When was Grok 4.20 Non-Reasoning released?

xAI released Grok 4.20 Non-Reasoning on 7 Apr 2026. It is available through the Opper gateway.

Does Grok 4.20 Non-Reasoning support zero data retention?

With abuse monitoring, yes. On Google Cloud through the Opper gateway, prompts and outputs are not used for training and are kept only for abuse monitoring.

Where is Grok 4.20 Non-Reasoning hosted?

See the per-route table for Grok 4.20 Non-Reasoning hosting locations and residency details.

Is Grok 4.20 Non-Reasoning trained on prompts and outputs?

No. Every hosting route for Grok 4.20 Non-Reasoning is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Grok 4.20 Non-Reasoning?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Grok 4.20 Non-Reasoning. Contact hello@opper.ai to receive it.

Grok 4.20 Non-Reasoning

by xAI

Released 28 days after Grok 4.20 Non-Reasoning · All xAI releases

Grok 4.20 Non-Reasoning is the speed-optimized production variant of xAI's March 2026 Grok 4.20 generation, returning direct answers without extended reasoning. It keeps a 2 million token context window and real-time integration with X data, enabling applications that need current information and low latency. The model supports native tool use, structured outputs, and image input across multimodal requests. Without the reasoning overhead of the chain-of-thought variants, the non-reasoning mode prioritizes response speed, reported at around 232 tokens per second output and roughly half-a-second time-to-first-token, making it a fit for interactive systems, support, and content generation. Released in March 2026, Grok 4.20 Non-Reasoning is xAI's high-throughput path for the 4.20 generation when you need capability, long context, and real-time grounding without the latency of reasoning steps.

Call Grok 4.20 Non-Reasoning on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

30K

Input price

$1.25 /1M$0.20 cache read

Output price

$2.50 /1M

Released

7 Apr 2026

Zero data retention with abuse monitoring
No training by default
GDPR DPA available

Available routes

Grok 4.20 Non-Reasoning runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Google Cloud	Multi		No	$1.25	$2.50	$0.20

Live routes and prices as JSON: api.opper.ai/v3/models?q=vertexai%2Fgrok-4.20-non-reasoning

Uptime and availability

Grok 4.20 Non-Reasoning runs on a single route through the Opper gateway today, so its availability is that provider's availability.

99.18%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. Set up a fallback chain.

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

Data handling per route

Each route hosting Grok 4.20 Non-Reasoning has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Google Cloud — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: With abuse monitoring, window not stated.
Training: No training on customer data.
Logging: Abuse monitoring
Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
GDPR DPA: DPA available
Transfer mechanism: SCCs

Benchmarks

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

Global rank#310 of 694 LLMs

TierEfficient

Intelligence Index14.2

Reasoning & knowledge

GPQA Diamond

78%

Humanity's Last Exam

28%

Long-context reasoning

23%

Agentic & tool use

Terminal-Bench Hard

17%

τ²-Bench Telecom

60%

Math & instruction following

IFBench

49%

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

Get started

Call Grok 4.20 Non-Reasoning through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Grok 4.20 Non-Reasoning is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

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 Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "vertexai/grok-4.20-non-reasoning",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);