xAI: grok-4.20-multi-agent

Price, performance, capabilities, and a ready-to-use request for grok-4.20-multi-agent.

Compare models

grok-4.20-multi-agent

AvailablexAIChatCached input 84% less

Input / Output-50%: $1.25 / $2.50$0.625 / $1.25
Context: 1M
Max output: 128K
Modalities: VisionChat
Capabilities: Tool usePrompt CacheReasoning

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.
02
Send your first request
Copy the example for your language and run it against the endpoint.
chat_completionResponses API
POST/v1/responses
API format:
```
curl https://api.tokenlab.sh/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "grok-4.20-multi-agent",
    "input": "Hello!"
  }'
```

Pricing

Official price is the model maker's public baseline. TokenLab price is what you pay for this model on TokenLab.

Display Base Rates

Per 1M tokens

Official price: Input $1.25 / Output $2.50 / Cache read $0.20
TokenLab price: Input $0.625 / Output $1.25 / Cache read $0.10
Discount: -50%

Prompt cache pricing

Cache read

Official price: $0.20
TokenLab price: $0.10
Discount: -50%

	Official pricePer 1M tokens	TokenLab pricePer 1M tokens	Discount
Display Base Rates	Input $1.25 / Output $2.50 / Cache read $0.20	Input $0.625 / Output $1.25 / Cache read $0.10	-50%

Prompt cache pricing

Cache read

$0.20

$0.10

-50%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

No data yet

Model performance

Last updated Sep 17, 2026, 06:02 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open grok-4.20-multi-agent in Console with a prompt ready to edit or send.

Help me try grok-4.20-multi-agent with a short message at /v1/responses. Show the reply, latency, and cost.

Use cases

Best for

Reasoning

Multi-step reasoning, analysis, and research workflows

Vision

Reading images, parsing documents, and answering visual questions

Agents and tools

Handle reasoning, support triage, tool calls, and multi-step tasks.

Coding

Generate, review, or debug code in the tools you already use.

Knowledge assistants

Build chat, search, and retrieval with a clear price and capability profile.

Side-by-side test

Compare response quality, latency, and price side by side.

Prompt examples

Write a concise support reply and list the assumptions behind it.

Review this API design and call out the top three integration risks.

Turn a long changelog into release notes a non-engineer would read.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

How much does grok-4.20-multi-agent cost?

On TokenLab, grok-4.20-multi-agent costs Input $0.625 / Output $1.25 Per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What is grok-4.20-multi-agent best for?

grok-4.20-multi-agent supports JSON mode, Prompt Cache, Reasoning. You can open it directly in Create.

How do I test grok-4.20-multi-agent?

Open grok-4.20-multi-agent in Create. A sample for /v1/responses will be ready to try.

Which endpoint should grok-4.20-multi-agent use?

Use https://api.tokenlab.sh/v1/responses for grok-4.20-multi-agent. The request example below shows the matching code shape.

Can I test grok-4.20-multi-agent before integrating it?

Yes. Open Console starts a ready draft for grok-4.20-multi-agent and keeps your prompt after sign-in, so you don’t lose context.

Which operations does grok-4.20-multi-agent support?

grok-4.20-multi-agent supports chat_completion. Select an operation above to see its endpoint and request example.