Grok 4.20 Non-Reasoning
Grok 4.20 Non-Reasoning is xAI'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.
import { streamText } from 'ai'
const result = streamText({ model: 'xai/grok-4.20-non-reasoning', prompt: 'Why is the sky blue?'})Playground
Try out Grok 4.20 Non-Reasoning by xAI. 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.
Providers
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.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by xAI
| Model |
|---|
| 256K | 0.3s | 175tps | $1.00/M | $2.00/M | Read: $0.2/M Write: — | $5/K + input costs | — |  | 05/20/2026 | ||||
| 1M | 1.0s | 102tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | | 04/30/2026 | ||||
| 2M | 0.5s | 177tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | | 03/11/2026 | ||||
| 2M | 2.5s | 1789tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | | 03/09/2026 | ||||
| 1M | 1.0s | 249tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | — |  | 07/09/2025 | ||||
| 1M | 0.5s | 66tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | — | | 07/09/2025 |
About Grok 4.20 Non-Reasoning
Grok 4.20 Non-Reasoning was released March 9, 2026 as part of xAI's Grok 4.20 beta generation. It's optimized for speed and direct responses, producing answers without chain-of-thought reasoning overhead. The model features low hallucination rates and strict prompt adherence, making it suitable for production workloads that need precise, reliable output.
As a non-reasoning variant, Grok 4.20 Non-Reasoning skips intermediate reasoning traces and delivers answers directly. This reduces latency and output token cost per request, which is particularly valuable in high-throughput applications and agentic tool-calling loops where per-step speed compounds into overall workflow efficiency.
This model is currently in beta.
What To Consider When Choosing a Provider
- Configuration: Grok 4.20 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: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Grok 4.20 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
Conclusion
Grok 4.20 Non-Reasoning brings Grok 4.20 generation capabilities to speed-focused workloads. It pairs direct responses with xAI's reported low hallucination rates and strict prompt adherence. Remember it's beta when you plan production deployments.
Frequently Asked Questions
What does 'non-reasoning' mean for Grok 4.20 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 Non-Reasoning?
2M tokens.
Is Grok 4.20 Non-Reasoning in beta?
Yes. Grok 4.20 Non-Reasoning is currently in beta. Behavior, pricing, or availability may change before general availability.
What does Grok 4.20 Non-Reasoning cost?
Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.
How do I authenticate with Grok 4.20 Non-Reasoning through Vercel AI Gateway?
Use your Vercel AI Gateway API key with
xai/grok-4.20-non-reasoningas the model identifier. No separate xAI account is needed for gateway-managed access.How does Grok 4.20 Non-Reasoning compare to Grok 4.1 Fast Non-Reasoning?
Grok 4.20 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 Non-Reasoning?
Yes, Zero Data Retention is 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.