head-to-head

OpenAI: GPT-6.1 Sol Pro vs OpenAI: GPT-6 Luna (batch)

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-19.

OpenAI: GPT-6.1 Sol Pro OpenAI: GPT-6 Luna (batch)
Vendoropenaiopenai
Quality Score100100
Input Price$2.00/M$0.05/M
Output Price$10.00/M$0.25/M
Context Window1,050,0001,050,000
Max Output128,000128,000
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--

The verdict

For a sample job of 1 million input tokens and 250,000 output tokens, GPT-6 Luna (batch) costs $0.11 and GPT-6.1 Sol Pro costs $4.50, so GPT-6 Luna (batch) is about 40.0 times cheaper for the same work.

Both read up to 1,050,000 tokens at once, roughly 1,575 pages of text.

Across the 10 tasks where they differ, GPT-6 Luna (batch) on 10 (SQL Generation, Code Completion, Code Documentation and others).

Pick GPT-6 Luna (batch) if you need lower cost or the stronger all-round task scores.

Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.

Who wins by task?

TaskOpenAI: GPT-6.1 Sol ProOpenAI: GPT-6 Luna (batch)
SQL Generation 132 134
Code Completion 117 131
Code Documentation 129 131
Regex Writing 117 119
CSV / Spreadsheet Cleanup 132 134
JSON Extraction 121 131
Bulk Data Labeling 118 129
Long-Document Summarization 136 138
Short-Form Summarization 113 123
Blog Post Writing 120 122

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Google: Gemini 4 Neon vs OpenAI: GPT-6.1 Sol Pro Google: Gemini 4 Neon (batch) vs OpenAI: GPT-6.1 Sol Pro OpenAI: GPT-6.2 Sol Pro vs OpenAI: GPT-6.1 Sol Pro OpenAI: GPT-6.2 Sol Pro (batch) vs OpenAI: GPT-6.1 Sol Pro OpenAI: GPT-6.2 Sol vs OpenAI: GPT-6.1 Sol Pro OpenAI: GPT-6.2 Sol (batch) vs OpenAI: GPT-6.1 Sol Pro Tencent: Hy4 flash vs OpenAI: GPT-6.1 Sol Pro Qwen: Qwen4 Max vs OpenAI: GPT-6.1 Sol Pro

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.