OpenAI: GPT-6 Luna
gpt-6-luna- Input / Output-70%
- $0.10 / $0.50$0.03 / $0.15
- Context
- 1.05M
- Released
- Sep 23, 2026
- Max output
- 128K
- Modalities
- VisionChat
- Capabilities
- Tool usePrompt CacheReasoning
About GPT-6 Luna
GPT-6 Luna is OpenAI's most efficient GPT-6 model, tuned for focused, high-volume tasks where speed and cost decide. It carries over improvements from GPT-6 Astra in factuality, coding, and alignment, and it improves on GPT-5.6 Luna. It accepts text and images, supports tools and JSON output, and lets you turn reasoning off for simple calls.
Where it works well
- OpenAI ranks it first on its Codexometer benchmark, a ranking that puts cost first, across three coding tasks.
- Supports a reasoning setting of none, so simple calls skip thinking entirely.
- Inherits Astra-era gains in alignment and factuality over the earlier GPT-5.6 Luna.
- Handles images, tool calls, and schema-checked JSON in the same request.
When to choose another model
- GPT-6 Sol and Astra are stronger on difficult multi-file engineering and long agent runs.
- Focused tasks are its design target; open-ended research or deep analysis will show the gap.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses APIPOST/v1/responsesAPI format:curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "gpt-6-luna", "input": "Hello!" }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Input tokens <= 272K
per 1M tokens- Official price
- Input $0.10 / Output $0.50 / Cache read $0.01 / Cache write $0.125
- Verified price
- Input $0.03 / Output $0.15 / Cache read $0.003 / Cache write $0.0375
- Discount
- -70%
Input tokens 272K-1.05M
per 1M tokens- Official price
- Input $0.20 / Output $0.75 / Cache read $0.02 / Cache write $0.25
- Verified price
- Input $0.06 / Output $0.225 / Cache read $0.006 / Cache write $0.075
- Discount
- -70%
Cache read
- Official price
- $0.01
- Verified price
- $0.003
- Discount
- -70%
Cache write
- Official price
- $0.125
- Verified price
- $0.0375
- Discount
- -70%
Charged per call, only when the model uses the tool.
Web search
- Official price
- $0.01/search
- Verified price
- $0.003/search
- Discount
- -70%
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Input tokens <= 272K | Input $0.10 / Output $0.50 / Cache read $0.01 / Cache write $0.125 | Input $0.03 / Output $0.15 / Cache read $0.003 / Cache write $0.0375 | -70% |
| Input tokens 272K-1.05M | Input $0.20 / Output $0.75 / Cache read $0.02 / Cache write $0.25 | Input $0.06 / Output $0.225 / Cache read $0.006 / Cache write $0.075 | -70% |
| Prompt cache pricing | |||
| Cache read | $0.01 | $0.003 | -70% |
| Cache write | $0.125 | $0.0375 | -70% |
| Tool feesCharged per call, only when the model uses the tool. | |||
| Web search | $0.01/search | $0.003/search | -70% |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
- 30-day success rate
- 91.1%
- 7-day median latency
- 14.0sn=2,870
- 7-day P95 latency
- 82.9sn=2,870
- 30-day requests
- 5K+
- Last active
- 32 minutes ago
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open GPT-6 Luna in Console with a prompt ready to edit or send.
Help me try gpt-6-luna with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Best for- Code
- Reasoning
- Vision
High-volume extraction
Pull fields from thousands of documents or messages per hour and return validated JSON.
Fast chat features
Run autocomplete, rewriting, and short answers inside a product where response time is visible to users.
Routing and moderation
Decide which team or model should handle an input, flagging policy issues before a larger model sees it.
Cheap coding chores
Generate boilerplate, rename symbols, and write small tests where the change is well specified.
Prompt examples
Extract company name, contract value, and renewal date from the paragraph below and answer only with JSON.
Is this user message a refund request, a bug report, or something else? Reply with one word.
Rewrite this function to use early returns without changing behaviour.
This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.
FAQ
What is GPT-6 Luna?
GPT-6 Luna is the efficiency-focused model in OpenAI's GPT-6 generation, designed for focused, high-volume tasks. It brings advances from Astra to a faster, lower-cost tier.
How does GPT-6 Luna differ from GPT-5.6 Luna?
It builds on GPT-6 Astra's methods, with OpenAI reporting better alignment than the GPT-5.6 counterparts. It is also the current recommendation for cost-efficient work, while GPT-5.6 is marked legacy.
Can I turn reasoning off on GPT-6 Luna?
Yes. OpenAI's guidance lists none among its reasoning effort settings, unlike Astra and GPT-6.1 Sol. Use it for latency-critical turns and raise the effort only when answers need checking.
When should I choose Luna over GPT-6 Sol?
Choose Luna for narrow, repeated work where throughput matters. Move to Sol when the task needs multi-step planning, large code changes, or fewer mistakes on ambiguous requests.
Does GPT-6 Luna read images and call tools?
Yes, it accepts images with text, calls functions, and can produce structured JSON in the same request. Output is text only, never images or audio.
How much does GPT-6 Luna cost?
On TokenLab, GPT-6 Luna costs Input $0.03 / Output $0.15 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the context window and output limit of GPT-6 Luna?
GPT-6 Luna accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens in one response.
Which endpoint should GPT-6 Luna use?
Use https://api.tokenlab.sh/v1/responses for GPT-6 Luna. The request example below shows the matching code shape.
Which operations does GPT-6 Luna support?
GPT-6 Luna supports Text to text. Select an operation above to see its endpoint and request example.
Compare GPT-6 Luna
Sources
Reviewed Oct 2, 2026
