AI model comparison

GPT-6 Luna vs Grok Build 0.1

Side by side comparison of GPT-6 Luna and Grok Build 0.1 on pricing, benchmark scores, context window, and more.

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

Input / 1M
$0.10
Output / 1M
$0.50
Context
1.05M

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows.

Grok Build 0.1 was retired on November 20, 2026. The prices and specs here are the last ones listed. Consider Grok 4.6 instead.

Input / 1M
$1
Output / 1M
$2
Context
256K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

openai logo

GPT-6 Luna

6.7x cheaper for a typical chat

Higher intelligence score

openai logo

GPT-6 Luna

27.9 vs 27.2 on Artificial Analysis

Larger context window

openai logo

GPT-6 Luna

1.05M vs 256K tokens

Newer release

openai logo

GPT-6 Luna

Released September 22, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

openai logoGPT-6 Luna27.9
x-ai logoGrok Build 0.127.2

Coding index

openai logoGPT-6 LunaNot available
x-ai logoGrok Build 0.151.5

Agentic index

openai logoGPT-6 LunaNot available
x-ai logoGrok Build 0.1Not available

Pricing

GPT-6 Luna vs Grok Build 0.1 API pricing

Per-token API rates. Cheaper option highlighted.

Metricopenai logoGPT-6 Lunax-ai logoGrok Build 0.1
Input tokensPer 1M tokens$0.10$1
Output tokensPer 1M tokens$0.50$2
Cached input (read)Per 1M tokens$0.01$0.20
Cache writePer 1M tokens$0.13Not available
Long-context pricingPer 1M tokens, for very long prompts$0.20 in / $0.75 out above 272K$2 in / $4 out above 200K
Web searchPer request$0.01$0.005

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

openai logoGPT-6 Luna$0.45
x-ai logoGrok Build 0.1$3

Coding task

30K in, 4K out

openai logoGPT-6 Luna$5$2.30 cached
x-ai logoGrok Build 0.1$38$14 cached

Long document summary

150K in, 2K out

openai logoGPT-6 Luna$16$2.50 cached
x-ai logoGrok Build 0.1$154$34 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricopenai logoGPT-6 Lunax-ai logoGrok Build 0.1
Context window1.05M tokens256K tokens
Max output128K tokens230K tokens
Input typesFile, Image, TextFile, Image, Text
Output typesTextText
Reasoning effort levelsMax, Extra high, High, Medium, Low, NoneNot available
Default reasoning effortMediumNot available
Release dateSeptember 22, 2026May 20, 2026

Features

Supported features

API features available for each model.

Metricopenai logoGPT-6 Lunax-ai logoGrok Build 0.1
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureNot supportedSupported
Stop sequencesNot supportedNot supported
Deterministic seedSupportedSupported
Verbosity controlSupportedNot supported

Our take

GPT-6 Luna is 6.7x cheaper for a typical chat. GPT-6 Luna scores higher on the Artificial Analysis Intelligence Index (27.9 vs 27.2). GPT-6 Luna has the larger context window (1.05M vs 256K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is GPT-6 Luna or Grok Build 0.1 cheaper?

GPT-6 Luna is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, while Grok Build 0.1 costs $1 per 1M input tokens and $2 per 1M output tokens.

Which has a bigger context window, GPT-6 Luna or Grok Build 0.1?

GPT-6 Luna supports up to 1.05M tokens of context, compared with 256K for Grok Build 0.1.

Is GPT-6 Luna smarter than Grok Build 0.1?

On the Artificial Analysis Intelligence Index, GPT-6 Luna scores 27.9 and Grok Build 0.1 scores 27.2, putting GPT-6 Luna ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use GPT-6 Luna and Grok Build 0.1 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-6 Luna and Grok Build 0.1 answer side by side and keep the better response.

openai logox-ai logo

Why choose? Ask both.

Send one prompt to GPT-6 Luna and Grok Build 0.1 at the same time. Compare the answers side by side and keep the best one.