How much does the GPT-6 Astra API cost?

On FastMetal, GPT-6 Astra is billed per token: $10.55 per 1M input tokens and $52.75 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-6 Astra with the OpenAI SDK?

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

What is the context window of GPT-6 Astra?

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

What do I need to try GPT-6 Astra?

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-6-astra

GPT-6 Astra

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

9/4/2026

1,050,000 tokens

Input: $10.55/M

Output: $52.75/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
Turning thinking off: Not possible (always thinks)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Unknown — not declared

"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)2.9s

Throughput (p50)111 tokens/s

Measured through FastMetal's own gateway over the last 30 days (642 first-response samples).

Throughput is sampled once a day: the median of 24 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-6-astra",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How GPT-6 Astra 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.

“strawberry” is spelled **s-t-r-a-w-b-e-r-r-y**. The letter **r** appears in positions **3, 8, and 9**, so there are **3 r’s**.

3.8s response85 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…

The error means **`users` is `undefined` when React renders `UserList`**, so calling `users.map(...)` fails. This commonly happens when the parent doesn’t pass the prop or when data hasn’t finished loading. ### 1. Default `users` to an empty array If an absent prop should mean “no users,” use a default value: ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => ( <li key={user.id}>{user.name}</li> ))} </ul> ); } ``` This handles a missing or `undefined` prop, but **not `null` or other non-array values**. ### 2. Check where the prop comes from Make sure the parent passes an array. For data loaded asynchronously, initialize state to…

6.7s response380 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):…

The function is compact, but its biggest issue is that **all failures silently become `[]`**, making an unavailable API indistinguishable from a successful response with no active items. ### Suggested improvements - **Move imports to module scope** for clarity and conventional organization. - **Avoid bare `except:`.** It catches everything, including `KeyboardInterrupt`, and hides bugs such as missing dictionary keys. - **Retry only transient failures**, such as connection errors, timeouts, rate limiting, and selected server errors. Retrying a `401` or `404` usually won’t help. - **Don’t sleep after the final failed attempt.** Use exponential backoff rather than a fixed delay. - **Use desc…

19.2s response965 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the GPT-6 Astra API cost?: On FastMetal, GPT-6 Astra is billed per token: $10.55 per 1M input tokens and $52.75 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-6 Astra with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-6-astra" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of GPT-6 Astra?: 1,050,000 tokens, shared between the prompt and the response.
What do I need to try GPT-6 Astra?: 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.