Polarison

GPT-6 Luna vs Grok 4.3: pricing and benchmarks

GPT-6 Luna is 92% cheaper on input tokens ($0.10 vs $1.25 per 1M). GPT-6 Luna is 80% cheaper on output tokens ($0.50 vs $2.50 per 1M). On our document Q&A workload (50,000 questions a month), GPT-6 Luna costs $55.00 a month versus $575.00 for Grok 4.3, 90% less. Epoch AI has not published a capability index score for GPT-6 Luna and Grok 4.3 yet.

Prices verified September 26, 2026.

Which should you choose?

Overall capability
Too close to call

Epoch AI has not published a capability index score for GPT-6 Luna and Grok 4.3 yet.

Price
GPT-6 Luna

GPT-6 Luna costs $0.20 per 1M tokens (3:1 input-to-output mix) vs $1.563 for Grok 4.3, 87% less.

Pricing and specs

GPT-6 LunaGrok 4.3
ProviderOpenAIxAI
API model IDgpt-6-lunagrok-4.3
Input / 1M tokens$0.10$1.25
Cached input / 1M tokens$0.01$0.20
Output / 1M tokens$0.50$2.50
Long-context rates$0.20 in / $0.75 out on long-context requests$2.50 in / $5.00 out above 200K prompt tokens
Context window1.05M tokens1M tokens
Max output128K tokens—
Batch discount50% off—

Monthly cost for real workloads

WorkloadGPT-6 LunaGrok 4.3Difference
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$35.00$287.50GPT-6 Luna 88% cheaper
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$55.00$575.00GPT-6 Luna 90% cheaper
Coding agent
10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens.
$24.80$256.00GPT-6 Luna 90% cheaper

Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.

GPT-6 Luna vs Grok 4.3 cost calculator

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.

GPT-6 Luna pricing notes

OpenAI’s most efficient GPT-6 model, for focused, high-volume tasks.

  • Cache writes are billed at $0.125 per 1M tokens.
  • Fast mode costs 2x the standard rate; Flex costs half.
  • Regional (data residency) endpoints add a 10% uplift, and EU data residency is available only with standard processing.
OpenAI official pricing ↗

Grok 4.3 pricing notes

An earlier Grok 4 model with a 1M-token context window.

  • Requests with 200K or more prompt tokens are billed at $2.50 input / $0.40 cached / $5 output for all tokens.
xAI official pricing ↗

Frequently asked questions

Is GPT-6 Luna cheaper than Grok 4.3?
GPT-6 Luna is 92% cheaper on input tokens ($0.10 vs $1.25 per 1M). GPT-6 Luna is 80% cheaper on output tokens ($0.50 vs $2.50 per 1M). On our document Q&A workload (50,000 questions a month), GPT-6 Luna costs $55.00 a month versus $575.00 for Grok 4.3, 90% less.
Which is more capable, GPT-6 Luna or Grok 4.3?
Epoch AI has not published a capability index score for GPT-6 Luna and Grok 4.3 yet.
How much does GPT-6 Luna cost per 1M tokens?
GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, and $0.01 per 1M cached input tokens on OpenAI’s standard tier.
How much does Grok 4.3 cost per 1M tokens?
Grok 4.3 costs $1.25 per 1M input tokens and $2.50 per 1M output tokens, and $0.20 per 1M cached input tokens on xAI’s standard tier.
Which has the larger context window, GPT-6 Luna or Grok 4.3?
GPT-6 Luna has the larger context window: 1.05M tokens versus 1M for Grok 4.3.

Related comparisons