By the toolist.ai editors. Researched from public sources, not hands-on tested by toolist.ai. Updated October 27, 2026; prices checked October 21, 2026.
GPT-6.1 Sol vs GPT-6 Luna
Verdict
Use GPT-6.1 Sol for complex coding and agent work, and GPT-6 Luna for focused, high-volume jobs. Luna costs a twentieth of Sol's price ($0.10 and $0.50 against $2 and $10 per million tokens), but Sol scores higher on all five Artificial Analysis scores both have, including 56% against 13% on Terminal-Bench 4.0 and 58% against 9% on Terminal-Bench-Science.
Verdict based on published prices, limits and benchmarks, not on our own tests.
Choose GPT-6.1 Sol if
- You run coding agents or long terminal work: 56% against 13% on Terminal-Bench 4.0
- You need stronger reasoning at the default setting: 46 against 18 on the Intelligence Index at medium effort
- You want Ultrafast mode for lower latency, which OpenAI prices for Sol at six times the standard rate and not for Luna
Choose GPT-6 Luna if
- Volume matters most: Luna's $0.10 and $0.50 per million tokens against Sol's $2 and $10
- Your function calls need no reasoning, since Luna accepts the "none" effort level and GPT-6.1 Sol does not
- You want typed answers from OpenAI's Decisions API, which launched in beta with GPT-6 Luna
- You want the more recent knowledge cutoff (May 18, 2026 against April 30, 2026)
Price
Input costs 20 times as much on GPT-6.1 Sol as on GPT-6 Luna. Output costs 20 times as much on GPT-6.1 Sol as on GPT-6 Luna.
| Per million tokens | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| Input | $2 source | $0.10 source |
| Cached input | $0.10 source | $0.01 source |
| Output | $10 source | $0.50 source |
GPT-6.1 Sol: Prompts over 272,000 input tokens are billed at twice the input rate and 1.5 times the output rate for the whole request. Batch and Flex processing cost half; Fast mode costs double and Ultrafast six times.
GPT-6 Luna: Prompts over 272,000 input tokens are billed at twice the input and cache rates and 1.5 times the output rate for the whole request. Cache writes cost $0.125 per million tokens (30-minute cache) or $0.25 (12-hour cache). Batch and Flex cost half; Fast mode costs double. OpenAI lists no Ultrafast price for it.
Worked example: what a month costs
We priced three monthly workloads at the standard rates. The provider does not publish these figures.
| Workload | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| Support chatbot 100,000 replies, each 3,000 input and 400 output tokens, no caching (300M in, 40M out) | $1,000 | $50.00 |
| Document Q&A 5,000 questions over the same 60,000-token document set (90% cache hits), 800 output tokens each (300M in, 4M out) | $127 | $7.70 |
| Coding agent 200 tasks, each 1.5 million input tokens (90% cache hits) and 50,000 output tokens (300M in, 10M out) | $187 | $10.70 |
Price your own workload
| Model | Cost a month |
|---|---|
| GPT-6.1 Sol | $150 |
| GPT-6 Luna | $7.50 |
Standard API prices, no batch or priority discounts. Cached input is billed at the cache-read price; cache-write charges are not included. Reasoning models bill their thinking as output tokens.
Limits and release dates
| GPT-6.1 Sol | GPT-6 Luna | |
|---|---|---|
| Released | September 29, 2026 source | September 22, 2026 source |
| Context window | 1,050,000 tokens source | 1,050,000 tokens source |
| Maximum output | 128,000 tokens source | 128,000 tokens source |
| Knowledge cutoff | April 30, 2026 source | May 18, 2026 source |
| Input and output | Text and images in; text out source | Text and images in; text out source |
| API model name | gpt-6.1-sol | gpt-6-luna |
Benchmarks
Scores as published by the provider or measured by Artificial Analysis; higher is better. A dash means no score was published.
| Benchmark | GPT-6.1 Sol | GPT-6 Luna |
|---|---|---|
| Artificial Analysis Intelligence Index max effort | 55.0 source | 28.0 source |
| Intelligence Index at everyday effort medium effort, the API default | 46.0 source | 18.0 source |
| Terminal-Bench 4.0 max effort | 56.0% source | 13.0% source |
| HLE-Diamond max effort | 59.0% source | 22.0% source |
| Terminal-Bench-Science 0.1 max effort | 58.0% source | 9.0% source |
| Output speed | 58.9 tokens/s (medium effort, Artificial Analysis) source | 124.3 tokens/s (max effort, Artificial Analysis; no medium-effort figure is published) source |
Benchmark and speed data from Artificial Analysis where linked.
Read more
- GPT-6.1 Sol: price, context window and benchmarks
- GPT-6 Luna: price, context window and benchmarks
- Gemini 4 Argon vs GPT-6.1 Sol
- GPT-6.1 Sol vs Claude Opus 5.5
- GPT-6.1 Sol vs Claude Sonnet 5.5
- GPT-6.1 Sol vs GPT-6 Astra
- GPT-6.1 Sol vs GPT-6 Sol
- GPT-6.1 Terra vs GPT-6.1 Sol
- GPT-6 Luna vs Claude Haiku 5.5
- AI model API price table
Sources
- OpenAI API docs: GPT-6.1 Sol (checked 2026-10-21)
- OpenAI API docs: Pricing (checked 2026-10-21)
- OpenAI API docs: Changelog (checked 2026-10-21)
- OpenAI API docs: Reasoning models (checked 2026-10-21)
- OpenAI API docs: GPT-6.1 Sol vs GPT-6 Sol (checked 2026-10-21)
- ChatGPT docs: Models (checked 2026-10-21)
- Artificial Analysis: GPT-6.1 Sol (max) (checked 2026-10-27)
- Artificial Analysis: GPT-6.1 Sol (medium) (checked 2026-10-27)
- Artificial Analysis: GPT-6.1 Sol vs GPT-6 Astra (checked 2026-10-27)
- OpenRouter: GPT-6.1 Sol (checked 2026-10-21)
- GPT-6.1 Sol vs GPT-6 Luna (checked 2026-10-27)
- OpenAI API docs: GPT-6 Luna (checked 2026-10-21)
- OpenAI API docs: Using GPT-6 (checked 2026-10-21)
- ChatGPT docs: Pricing and plan access (checked 2026-10-21)
- GPT-6 Luna (max) (checked 2026-10-27)
- GPT-6 Luna (medium) (checked 2026-10-27)
- OpenRouter: GPT-6 Luna (checked 2026-10-21)