training run reportedly used roughly 10x the compute of Grok 2. Pretraining used a multi-trillion-token mixture of web text, code, mathematical content, scientific papers and a continuously updated stream of public posts from the X platform, which gives Grok unusually fresh real-world data. Post-training combined supervised fine-tuning, RLHF and large-scale reinforcement learning against verifiable rewards on math, code and reasoning tasks. Grok 3 introduced two reasoning modes: 'Think' which produces an internal chain-of-thought and 'Big Brain' (later renamed) which spends additional test-time compute on complex problems. The model family also ships a Grok 3 mini variant tuned for low-latency and cost. Grok 3 supports a 1,000,000 token context window in the API, vision input, function calling and DeepSearch agent mode which crawls X and the public web with retrieval-augmented reasoning.
- Parameters
- Undisclosed (estimated multi-hundred billion dense parameters)
- Context
- 1M tokens
- 1,000,000 token context window in the API
- Two reasoning modes: Think (chain-of-thought) and high-effort variants
- DeepSearch agent that searches X and the public web with retrieval-augmented reasoning
- Trained on the Colossus 100K-200K H100 supercluster
- Vision input for images and screenshots
- Function calling and structured JSON output
- Real-time access to X (Twitter) posts via integrated tooling
- Top scores on AIME 2025, GPQA and Codeforces benchmarks at launch
- Available in X Premium+ and via the standalone Grok app
- Grok 3 mini variant for low-cost workloads
- Best for: real-time information chat, reasoning over X data, math/code benchmarks, edgy/uncensored content.
Multi-trillion-token pretraining corpus combining web text, code, scientific literature and a uniquely large continuous feed of public X (Twitter) posts. Knowledge cutoff is approximately late 2024 with live retrieval available via DeepSearch. Post-training uses RLHF and reinforcement learning against verifiable rewards.
License: Proprietary commercial license via the xAI API and X Premium+ subscription. Grok 1 weights were open under Apache 2.0; Grok 3 weights are not released.
Known limitations
- Lower refusal rate can yield offensive or politically charged outputs
- Limited third-party safety evaluations published
- DeepSearch quality depends on the X corpus and can amplify low-quality posts
- Region restrictions in some jurisdictions
- Vision quality below GPT-4o/Gemini on dense charts
Frequently asked questions
Related Models
View all Text & ChatClaude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Sonnet 4
Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.
DeepSeek V3.1
DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.
DeepSeek V4 Pro
DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.
Start using Grok 3 today
Get started with free credits. No credit card required. Access Grok 3 and 100+ other models through a single API.