Built for Repeated Tasks
Use Luna for focused work that runs many times: classify requests, extract fields, summarize selected material or draft short answers. Measure accuracy on your own examples before increasing volume.
GPT 6 Luna
Access GPT-6 Luna on GPTProto for high-volume chat, classification and structured extraction. Run focused tasks with adjustable reasoning and a 1.05M-token context window. Check the live rate and test the model using your GPTProto API key.
API Usage Examples
curl --request POST "https://gptproto.com/v1/chat/completions" \
--header "Authorization: Bearer $GPTPROTO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "gpt-6-luna",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'GPT 6 Luna pricing
Chat, coding agents & document work. Priced per 1M tokens — input, cached input and output are billed separately. GPTProto is 20% below official rates.
Your usage
OpenAI · ≈ 148M tokens/mo (48M cached)
OpenRouter
List + 5.5% credit fee
$14.4324
per month
Input (non-cached)$3.376
Cache read$0.5064
Output$10.5499
OpenAI
Direct from OpenAI (list price)
$13.68
per month
Input (non-cached)$3.2
Cache read$0.48
Output$10
BEST VALUE
GPTProto
20% off official
$10.9439
per month
After discount$10.9439
Effective$10.9439
Monthly cost by source
OpenRouter
$14.4324
OpenAI
$13.68
GPTProto
$10.9439
Save $2.74 / month
on GPTProto vs OpenAI (−20%)
Annual savings ≈ $32.83 · pay as you go
OpenRouter costs include its ~5.5% credit purchase fee. GPTProto applies a per-model discount (10–30% off) and your bonus credits are also spent at discounted rates — savings compound. Estimates assume a 60% cache hit rate.
Related Models
All Models
| Model | Input → Output | ||||
|---|---|---|---|---|---|
| 1.05M | $0.08 / $0.40 per 1M | $0.10 / $0.008 per 1M | Input: TextInput: ImageInput: Document Output: Text | |
| 1.05M | $1.60 / $8.00 per 1M | $2.00 / $0.16 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| — | $0.03 / — per 1M | — | Input: Text Output: Text | ||
| 500K | $1.20 / $3.60 per 1M | — / $0.30 per 1M | Input: TextInput: Image Output: Text | ||
| — | — | $0.30 / $1.20 per 1M | — / $0.006 per 1M | Input: TextInput: Image Output: Text | |
| 1M | $0.79 / $2.38 per 1M | — / $0.04 per 1M | Input: Text Output: Text | ||
| 1.05M | $8.00 / $40.00 per 1M | $10.00 / $0.80 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.90 / $4.50 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text | ||
| 1M | $9.00 / $45.00 per 1M | $11.25 / $0.23 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1M | $1.80 / $5.40 per 1M | $2.25 / $0.23 per 1M | Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text | ||
| — | 1.31M | $0.15 / $0.50 per 1M | — / $0.03 per 1M | Input: TextInput: ImageInput: VideoInput: Document Output: Text | |
| — | 1.05M | $0.30 / $1.20 per 1M | — / $0.006 per 1M | Input: TextInput: Image Output: Text | |
| 1.31M | $1.26 / $3.96 per 1M | — / $0.23 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.90 / $4.50 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 500K | $1.20 / $3.60 per 1M | — / $0.30 per 1M | Input: TextInput: Image Output: Text | ||
| 1M | $1.80 / $5.40 per 1M | $2.25 / $0.23 per 1M | Input: TextInput: ImageInput: VideoInput: Document Output: Text | ||
| 1M | $4.50 / $22.50 per 1M | $5.63 / $0.45 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.90 / $4.50 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $2.70 / $13.50 per 1M | $2.70 / $0.27 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.16 / $0.96 per 1M | $0.20 / $0.02 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $1.60 / $9.60 per 1M | $2.00 / $0.16 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $3.20 / $16.00 per 1M | $4.00 / $0.32 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 500K | $1.20 / $3.60 per 1M | $0.30 / $0.30 per 1M | Input: TextInput: Image Output: Text | ||
| 1M | $1.80 / $9.00 per 1M | $2.25 / $0.18 per 1M | Input: TextInput: Document Output: Text | ||
| 1.05M | $0.48 / $0.96 per 1M | $0.10 / $0.10 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $1.26 / $3.96 per 1M | $0.23 / $0.23 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| — | $1.00 / $8.00 per 1M | $0.10 / $0.10 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1M | $0.36 / $1.44 per 1M | $0.07 / $0.07 per 1M | Input: TextInput: Document Output: Text | ||
| — | 1.05M | $0.30 / $1.20 per 1M | — / $0.006 per 1M | Input: Text Output: Text | |
| 262K | $0.85 / $3.60 per 1M | $0.14 / $0.14 per 1M | Input: TextInput: Document Output: Text | ||
| 205K | $0.24 / $0.96 per 1M | $0.30 / $0.02 per 1M | Input: TextInput: Document Output: Text | ||
| 262K | $0.54 / $2.70 per 1M | $0.09 / $0.09 per 1M | Input: TextInput: Document Output: Text | ||
| 262K | $0.10 / $0.97 per 1M | — | Input: TextInput: Image Output: Text | ||
| 262K | $0.10 / $0.97 per 1M | — | Input: TextInput: Image Output: Text | ||
| 262K | $0.02 / $0.18 per 1M | — | Input: TextInput: Image Output: Text |
GPT-6 Luna API
Build repeatable application workflows with Luna, from labeling support messages to extracting product details and handling small agent steps. Test accuracy on real inputs, then compare latency, retries and total cost before moving a high-volume workload to this tier.
1.05M-Token Context
The model accepts up to 1,050,000 tokens of context and supports up to 128,000 output tokens. Retrieve only useful material for each request; a large window is a capacity limit, not a recommended prompt length.
