NOUMENOpen app
NOUMEN

xAI · Balanced

Grok 4.20

Added Mar 31, 2026

Compare models

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

Loading models…

Use in the app

SpaceXAI's Grok 4.20 flagship release with tool calling, multimodal input support, and a 2M-token context window. 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
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)
679 tokens
Longer than 60% of 473 models

Side by side

Grok 4.20 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 4.20xAIThis modelKimi K2.7 Code TEEMoonshotRemove
ProviderxAIMoonshot
Discovery tierBalancedOpen weights
AddedMar 31, 2026Aug 15, 2026
Limits
Context window2MBest262.14K
Max output131.07KBest65.54K
Average output679 tokens1.1K tokens
Pricing, USD per 1M tokens
Input$1.25$0.95Best
Output$2.50Best$4.00
Cache read$0.20$0.19Best
Performance
Throughput327.6 tok/s—
Time to first token1.8 s—
Request success (24h)99.8%—
Benchmark indexes
Intelligence Index25.725.8Best
Coding Index—60.8
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesNo
Parallel toolsNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Grok 4.20
  • Kimi K2.7 Code TEE

Intelligence Index

  • Grok 4.2025.7
  • Kimi K2.7 Code TEE25.8

Grok 4.20: Better than 62% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 60.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 24.5%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 4.7%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 858 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 1,038 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 11.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • Grok 4.20: 69.0%
    • Kimi K2.7 Code TEE: 79.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 12.2%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Grok 4.20: 34.5%
    • Kimi K2.7 Code TEE: 35.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • Grok 4.20: 91.1%Top
    • Kimi K2.7 Code TEE: 89.6%

  • IFBench

    Following precise output instructions

    • Grok 4.20: 81.2%Top
    • Kimi K2.7 Code TEE: 63.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 1.0%

  • SciCode

    Scientific computing in Python

    • Grok 4.20: —
    • Kimi K2.7 Code TEE: 47.8%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Grok 4.20: 37.9%
    • Kimi K2.7 Code TEE: 44.7%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Grok 4.20: 93.0%Top
    • Kimi K2.7 Code TEE: 90.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Grok 4.20: 69.0%
    • Kimi K2.7 Code TEE: 79.3%Top

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

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
327.6 tok/s
Faster than 93% of 260 models
Time to first token
1.8 s
Quicker than 78% of 260 models
Prompt cache hits
45.4%
About $0.77 per 1M input tokens with caching
Request success (24h)
99.8%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 75.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

xAI

Other xAI models, starting with the same family.