When was Grok 3 Mini released?

xAI released Grok 3 Mini on 19 Feb 2025. It is available through the qynio gateway.

Does Grok 3 Mini support zero data retention?

Not by default. See the per-route data-handling section for each route's logging stance and retention window.

Where is Grok 3 Mini hosted?

Grok 3 Mini runs on US hosting routes through the qynio gateway.

Is Grok 3 Mini trained on prompts and outputs?

No. Every hosting route for Grok 3 Mini is configured so customer prompts and outputs are not used to train models by default.

Is a no-KYC deposit available for Grok 3 Mini?

Yes. A no-KYC Data Processing Agreement is available on at least one route serving Grok 3 Mini. Contact hello@qyn.io to receive it.

Grok 3 Mini

by xAI

All xAI releases

Grok 3 Mini is a smaller thinking model that verbalizes its reasoning before responding, making its internal thought process inspectable. It exposes reasoning tokens so you can follow how it arrived at an answer, which helps with debugging and trust in agentic workflows. It is suited to logic-based tasks, math, and structured problem solving where deep domain knowledge is not required. The model supports adjustable reasoning effort with low and high settings, structured outputs, and tool calling, making it a fit for applications that balance cost and reasoning quality on lighter workloads. With a 131k token context window and a May 2025 release, Grok 3 Mini offers a fast, compact alternative to larger reasoning models while keeping the transparent thinking that characterizes xAI's reasoning approach.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

16K

Input price

$0.30 /1M

Output price

$0.50 /1M

Released

19 Feb 2025

US residency available
No training by default
no-KYC deposit available

Available routes

Grok 3 Mini runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
xAI	US	Not by default	No	$0.30	$0.50

Uptime and availability

Grok 3 Mini runs on a single route through the qynio gateway today, so its availability is that provider's availability.

98.63%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting Grok 3 Mini has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

xAI — United States🇺🇸

Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; wallets; deposit available.

Zero data retention: Not by default — abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
no-KYC deposit: deposit available
Transfer mechanism: wallets

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#250 of 630 LLMs

TierEfficient

Intelligence Index22.9

Math Index84.7

Reasoning & knowledge

MMLU-Pro

83%

GPQA Diamond

79%

Humanity's Last Exam

11%

Long-context reasoning

53%

Coding

LiveCodeBench

70%

SciCode

41%

Agentic & tool use

Terminal-Bench Hard

17%

τ²-Bench Telecom

90%

Math & instruction following

AIME 2025

85%

IFBench

46%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Grok 3 Mini through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.QYN_API_KEY,
5  baseURL: "https://api.qyn.io/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "xai/grok-3-mini",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);