ModelFoldgpt-6-luna
GPT-6 Luna and GPT-6 Sol are OpenAI GPT-6 models trained with methods similar to GPT-6 Astra, both available as API models on ModelFold.
Pricing: Input 7.5 credits / 1M tokens (≈ $0.04), Output 37.5 credits / 1M tokens (≈ $0.19).
How can I help you today?
Explore more Chat models
More AI models from OpenAI
Latest and popular AI models
GPT-6 Luna API and GPT-6 Sol API on ModelFold
GPT-6 Luna and GPT-6 Sol are OpenAI GPT-6 models trained with methods similar to GPT-6 Astra, which OpenAI describes as bringing Astra's advances to faster, more affordable models. GPT-6 Sol has since been upgraded to GPT-6.1 Sol. On ModelFold, both GPT-6 Luna and GPT-6 Sol are available as API models.
GPT-6 Luna and GPT-6 Sol API Parameters on ModelFold
GPT-6 Luna and GPT-6 Sol take the same parameters on ModelFold; only the model name changes.
| Parameter | Value |
|---|---|
| Models | gpt-6-luna, gpt-6-sol |
| Endpoint | POST https://ai.modelfold.online/v1/chat/completions (OpenAI-compatible) |
| Context window | 1,050,000 tokens |
| Maximum input | 922,000 tokens |
| Maximum output | 128,000 tokens |
| Input types | Text messages |
| Reasoning effort | low, medium, high, xhigh or max (adjustable in the Playground) |
| Tools | Web search (available in the Playground) |
| Streaming | Not streamed; the API returns one JSON response with usage and credits charged |
| Pricing | Shown in the pricing card above; switch the model type to see each price |
GPT-6 Luna vs GPT-6 Sol: When Luna Is Enough
OpenAI calls GPT-6 Luna its most efficient model for focused, high-volume tasks, while GPT-6 Sol is built to take on difficult work tasks. On OpenAI's DeepSWE v1.1 coding benchmark at maximum reasoning effort, GPT-6 Sol scores 68.8% and GPT-6 Luna 66.6%, and LMArena's text leaderboard gives GPT-6 Sol 1456 and GPT-6 Luna 1443 (as of October 8, 2026). On ModelFold, Luna costs less than Sol. A practical default is Luna for high-volume, focused requests and Sol for harder work tasks; GPT-6 Sol has since been upgraded to GPT-6.1 Sol, and OpenAI points to GPT-6 Astra for the most demanding work.
| GPT-6 Luna | GPT-6 Sol | |
|---|---|---|
| How OpenAI positions it | Its most efficient model for focused, high-volume tasks | Built to take on difficult work tasks |
| DeepSWE v1.1, max reasoning effort (OpenAI-reported) | 66.6% | 68.8% |
| LMArena text score (Oct 8, 2026) | 1443 | 1456 |
| Artificial Analysis Intelligence Index (Oct 2026) | 38 | Not listed |
| Newer version | — | Upgraded to GPT-6.1 Sol |
| Available on ModelFold | Yes | Yes |
What OpenAI Reports for GPT-6 Luna and GPT-6 Sol
OpenAI trained GPT-6 Sol and Luna with methods similar to GPT-6 Astra and reports these improvements over their GPT-5.6 predecessors.
Business Workflows Across Apps
On AutomationBench, a test of business workflows across apps, GPT-6 Luna at high reasoning effort scores 5.4 points above its predecessor.
Fewer Factual Mistakes
On OpenAI's factuality evaluation, built from real conversations where users flagged mistakes, GPT-6 Sol makes about half as many mistakes as its predecessor, and GPT-6 Luna also improves.
Code Ready to Merge
On FrontierCode, which checks whether coding agents produce changes ready to merge into real codebases, GPT-6 Sol improves substantially over GPT-5.6 Sol.
Clearer, Shorter Replies
OpenAI brought GPT-6 Astra's communication style to Sol and Luna: more clarity, less jargon, fewer low-value details and slightly shorter answers.
Typical Uses for GPT-6 Luna and GPT-6 Sol
These are the kinds of work each model fits, based on how OpenAI positions them.
