How much does Grok 4.20 cost on Zeplik?

Input tokens cost 15.0 credits per million and output tokens 30.0 credits per million (1 credit = $0.10; the raw provider rates are $1.25 and $2.50 per million). New accounts start with free credits.

How long can a conversation with Grok 4.20 be?

Grok 4.20 has a 2M-token context window (2,000,000 tokens), which covers the conversation plus any documents you attach.

Does Grok 4.20 support images and tools?

Grok 4.20 accepts image input and supports tool calling.

Grok 4.20

General purposeVisionTools

SpaceXAI · Released March 2026 · Knowledge cutoff September 2025

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.

It belongs to SpaceXAI's Grok family (the lab was previously xAI), where Grok 4.7 leads on reasoning and long-running engineering work and Grok Build targets software engineering.

Facts and pricing

Provider: SpaceXAI
Context window: 2M tokens
Input price: 15.0 credits / 1M tokens ($1.25 raw)
Output price: 30.0 credits / 1M tokens ($2.50 raw)
Vision (image input): Yes
Tool calling: Yes
Extended reasoning: No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.

Try Grok 4.20 now

Or open Zeplik with Grok 4.20 already selected

What Grok 4.20 is best for

Balanced everyday work: writing, questions, brainstorming and summarization
Very long documents and codebases: a 2M-token window fits entire books or repositories in one conversation
Working with images: screenshots, charts, photos and scanned documents alongside text
Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Example prompts

Prompts that suit a general purpose model like Grok 4.20:

Help me outline a talk about what I learned this year
Compare these two paragraphs and tell me which is clearer and why
Draft a polite reply declining this invitation
Explain this concept with a concrete everyday analogy

SpaceXAI family

Model	Context	Input cr/M	Output cr/M	Released
Grok 4.7	500K	24.0	72.0	September 2026
Grok 4.6	500K	24.0	72.0	August 2026
Grok 4.5	500K	24.0	72.0	July 2026
Grok Build 0.1	256K	12.0	24.0	May 2026
Grok 4.3 (batch)	1M	12.0	24.0	April 2026
Grok 4.3	1M	15.0	30.0	April 2026
Grok 4.20 Multi-Agent	2M	15.0	30.0	March 2026
Grok 4.20	2M	15.0	30.0	March 2026

Model comparisons

Frequently asked questions

What is Grok 4.20?: Grok 4.20 is an AI model by SpaceXAI. Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.
How much does Grok 4.20 cost on Zeplik?: Input tokens cost 15.0 credits per million and output tokens 30.0 credits per million (1 credit = $0.10; the raw provider rates are $1.25 and $2.50 per million). New accounts start with free credits.
How long can a conversation with Grok 4.20 be?: Grok 4.20 has a 2M-token context window (2,000,000 tokens), which covers the conversation plus any documents you attach.
Does Grok 4.20 support images and tools?: Grok 4.20 accepts image input and supports tool calling.