Skip to content
Dashboard

Grok 4.20 Beta Non-Reasoning

Grok 4.20 Beta Non-Reasoning is SpaceXAI's non-reasoning model in the Grok 4.20 beta generation, optimized for speed and direct responses with low hallucination rates and strict prompt adherence.

View API reference
Input and output price
Input $1.25, Output $2.50, Per 1M tokens
24h uptime
Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingPlayground

Try out Grok 4.20 Beta Non-Reasoning by SpaceXAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

spacexai logo
spacexai logo

Grok 4.20 Beta Non-Reasoning

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Free Tier
Release Date
2M2M
$1.25/M+1 more
$2.50/M+1 more
Read$0.20/M
$5/K
+2
03/11/2026

Copy link to headingUptime

Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.

Copy link to headingThroughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.

Copy link to headingLatency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.

Getting started

Call Grok 4.20 Beta Non-Reasoning through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
prompt: 'Why is the sky blue?',
});
console.log(result.text);
}
main().catch(console.error);

Top-level parameters

The same Grok 4.20 Beta Non-Reasoning request in each API format AI Gateway supports.

top-level-params.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
system: 'You are a concise technical assistant.',
prompt: 'Summarize the tradeoffs between static generation and SSR.',
maxOutputTokens: 1024,
temperature: 0.5,
});
console.log(result.text);
}
main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. spacexai/grok-4.20-non-reasoning-beta. AI Gateway routes the request to an available provider.
maxOutputTokensnumberNoHard cap on generated tokens. Grok 4.20 Beta Non-Reasoning supports up to 2,000,000 output tokens.
providerOptionsRecord<string, JSONValue>NoAI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

InputFormatsSourcesMax countMax sizeLimits
TextPrompt and response share the 2M-token context window
ImageURL, base64, Uint8ArraySent as image parts in messages; counts as input tokens
PDFURL, base64, Uint8ArraySent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK xai provider docs.

provider-options.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
prompt: 'Why is the sky blue?',
providerOptions: {
gateway: {
only: ['xai'],
},
},
});
console.log(result.text);
}
main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

ParameterTypeRequiredDescription
providerOptions.gateway.onlystring[]NoRestrict routing to these provider slugs. Requests fail over only within the listed providers.
providerOptions.gateway.orderstring[]NoPreferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
providerOptions.gateway.sort'cost' | 'ttft' | 'tps'NoRank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
providerOptions.gateway.zeroDataRetentionbooleanNoRoute only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Describe this image.' },
{ type: 'image', image: 'https://example.com/photo.jpg' },
],
},
],
});
console.log(result.text);
}
main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Summarize this document.' },
{
type: 'file',
mediaType: 'application/pdf',
data: 'https://example.com/document.pdf',
},
],
},
],
});
console.log(result.text);
}
main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts
import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'spacexai/grok-4.20-non-reasoning-beta',
prompt: 'What is the weather in San Francisco?',
tools: {
getWeather: tool({
description: 'Get the current weather for a location',
inputSchema: z.object({ location: z.string() }),
execute: async ({ location }) => ({ location, temperatureC: 18 }),
}),
},
});
console.log(result.text);
}
main().catch(console.error);

Copy link to headingMore models by SpaceXAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Free Tier
Release Date
500K
$2/M+1 more
$6/M+1 more
Read$0.50/M
$5/K
+1
xai logo
08/12/2026
500K
$2/M+1 more
$6/M+1 more
Read$0.30/M
$5/K
+3
xai logo
07/08/2026
1M
$1.25/M+1 more
$2.50/M+1 more
Read$0.20/M
$5/K
+3
vertex logo
xai logo
04/30/2026
2M
$1.25/M+1 more
$2.50/M+1 more
Read$0.20/M
$5/K
+2
vertex logo
xai logo
03/10/2026
1M
$0.20/M
$0.50/M
Read$0.05/M
+1
vertex logo
11/19/2025
1M
$0.20/M
$0.50/M
Read$0.05/M
+2
vertex logo
11/19/2025

Copy link to headingAbout Grok 4.20 Beta Non-Reasoning

Grok 4.20 Beta Non-Reasoning was released March 11, 2026 as the beta-tagged variant of SpaceXAI's Grok 4.20 non-reasoning model. It produces direct answers without chain-of-thought overhead, optimizing for speed and strict prompt adherence rather than deliberation depth.

