Language models/xAI/Grok 4.20 Multi-Agent
xAItext1 route

Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent by xAI, through an OpenAI-compatible chat completions API.

grok-4.20-multi-agent-0309Get API key

Pricing USD per million tokens

TokensPer 1M tokens
Input$1.25
Cached input$1.25
Cache write (5 min)$1.25
Cache write (1 hour)$1.25
Output$2.50

Reasoning tokens are billed as output. Each answer's usage carries cost_usd, the amount taken from your balance; a request with no answer costs $0.00.

Request

curl
curl https://api.revana.si/v1/chat/completions \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-4.20-multi-agent-0309","messages":[{"role":"user","content":"Write a haiku about routing."}]}'
Python
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.revana.si/v1", api_key=os.environ["REVANA_API_KEY"])
reply = client.chat.completions.create(
    model="grok-4.20-multi-agent-0309",
    messages=[{"role": "user", "content": "Write a haiku about routing."}],
)
print(reply.choices[0].message.content)

Any OpenAI SDK works: set the base URL to https://api.revana.si/v1. Streaming, tools and the rest are in the chat completions docs.

Details

Model id
grok-4.20-multi-agent-0309
Maker
xAI
Endpoint
POST /v1/chat/completions
Streaming
Yes (server-sent events)
Routes
1

1 route

One route today. A request that gets no answer is not charged.

About the Grok 4.20 Multi-Agent API

How much does the Grok 4.20 Multi-Agent API cost?

Grok 4.20 Multi-Agent costs $1.25 per million input tokens, $1.25 per million cached input tokens and $2.50 per million output tokens on Revana. You pay from prepaid credit for the tokens each request used, with no subscription or minimum.

How do I call Grok 4.20 Multi-Agent from code?

Use any OpenAI SDK with base URL https://api.revana.si/v1 and your Revana API key, and set model to "grok-4.20-multi-agent-0309". POST /v1/chat/completions takes the OpenAI request body, streamed or not.

What happens if a request fails?

A request that gets no answer costs nothing.

Is Grok 4.20 Multi-Agent on Revana the same model?

Yes. Revana passes your request to xAI's model unchanged and returns its answer in the OpenAI format, with the usage it reported and what the request cost.

More from xAI

Also as markdown for agents. Every language model and price: llms.json.