NOUMENOpen app
NOUMEN

xAI · Balanced

Grok 4.20 Multi-Agent

Added Mar 31, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Grok 4.20 Multi-Agent is tuned for collaborative agentic workflows while keeping the same 2M-token context window and multimodal support. Content policy rejections can still be charged: SpaceXAI may pass through a $0.05 moderation-failure fee, or a $0.055 usage-guidelines violation fee, depending on which rejection upstream returns.

  • Reasoning
  • Tools
  • Vision
  • Structured output
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$1.25
Output
$2.50
Cache read
$0.20

Reference prices as published by the model provider. API example

Specifications

Context window
2M
Max output
131.1K
Average output (7 days)
3.3K tokens
Longer than 97% of 465 models

Side by side

Grok 4.20 Multi-Agent compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Grok 4.20 Multi-AgentxAIThis modelGPT 5.1 CodexOpenAIRemove
ProviderxAIOpenAI
Discovery tierBalancedBalanced
AddedMar 31, 2026Nov 13, 2025
Limits
Context window2MBest400K
Max output131.07KBest128K
Average output3.3K tokens22 tokens
Pricing, USD per 1M tokens
Input$1.25$1.25
Output$2.50Best$10.00
Cache read$0.20$0.13Best
Benchmark indexes
Intelligence Index—23.7
Math Index—95.7
Capabilities
ReasoningYesYes
ToolsYesNo
VisionYesYes
Structured outputYesNo
Reasoning effortlow, medium, high, xhigh—

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Grok 4.20 Multi-Agent
  • GPT 5.1 Codex

Intelligence Index

  • Grok 4.20 Multi-Agent—
  • GPT 5.1 Codex23.7
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 95.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 69.3%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 25.7%

  • GPQA Diamond

    Graduate-level science questions

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 86.0%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 86.0%

  • IFBench

    Following precise output instructions

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 70.0%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 84.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 95.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 34.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 83.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Grok 4.20 Multi-Agent: —
    • GPT 5.1 Codex: 69.3%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.20-multi-agent",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="x-ai/grok-4.20-multi-agent",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

xAI

Other xAI models, starting with the same family.