The non-reasoning architecture makes Grok 4.20 Beta Non-Reasoning well suited for agentic pipelines where individual steps need fast, deterministic responses: tool selection, structured data extraction, classification, and routing decisions. Low hallucination rates and tight prompt following reduce the need for output validation in automated workflows.

As a beta release, Grok 4.20 Beta Non-Reasoning may receive weight updates or behavior changes before SpaceXAI stabilizes it. Teams running production traffic should use the stable grok-4.20-non-reasoning and reserve Grok 4.20 Beta Non-Reasoning for evaluation and staging.

Copy link to headingWhat To Consider When Choosing a Provider

  • Configuration: Grok 4.20 Beta Non-Reasoning is in beta. Expect potential changes to behavior, pricing, or availability before general availability.
  • Configuration: This variant produces direct answers. If you need the model to reason through complex problems step by step, use the Grok 4.20 Reasoning variant instead.
  • Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Grok 4.20 Beta Non-Reasoning

Best for

  • High-throughput production APIs: Direct, precise answers at low latency serve end users best
  • Agentic tool-calling workflows: That benefit from fast decision-making with low hallucination rates
  • Classification and routing pipelines: That need reliable, prompt-adherent output for downstream processing
  • Chat and conversational interfaces: Low-hallucination, prompt-adherent responses arrive quickly without chain-of-thought overhead
  • Content generation tasks: Where strict prompt adherence matters more than deep reasoning

Consider alternatives when

  • Complex analytical tasks: Requiring multi-step reasoning. Use the Grok 4.20 Reasoning variant
  • Multi-agent orchestration: The Grok 4.20 Multi-Agent variant is purpose-built for agent collaboration
  • Stable production deployments: Beta models introduce unwanted risk. Use Grok 4.1 Fast Non-Reasoning instead
  • Maximum cost efficiency on simple tasks: Grok 3 Mini Fast offers lower per-token costs

Grok 4.20 Beta Non-Reasoning trades reasoning depth for speed. Use it in agentic pipelines where fast, direct responses matter more than extended deliberation. For production stability, prefer the non-beta grok-4.20-non-reasoning.

Copy link to headingFrequently Asked Questions

  • What does 'non-reasoning' mean for Grok 4.20 Beta Non-Reasoning?

    The model produces direct answers without generating chain-of-thought reasoning traces. This reduces latency and output token cost compared to the reasoning variant.

  • What is the context window for Grok 4.20 Beta Non-Reasoning?

    2M tokens.

  • Is Grok 4.20 Beta Non-Reasoning in beta?

    Yes. Grok 4.20 Beta Non-Reasoning is currently in beta. Behavior, pricing, or availability may change before general availability.

  • What does Grok 4.20 Beta Non-Reasoning cost?

    Current pricing is shown on this page. AI Gateway routes across providers, and rates may vary by provider.

  • How do I authenticate with Grok 4.20 Beta Non-Reasoning through Vercel AI Gateway?

    Use your Vercel AI Gateway API key with spacexai/grok-4.20-non-reasoning-beta as the model identifier. No separate SpaceXAI account is needed for gateway-managed access.

  • How does Grok 4.20 Beta Non-Reasoning compare to Grok 4.1 Fast Non-Reasoning?

    Grok 4.20 Beta Non-Reasoning is the newer generation with improved hallucination rates and prompt adherence. Grok 4.1 Fast Non-Reasoning is a stable, generally available alternative if you prefer to avoid beta models.

  • Does Vercel AI Gateway support Zero Data Retention for Grok 4.20 Beta Non-Reasoning?

    Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

Your use is subject to SpaceXAI's Terms & Privacy Policies.