How much does the GPT-6 Luna Pro API cost?

On FastMetal, GPT-6 Luna Pro is billed per token in yen: ¥17.87 per 1M input tokens and ¥89.35 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call GPT-6 Luna Pro with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-6-luna-pro" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of GPT-6 Luna Pro?

1,050,000 tokens, shared between the prompt and the response.

What do I need to try GPT-6 Luna Pro?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

gpt-6-luna-pro

GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

9/22/2026

1,050,000 tokens

Input: ¥17.87/M

Output: ¥89.35/M

Try in Chat Get API Key

Specifications

Modalities

Input

file

image

text

Output

text

Supported Parameters

include_reasoning

max_completion_tokens

max_tokens

reasoning

reasoning_effort

response_format

seed

structured_outputs

tool_choice

tools

Max Output Tokens

128,000

Reasoning Configuration

Default: Thinking on (effort: medium)
Selectable effort levels: max
xhigh
high
medium
low
none
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-6-luna-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How GPT-6 Luna Pro actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

In “strawberry,” the letters are s-t-**r**-a-w-b-e-**r**-**r**-y. There are **3** “r”s.

4.7s response279 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

`users` is `undefined` when `UserList` renders, so calling `users.map(...)` throws. This usually means the parent hasn’t passed a `users` prop yet—for example, the data is still loading—or passed a value that isn’t an array. Make sure the parent supplies an array: ```jsx <UserList users={users} /> ``` If the data may not be ready, give the component a fallback: ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => ( <li key={user.id}>{user.name}</li> ))} </ul> ); } ``` You can also handle loading explicitly: ```jsx function UserList({ users }) { if (!Array.isArray(users)) { return <p>Loading users…</p>; } return ( <ul…

6.8s response789 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

### Main issues - `except:` catches everything, including programming errors and `KeyboardInterrupt`. Catch only errors you expect to retry. - Failures are silently turned into `[]`, making “no active records” indistinguishable from a failed request. - Non-200 responses are retried indiscriminately; most 4xx responses won’t improve on retry. - A fixed two-second delay can make retries slow. Exponential backoff is a common alternative. - `item["active"] == True` is less precise than `item.get("active") is True`. - Imports belong at module level. Type hints and a clearer parameter name also help. - `range(retries)` makes `retries` the total number of attempts, not the number of attempts *afte…

42.4s response6417 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the GPT-6 Luna Pro API cost?: On FastMetal, GPT-6 Luna Pro is billed per token in yen: ¥17.87 per 1M input tokens and ¥89.35 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call GPT-6 Luna Pro with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-6-luna-pro" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of GPT-6 Luna Pro?: 1,050,000 tokens, shared between the prompt and the response.
What do I need to try GPT-6 Luna Pro?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try GPT-6 Luna Pro right now

GPT-6 Luna Pro is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

More from OpenAI