Grok 4
ActiveMost capable Grok model.
Updated 3 days agoStructured data from Modeldex catalog
AgenticLong context
Knowledge cutoff
Jul 31, 2025(9 months ago)
API release
Jul 9, 2025(9 months ago)
Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.
History
Grok 4 became available via the xAI API on 2025-07-09.
Training & availability
Training data has a knowledge cutoff of 2025-07-31 — 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: 256K tokens.
-
Max output: 256K tokens.
-
Input modalities: text.
Recommended for: agentic, long-context.
Limitations
- Text-only — cannot process images, audio, or video inputs.
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-4",
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.
5.0M
@ $3/1M
2.0M
@ $15/1M
Input cost
$15
5.0M × $3/1M
Output cost
$30
2.0M × $15/1M
Total / month
$45
$540 / year
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Not supported
Price vs quality
Premium pricing
Priced like a frontier model. Quality tier pending more benchmark coverage.
- Quality percentile
- —
- Effective price
- $12/1M
- Pricing breakdown
- $3/1M in
$15/1M out
not enough benchmark coverage
/ 1M tokens (input + 3× output)
Community ratings
No ratings yet. Be the first to rate Grok 4.
Rate Grok 4
Sign in to rate and review.
Comments
Sign in to leave a comment.