Overview
Grok 4.20 (0309 Non-Reasoning) is the non-reasoning variant of xAI's Grok 4.20, a high-performance model built for agentic tool calling and strict prompt adherence. xAI says it aims for precise and truthful responses. It supports tool calling and structured output, accepts text and image input, returns text, and has a 1M-token context window.
It has a 1M-token context window. It accepts text and image input and returns text.
Capabilities
This variant answers directly without a dedicated reasoning phase, which suits requests that do not need long deliberation. It keeps the tool calling and structured output that agentic workflows depend on.
Text and images can be sent together, and the 1M-token context window leaves room for long prompts, documents and tool results. Replies are text.
Pricing
Grok 4.20 (0309 Non-Reasoning) is priced from $1.25 per 1M input tokens and $2.50 per 1M output tokens. Cached input reads cost $0.20 per 1M tokens. The prices shown are for the starting tier; requests with very long prompts are billed at higher rates.
Grok 4.20 (0309 Non-Reasoning) is available through RealRelay's OpenAI-compatible API.
Use cases
Use Grok 4.20 (0309 Non-Reasoning) for high-volume agent steps where each call is simple: routing a request, calling a tool, extracting fields from a document and returning them as structured data.
It also suits assistants that must stick closely to written instructions, such as support bots answering from a long policy document that is supplied in the prompt.
What is Grok 4.20 (0309 Non-Reasoning)?
Grok 4.20 (0309 Non-Reasoning) is the non-reasoning variant of xAI's Grok 4.20, a high-performance model built for agentic tool calling and strict prompt adherence. xAI says it aims for precise and truthful responses. It supports tool calling and structured output, accepts text and image input, returns text, and has a 1M-token context window.
How much does Grok 4.20 (0309 Non-Reasoning) cost?
Grok 4.20 (0309 Non-Reasoning) is priced from $1.25 per 1M input tokens and $2.50 per 1M output tokens. Cached input reads cost $0.20 per 1M tokens. The prices shown are for the starting tier; requests with very long prompts are billed at higher rates.
What is the context window of Grok 4.20 (0309 Non-Reasoning)?
Grok 4.20 (0309 Non-Reasoning) has a 1M-token context window.
What inputs and outputs does Grok 4.20 (0309 Non-Reasoning) support?
Grok 4.20 (0309 Non-Reasoning) accepts text and image input and returns text.
Does Grok 4.20 (0309 Non-Reasoning) support tool calling?
Yes. Grok 4.20 (0309 Non-Reasoning) supports tool calling and structured output, and it accepts text and image input.
What is Grok 4.20 (0309 Non-Reasoning) used for?
Use Grok 4.20 (0309 Non-Reasoning) for high-volume agent steps where each call is simple: routing a request, calling a tool, extracting fields from a document and returning them as structured data.
How do I call Grok 4.20 (0309 Non-Reasoning) through the API?
Call Grok 4.20 (0309 Non-Reasoning) through RealRelay's OpenAI-compatible API by setting the model field to xai/grok-4.20-0309-non-reasoning.