Skip to content
All models
OpenAIAvailable

GPT-6 Astra

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.

Try in ewpireopenai/gpt-6-astra

Opens in the ewpire workspace. Creating an account is free; runs are paid from your credits.

GPT-6 Astra in plain words

GPT-6 Astra is a text model from OpenAI. It takes files, images, and text as input and returns text. Its context window is 1,050,000 tokens. It costs 9.7 credits per 1M input tokens and 48.5 credits per 1M output tokens. A request with 272,000 or more input tokens is charged, as a whole, at 19.4 credits per 1M input tokens and 72.75 credits per 1M output tokens.

It is good at reasoning through multi-step problems, reading attached files, and calling tools. It reads images as well as text. It is one of the slower models in the catalog. A context window of 1,050,000 tokens holds about 4,200,000 characters of English text, at 4 characters a token.

For example, a question of 2,000 tokens (about 8,000 characters) with an answer of 1,000 tokens (about 4,000 characters) costs 0.0679 credits. The exact charge follows the usage the model reports for your request.

Details

Made by
OpenAI
Good at
ReasoningVisionFilesTool use
Reads
Files, Images, Text
Produces
Text
Context window
1,050,000 tokens
Speed
Slower

Price

Input, per 1M tokens
9.7 credits
Output, per 1M tokens
48.5 credits

Requests with 272,000 or more input tokens

Input, per 1M tokens
19.4 credits
Output, per 1M tokens
72.75 credits

The whole request is charged at these rates, not only the tokens past that size.

Charged per request from your credit balance. No subscription. See pricing

Use it through the API

Call it with the OpenAI SDK or plain HTTP: set the base URL to ewpire and pass this model id. Read the docs

curl https://ewpire.com/api/v1/chat/completions \
  -H "Authorization: Bearer $EWPIRE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-6-astra","messages":[{"role":"user","content":"Hello!"}]}'

The docs show how to list the models the API serves, with their capabilities and prices. Models in the docs

Similar models