LLM Comparison

GPT-6 Luna vs Granite 4.0 Micro

Side-by-side specs, pricing & capabilities · Updated September 2026

Add to comparison

2/6 models

Same tier:

	GPT-6 Luna	Granite 4.0 Micro
Organization	OpenAI	IBM
OpenTools Score		2 31.5
Family	GPT-6	Granite
Status	Current	Current
Release Date	Sep 2026	Oct 2025
Context Window	1.1M tokens	131K tokens
Input Price	$0.10/M tokens	$0.02/M tokens
Output Price	$0.50/M tokens	$0.11/M tokens
Pricing Notes	OpenAI standard API, USD per million tokens for prompts up to 272K input tokens: $0.10 input, $0.01 cached input, $0.125 cache writes, $0.50 output. Above 272K input tokens, the full request costs 2x input/cache and 1.5x output. Batch/Flex cost 50% of Standard; Fast costs 2x; regional processing adds 10% where available. Reasoning output tokens are charged at output rates.	—
Capabilities	textvisionreasoningcodingtool-uselong-contextcontext-caching	textcode
Training Cutoff	2026-05-18	—
Max Output	128K tokens	—
API Identifier	`gpt-6-luna`	`ibm-granite/granite-4.0-h-micro`
Benchmarks
Artificial Analysis Intelligence Index v4.3.2	37.2559686869738artificial-analysis	—
GPQA Diamond	—	33.6364artificial-analysis
AIME 2025	—	6artificial-analysis
	View GPT-6 Luna	View Granite 4.0 Micro

Cost Calculator

Enter your expected monthly token usage to compare costs.

Input tokens / month

Output tokens / month

Model	Input	Output	Total / mo	vs Best
Granite 4.0 MicroCheapest	$0.02	$0.06	$0.07	—
GPT-6 Luna	$0.10	$0.25	$0.35	+386%

OpenAI

GPT-6 Luna

GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, produces text, supports a 1,050,000-token context window and 128,000 output tokens, and is available through the Responses and Chat Completions APIs under the exact gpt-6-luna identifier.

IBM

Granite 4.0 Micro

Granite 4.0 Micro is a large language model from IBM. Supports up to 131,000 token context window. Available from $0.02/M input tokens.