How much does the GPT-5.6 Luna API cost?

On FastMetal, GPT-5.6 Luna is billed per token: $0.211 per 1M input tokens and $1.27 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call GPT-5.6 Luna with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-5.6-luna" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of GPT-5.6 Luna?

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

What do I need to try GPT-5.6 Luna?

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

OpenAI

gpt-5.6-luna

GPT-5.6 Luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

7/9/2026

1,050,000 tokens

Input: $0.211/M

Output: $1.27/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.

Measured performance

Time to first response (p50)974ms

Throughput (p50)258 tokens/s

Measured through FastMetal's own gateway over the last 30 days (653 first-response samples).

Throughput is sampled once a day: the median of 26 observations over the last 30 days.

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How GPT-5.6 Luna 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.

The word **“strawberry”** is spelled: **s – t – r – a – w – b – e – r – r – y** The letter **“r”** appears at positions **3, 8, and 9**. **Answer: 3**

3.0s response120 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 `.map()` on it fails. `.map()` only exists on arrays. Common causes include: - The parent does not pass a `users` prop. - The prop name differs, such as `userList` instead of `users`. - Users are loaded asynchronously and are initially undefined. - The API response has a different shape, such as `{ data: [...] }`. ### Provide a default value ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => ( <li key={user.id}>{user.name}</li> ))} </ul> ); } ``` The parent should pass an array: ```jsx <UserList users={users} /> ``` If the list comes from state, initialize it as an empty…

4.8s response507 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 - Imports should be at module level, not inside the function. - A bare `except:` catches everything, including programming errors and `KeyboardInterrupt`. - The function sleeps even after the final failed attempt. - It retries all HTTP statuses, including permanent errors such as `404`. - `status_code == 200` excludes other successful `2xx` responses. - `if item["active"] == True` should generally be `if item.get("active") is True`. - A `requests.Session` can reuse connections and improve performance. - Returning `[]` for every failure makes it impossible to distinguish “no active items” from “request failed.” - Retries should generally use backoff rather than a fixed delay.…

23.3s response1978 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the GPT-5.6 Luna API cost?: On FastMetal, GPT-5.6 Luna is billed per token: $0.211 per 1M input tokens and $1.27 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call GPT-5.6 Luna with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-5.6-luna" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of GPT-5.6 Luna?: 1,050,000 tokens, shared between the prompt and the response.
What do I need to try GPT-5.6 Luna?: 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.