NOUMENOpen app
NOUMEN

xAI · Frontier

Grok Latest

Added May 3, 2026

Compare models

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

Loading models…

Use in the app

Compatibility alias that routes to the newest Grok model. Currently routes to Grok 4.7. 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
Frontier

Pricing

USD per 1M tokens
Input
$2.00
Output
$6.00
Cache read
$0.50

Reference prices as published by the model provider. API example

Specifications

Context window
500K
Max output
—

Side by side

Grok Latest 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 LatestxAIThis modelGrok 4.20xAIRemove
ProviderxAIxAI
Discovery tierFrontierBalanced
AddedMay 3, 2026Mar 31, 2026
Limits
Context window500K2MBest
Max output—131.07K
Average output—679 tokens
Pricing, USD per 1M tokens
Input$2.00$1.25Best
Output$6.00$2.50Best
Cache read$0.50$0.20Best
Performance
Throughput69.5 tok/s327.6 tok/sBest
Time to first token2.7 s1.8 sBest
Request success (24h)99.9%Best99.8%
Benchmark indexes
Intelligence Index46.3Best25.7
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
Reasoning effortlow, medium, high, xhigh—

Public evaluations

Benchmarks

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

  • Grok Latest
  • Grok 4.20

Intelligence Index

  • Grok Latest46.3
  • Grok 4.2025.7

Grok Latest tested at high reasoning effort

Grok Latest: Better than 92% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Grok Latest: 63.5%
    • Grok 4.20: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Grok Latest: 37.7%
    • Grok 4.20: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Grok Latest: 1,630 Elo
    • Grok 4.20: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Grok Latest: 1,707 Elo
    • Grok 4.20: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Grok Latest: 23.2%
    • Grok 4.20: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Grok Latest: 77.0%Top
    • Grok 4.20: 69.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Grok Latest: 18.9%
    • Grok 4.20: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Grok Latest: 42.3%Top
    • Grok 4.20: 34.5%

  • GPQA Diamond

    Graduate-level science questions

    • Grok Latest: —
    • Grok 4.20: 91.1%

  • IFBench

    Following precise output instructions

    • Grok Latest: —
    • Grok 4.20: 81.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Grok Latest: 24.7%
    • Grok 4.20: —

  • SciCode

    Scientific computing in Python

    • Grok Latest: 57.8%
    • Grok 4.20: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Grok Latest: —
    • Grok 4.20: 37.9%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Grok Latest: —
    • Grok 4.20: 93.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Grok Latest: 77.0%Top
    • Grok 4.20: 69.0%

Scores from Artificial Analysis, updated Oct 26, 2026. Grok Latest was tested at high reasoning effort; compare scores measured at the same effort.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
69.5 tok/s
Faster than 50% of 260 models
Time to first token
2.7 s
Quicker than 60% of 260 models
Prompt cache hits
16.4%
About $1.75 per 1M input tokens with caching
Request success (24h)
99.9%
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 92.8%
  • 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-latest",
    "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-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

xAI

Other xAI models, starting with the same family.