GPT-6 Luna Max vs Inkling 2 Small: which responds faster?

GPT-6 Luna (Max) and Inkling 2 Small are close rivals from OpenAI and Thinking Machines. Inkling 2 Small starts answering far sooner, with a time to first token of 2.2 seconds compared with 2.0 minutes for GPT-6 Luna Max. The figures come from tracked catalogue data, not from our own testing, so treat them as a starting point for a trial on your tasks.

Throughput and time to first token

Measured output speed is 121 tokens per second for GPT-6 Luna Max and 139 tokens per second for Inkling 2 Small. On long outputs, that is a real advantage for Inkling 2 Small. Time to first token is 2.0 minutes for GPT-6 Luna Max and 2.2 seconds for Inkling 2 Small. In an interactive app, Inkling 2 Small will feel noticeably more responsive. A first-token wait of that length suits background work better than live conversation.

Put together, a 2,000-token answer would take about 2.3 minutes from GPT-6 Luna Max and 17 seconds from Inkling 2 Small, counting the first-token wait.

Which is newer

Inkling 2 Small arrived on November 5, 2026, 44 days after GPT-6 Luna Max (September 22, 2026). That is close enough to count them as the same generation.

The headline benchmark

Inkling 2 Small comes out ahead on the intelligence index, 30.6 to 27.9. That is a modest edge: real, but small enough that the right set of tasks could reverse it. In relative terms, Inkling 2 Small scores 10% higher.

For context, that places GPT-6 Luna Max 62nd and Inkling 2 Small 52nd out of 109 scored models still on offer.

There are no coding or math index scores for either model in the catalogue, which keeps this comparison at the aggregate level.

Token pricing and a sample bill

The list prices are $0.10 in and $0.50 out for GPT-6 Luna Max, and $0.30 in and $1.00 out for Inkling 2 Small, per million tokens. Inkling 2 Small costs twice as much per output token.

For a sample workload of 1 million input tokens and 200,000 output tokens, GPT-6 Luna Max would cost $0.20 and Inkling 2 Small $0.50, a difference of $0.30. Scale it up to classifying 100,000 short messages at 150 input tokens and 5 output tokens each and the bill is $1.75 for GPT-6 Luna Max against $5.00 for Inkling 2 Small.

Is the price in proportion?

Per point of intelligence index, GPT-6 Luna Max costs $0.0072 of blended price per million tokens and Inkling 2 Small $0.016. GPT-6 Luna Max delivers each index point for 54% less; whether Inkling 2 Small's extra 2.7 points are worth the premium depends on how often your tasks need them.