Adjustable Reasoning
Choose none, low, medium (default), high, xhigh or max upstream. Start with a small task set and compare completed results, latency and token use at different effort levels.
Structured Text Results
OpenAI documents structured outputs, streaming and function calling for Luna. Use these capabilities for extraction or application workflows where supported by the GPTProto route; validate the response before writing to your database.
What Is the GPT-6 Luna API?
GPT-6 Luna is OpenAI's efficiency-focused model for high-volume, repeatable work. Its published API model ID is gpt-6-luna. The model accepts text and images as input and produces text; it is a hosted model, not an open-source download. OpenAI lists streaming, structured outputs and function calling among its upstream capabilities.
Luna is a first candidate for bounded requests: ticket labels, answers grounded in retrieved text, or product attributes. For ambiguous plans, cross-file edits or longer agent runs, test GPT-6 Sol too. Select by completed-task cost, not token rate alone.
| Published specification | GPT-6 Luna |
|---|---|
| OpenAI model ID | gpt-6-luna |
| Context window | 1,050,000 tokens |
| Maximum output | 128,000 tokens |
| Input / output | Text and image / text |
| Reasoning effort | none, low, medium (default), high, xhigh, max |
| Structured outputs / streaming | Supported upstream |
| Fine-tuning | Not supported |
The long context window does not guarantee success on a long-horizon task. Break work into checkable stages, save state outside the prompt and count retries when comparing costs.
GPT-6 Luna API Applications
High-volume chat and classification. Route narrowly defined messages to Luna. Provide category definitions or a short knowledge excerpt, then test accuracy and response time on real inputs.
Structured extraction. Extract fields from product descriptions or customer messages. Request a schema, validate fields in your application and review uncertain cases.
Bounded coding and agent steps. Explain a function, draft a targeted test or summarize a tool result. Your application runs tools and tests; escalate difficult changes or repeated failures to Sol.
GPT-6 Luna vs GPT-5.6 Luna and GPT-6 Sol
The table shows OpenAI's standard upstream short-context text rates, not GPTProto prices. Consult this page's live pricing panel for the rate billed by GPTProto. All three models publish a 1,050,000-token context window and a 128,000-token maximum output.
| Model | OpenAI input / output per 1M tokens | Good first test |
|---|---|---|
| GPT-5.6 Luna | $0.20 / $1.20 | Existing workload baseline; retain it until migration tests pass. |
| GPT-6 Luna | $0.10 / $0.50 | Repeatable tasks where cost and response time matter. |
| GPT-6 Sol | $2.00 / $10.00 | Tasks needing stronger reasoning or longer agent loops. |
OpenAI's GPT-6 Luna list rates are 50% lower for input and about 58% lower for output than GPT-5.6 Luna's current rates. This compares token prices, not quality. Above 272,000 input tokens, higher upstream long-context rates apply to the entire request; check GPTProto's billing rules for large jobs.
Moving a Repeated Workflow to Luna
Run a representative task sample on GPT-5.6 Luna, GPT-6 Luna and Sol. Compare accepted answers, retries, latency and total charge. Set a rule for escalation. For reasoning-enabled tool calls, check the endpoint: OpenAI recommends Responses, while Chat Completions permits function calling only with reasoning_effort: "none". Verify GPTProto's route in the Quick Start.
FAQ
What does the GPT-6 Luna API cost on GPTProto?
Check the live Pricing panel for GPTProto's rates. OpenAI's standard upstream short-context list rates are $0.10 input and $0.50 output per million tokens; these are not GPTProto billing rates.
How do I get a GPT-6 Luna API key and test the model?
Create a GPTProto key in your dashboard, then choose Try this model for its model ID and Quick Start. The key accesses other listed models; keep it on your server.
GPT-6 Luna vs GPT-6 Sol: which should I use for coding agents?
Start Luna with short, verifiable steps. Trial Sol for harder planning or cross-file changes. Use identical acceptance tests and compare cost per completed task.
Is GPT-6 Luna better than GPT-5.6 Luna?
Upstream token prices are lower, but that does not prove higher quality. Test both models with the same tasks and reasoning settings. Keep the previous route until success and latency targets are met.
Can GPT-6 Luna call tools with reasoning enabled?
OpenAI documents tool calling through Responses; Chat Completions allows it only with reasoning_effort: "none". Confirm GPTProto's supported route before relying on reasoning-enabled tool calls.
Is GPT-6 Luna an open-source model or an image generator?
No. It is a hosted API model with image input and text output, not downloadable weights or direct image output. If your app needs generated pictures, select a dedicated image model from the OpenAI model collection.
How does GPT-6 Luna compare with Gemini 4 or GLM-5.3 Flash?
Test exact versions with the same prompts, time limits and acceptance checks. Tool support and provider billing may differ; a general winner claim needs shared workload results.
Related Articles
Guides, comparisons, and updates related to this model.
All Articles
6 Best LLM API Providers in 2026: Multi-Model Platforms Compared
Compare the six best LLM API providers in 2026 by model access, pricing structure, speed, compatibility, governance, and developer experience.
What Is GPT-6 Sol? Release Status, Pricing, Tests, and What We Know
What is GPT-6 Sol? Check its release status, reported features, pricing, coding tests, and how it compares with GPT-6 Astra and GPT-5.6 Sol.
6 Best Affordable LLM APIs for AI Agents in 2026
Compare 6 affordable LLM APIs for AI agents by pricing, tool calling, speed, context, and cost per successful task to choose the right model in 2026.
Qwen3.8-Flash-Next vs GLM-5.3 Flash: Which Is Better for Coding, Agents, and Price?
Qwen3.8-Flash-Next vs GLM-5.3 Flash compared for coding, agents, frontend work, speed, pricing, context, licenses, and production use.