Grok 3 Mini — xAI | Modeldex

Grok 3 Mini

Active

Fast and cost-efficient reasoning model.

Updated 4 days agoStructured data from Modeldex catalog

Agentic

Knowledge cutoff

Feb 28, 2025(1.1 years ago)

API release

Jun 10, 2025(10 months ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

History

Grok 3 Mini 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

Input modalities: text.

Recommended for: agentic.

Limitations

The knowledge cutoff is 13 months old — this model will not know about recent events, releases, or API changes.
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-3-mini",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Providers & performance

2 providers

Multi-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	56tok/s	428ms	$0.3	$0.5	131K	—	tools · json
xAI	—	—	$0.6	$4	131K	—	tools · json

Benchmarks

Benchmark	Score	Source
Aider PolyglotCoding	34.7% pass@2	Third-party Papers With Code

Integrations & tooling support

Tool calling: Supported
Structured outputs: Not supported

Price vs quality

Below-average benchmarks

Performance trails frontier models. Pricing not publicly available — check the provider.