Grok 3
Active80.1FrontierxAI's frontier reasoning model with real-time web access.
Intelligence Index
80.1/ 100
Frontierweighted across 8 benchmarks
- Math
- 88.6
- Reasoning
- 84.6
- General knowledge
- 83.2
- Coding
- 63.9
Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.
Overview
Grok 3 is xAI's most capable model with strong reasoning capabilities and real-time access to information through X's data firehose. Available through the xAI API and to X Premium subscribers.
History
Grok 3 became available via the xAI API on 2025-06-10.
Training & availability
Training data has a knowledge cutoff of 2025-02-28 — information about events after that date is unlikely to appear in the model's responses. xAI has not released the underlying model weights — access is via their hosted API only.
Capabilities
-
Context window: 131K tokens.
-
Max output: 16K tokens.
-
Input modalities: text, image.
-
Intelligence Index: 80.1/100.
Strongest categories: Math (89), Reasoning (85), General knowledge (83).
Recommended for: vision, math, agentic, frontier, reasoning.
Limitations
- The knowledge cutoff is 13 months old — this model will not know about recent events, releases, or API changes.
Pricing
- Input: $3.0000 per 1M tokens
- Output: $15.0000 per 1M tokens
Use the cost calculator above to estimate monthly spend for your workload.
Quick start
Minimal example using the OpenRouter API. Copy, paste, replace the key.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="sk-or-...",
)
resp = client.chat.completions.create(
model="xai/grok-3",
messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)Cost calculator
Estimate your monthly bill. Presets are typical workload sizes.
Providers & performance
2 providersMulti-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.
| Provider | Throughput | Latency (TTFT) | Input $ / 1M | Output $ / 1M | Context | Quant | Supports |
|---|---|---|---|---|---|---|---|
| xAI | 64tok/s | 518ms | $5 | $25 | 131K | — | tools · json |
| xAI | 50tok/s | 485ms | $3 | $15 | 131K | — | tools · json |
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| AIME 2024Math | 83.9% accuracy | Self-reported xAI model card |
| Aider PolyglotCoding | 53.3% pass@2 | Third-party Papers With Code |
| GPQA DiamondReasoning | 84.6% accuracy | Self-reported xAI model card |
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Supported
Price vs quality
Mid-tier performance at frontier pricing.
- Quality percentile
- 58.6%
- Effective price
- $12/1M
- Pricing breakdown
- $3/1M in
$15/1M out
Community ratings
Rate Grok 3
Sign in to rate and review.
Comments
Sign in to leave a comment.