Grok 4.20
General purposeVisionToolsxAI · Released March 2026 · Knowledge cutoff September 2025
Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
It belongs to xAI's Grok family, where the 4.x generation leads on reasoning and Grok Build targets software engineering.
Facts and pricing
- Provider
- xAI
- Context window
- 2M tokens
- Input price
- 13.8 credits / 1M tokens ($1.25 raw)
- Output price
- 27.5 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 1.10x margin. Raw prices shown per 1M tokens.
Try Grok 4.20 now
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
xAI family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Grok 4.5 | 500K | 22.0 | 66.0 | July 2026 |
| Grok Build 0.1 | 256K | 11.0 | 22.0 | May 2026 |
| Grok 4.3 | 1M | 13.8 | 27.5 | April 2026 |
| Grok 4.20 Multi-Agent | 2M | 13.8 | 27.5 | March 2026 |
| Grok 4.20 | 2M | 13.8 | 27.5 | March 2026 |
Frequently asked questions
- What is Grok 4.20?
- Grok 4.20 is an AI model by xAI. Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
- How much does Grok 4.20 cost on Zeplik?
- Input tokens cost 13.8 credits per million and output tokens 27.5 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.
Related models
Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...
Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...