Grok 4.20

x-ai/grok-4.20

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

InputFileImageText
OutputText
Input / Outputclub$1.325 / $2.65per 1M tokens · USD
Context window2Mtoken
Maximum output1.8Mtoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$1.325/ 1M token
InputInput length ≥ 200,001 tokensUS$2.65/ 1M token
Cache readUS$0.212/ 1M token
Cache readInput length ≥ 200,001 tokensUS$0.424/ 1M token
OutputUS$2.65/ 1M token
OutputInput length ≥ 200,001 tokensUS$5.3/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
FileImageText
Output
Text
Context window
2,000,000 token
Maximum output
1,800,000 token

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Grok 4.20, and who develops it?

Grok 4.20 is a model from x-ai. Its model ID on Vecbase is x-ai/grok-4.20. Grok 4.20 is a reasoning model from SpaceXAI 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 Vecbase?

For Grok 4.20, the Club plan lists USD 1.325 per 1 million input tokens and USD 2.65 per 1 million output tokens, as of 10/22/2026, 9:27:10 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Grok 4.20’s context window?

Grok 4.20 has a context window of 2,000,000 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Grok 4.20?

Grok 4.20 can generate up to 1,800,000 tokens per response. Your API or request settings may set a lower limit.

Can Grok 4.20 call tools in an agent workflow?

Yes. Grok 4.20 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Grok 4.20 support structured outputs?

Yes. Grok 4.20 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Grok 4.20 support?

Grok 4.20 accepts File, Image, and Text and produces Text.

Which providers make Grok 4.20 available through Vecbase?

Vecbase offers Grok 4.20 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Grok 4.20?

Use x-ai/grok-4.20 as the model identifier for Grok 4.20. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

What does an agent need to access Grok 4.20 through Vecbase?

To use Grok 4.20, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Grok 4.20?

We do not yet have a confirmed release date for Grok 4.20.

Which models can I compare with Grok 4.20 on Vecbase?

You can compare Grok 4.20 with Grok 4.20 Multi-Agent (x-ai/grok-4.20-multi-agent), Grok 4.3 (x-ai/grok-4.3), and Grok 4.5 (x-ai/grok-4.5). Check their capabilities and prices to find the best fit for your task.