Focused Requests at Volume
Well-defined requests that run many times a day, where Luna's efficiency matters most.
Coding in Real Codebases
Writing and fixing code in existing repositories, with Sol for the harder changes.
Business Workflows Across Apps
Multi-step tasks that move information between apps.
Professional Work With Agents
Complex professional workflows run by agents, where Sol takes on the difficult steps.
How to Use the GPT-6 Luna and GPT-6 Sol APIs on ModelFold
- 1
Step 1. Get Your API Key
Sign up on ModelFold, open the API Key Management page and create a key. Every request sends it in the Authorization header.
- 2
Step 2. Test Your Prompt in the Playground
You can try this model in the playground on this page without writing code. Switch between GPT-6 Luna and GPT-6 Sol to compare answers on the same prompt.
- ✓
Step 3. Send a Request
Send a POST request to https://ai.modelfold.online/v1/chat/completions with model set to gpt-6-luna or gpt-6-sol and an OpenAI-style messages array, authenticated with your API key.
Tips Before You Ship
Handle Standard HTTP Errors
ModelFold returns standard HTTP status codes — for example 401 for an invalid API key and 402 for insufficient credits — with an error code and message in the JSON body. Failed upstream calls are refunded automatically.
Try Web Search in the Playground
Web search and reasoning effort for these models can be switched on in the Playground on this page, so you can see how they change the answers before you integrate.
Why Use GPT-6 Luna and GPT-6 Sol on ModelFold
Same Key Across the ModelFold Market
All models in the ModelFold market use the same authentication method: an Authorization: Bearer YOUR_API_KEY header with the key from your ModelFold API Key Management page.
Free Credits to Start
New ModelFold users receive 80 free credits for testing. Your account has one credit balance that every model draws from, and you can see it, together with every charge, in your wallet.
Nothing to Host or Install
ModelFold provides this model as an API with a playground; there is no app to download or install. There are no GPUs or model weights to manage.
FAQs About GPT-6 Sol API and GPT-6 Luna API
How much does the GPT-6 Luna API cost?⌄
Pricing is shown in the pricing card above. Switch the model type between GPT-6 Luna and GPT-6 Sol to see each model's price.
Is GPT-6 Luna free?⌄
Not on ModelFold: each request uses credits, as shown in the pricing card above. New ModelFold users receive 80 free credits for testing.
What is the difference between GPT-6 Luna and GPT-6 Sol?⌄
OpenAI positions Luna for focused, high-volume tasks and Sol for difficult work tasks. Sol scores higher on OpenAI's DeepSWE results and on LMArena, and Luna costs less on ModelFold; the comparison table above has the scores.
Is there a GPT-6.1 Luna?⌄
As of October 2026, OpenAI's GPT-6.1 release page covers only GPT-6.1 Sol, and the Luna model available on ModelFold is GPT-6 Luna (gpt-6-luna).
What is GPT-6 Luna?⌄
GPT-6 Luna is the GPT-6 model OpenAI describes as its most efficient, built for focused, high-volume tasks. On ModelFold it is the API model gpt-6-luna; its parameters, results and uses are covered above.
What is the GPT-6 Luna context window?⌄
OpenAI lists a 1,050,000-token context window, with up to 922,000 input tokens and 128,000 output tokens. The parameter table above has the other limits.
How do I use the GPT-6 Luna API?⌄
Create a ModelFold API key, then send a request to https://ai.modelfold.online/v1/chat/completions with model set to gpt-6-luna. The steps above show the full flow.
Is GPT-6 Sol still available?⌄
Yes. On ModelFold you can still call gpt-6-sol, although OpenAI has since upgraded it to GPT-6.1 Sol.
| Input | 7.5 credits 1M tokens≈ $0.04 |
| Output | 37.5 credits 1M tokens≈ $0.19 |
Billed per token: input and output are priced separately, and thinking tokens count as output. The Playground charges exactly the same way.
Read API docs →curl https://ai.modelfold.online/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6-luna","messages":[{"role":"user","content":"Hello"}]}'