tokenledger.dev

TokenLedger

Claude Opus 5.5 vs GPT-6 Luna

Claude Opus 5.5 vs GPT-6 Luna: blended $8.00 vs $0.20 per 1M tokens on a 3:1 mix, context 1,000,000 vs 1,050,000.

GPT-6 Luna is cheaper on the 3:1 blend by $7.80 per 1M tokens.

SpecClaude Opus 5.5GPT-6 Luna
ProviderAnthropicOpenAI
Open weightsNoNo
Context1,000,0001,050,000
Input $/1M$4.00$0.10
Output $/1M$20.00$0.50
Blended $/1M$8.00$0.20
Listed22 Sep 202622 Sep 2026

Try Anthropic

Try OpenAI

Monthly cost

Defaults follow the 3:1 blend: 3,000,000 input tokens and 1,000,000 output tokens. Move either slider, or type a volume.

Claude Opus 5.5$32.00
GPT-6 Luna$0.80
DifferenceGPT-6 Luna costs $31.20 less this month

Questions

Which is cheaper on a 3:1 blend, Claude Opus 5.5 or GPT-6 Luna?
GPT-6 Luna is cheaper on the 3:1 blend at $0.20 per 1M tokens, versus Claude Opus 5.5 at $8.00. The gap is $7.80 per 1M tokens. The blend weighs 3 input tokens for every 1 output token.
How do the Claude Opus 5.5 and GPT-6 Luna context windows compare?
GPT-6 Luna has the longer context window at 1,050,000 tokens, compared with Claude Opus 5.5 at 1,000,000 tokens, a difference of 50,000 tokens.
What does a month of 3,000,000 input tokens and 1,000,000 output tokens cost?
At 3,000,000 input tokens and 1,000,000 output tokens, Claude Opus 5.5 costs $32.00 and GPT-6 Luna costs $0.80. GPT-6 Luna costs $31.20 less for that month. This volume uses the same 3:1 ratio as the blended price.

Related comparisons

All models