Skip to content
Pricing
OpenAI

GPT-6 Astra API

OpenAI positions GPT-6 Astra for demanding reasoning, coding, research and professional document creation.

MODALITIES
TextText
Available
INPUT / OUTPUT90% OFF
$1/ 1M
/
$5/ 1M
USD per million tokens
CACHED INPUT
$0.1/ 1M
Platform price · USD
CONTEXT WINDOW
1,050,000tokens
Max output: 128,000 tokens

API Usage Examples

API documentation ↗
POSTGet API Key ↗
curl 'https://newrouters.com/v1/chat/completions' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  --data '{
  "model": "gpt-6-astra",
  "messages": [
    {
      "role": "user",
      "content": "Explain how an HTTP request works in three concise steps."
    }
  ],
  "max_completion_tokens": 1024,
  "stream": false
}'

Set MODEL_API_KEY in your server environment. Requests use this model’s native API and your account pricing.

Docs: authentication and keys · Error handling

GPT-6 Astra pricing

Estimate one request, then choose a budget for your workflow.

UsageQuantityRateCost
tokens$1/ 1M$0.001
tokens$0.1/ 1M$0
tokens$5/ 1M$0.0025
tokens$5/ 1M$0
Cost per request$0.0035

Public USD estimate. Your account rate and final recorded usage determine the actual charge.

Model pricing details
SpecificationOur priceOfficial reference
Input · input ≤ 272,000$1 / 1M tokens$10 About 90% less than official
Input · input > 272,000$2 / 1M tokens$20 About 90% less than official
Cached input · input ≤ 272,000$0.1 / 1M tokens$1 About 90% less than official
Cached input · input > 272,000$0.2 / 1M tokens$2 About 90% less than official
Output · input ≤ 272,000$5 / 1M tokens$50 About 90% less than official
Output · input > 272,000$7.5 / 1M tokens$75 About 90% less than official
Reasoning · input ≤ 272,000$5 / 1M tokens$50 About 90% less than official
Reasoning · input > 272,000$7.5 / 1M tokens$75 About 90% less than official

GPT-6 Astra API · Examples

Original prompts adapted to documented capabilities; these are not vendor-generated outputs.

Official source ↗ · 2026-10-14

EXAMPLE PROMPT

Compare the evidence, assumptions and risks in these three proposals. Flag unverified conclusions and list the next checks. Proposals: [paste material]

USER MESSAGE
01

Multi-step research

Compare evidence across documents while keeping assumptions and unresolved checks explicit.

EXAMPLE PROMPT

Review concurrency and recovery in this order system. Identify consistency risks, reproduction conditions and minimal fixes. Design: [paste design]

USER MESSAGE
02

Architecture review

Focus on concurrency and recovery boundaries, reproducible problems and minimal fixes.

What Is GPT-6 Astra?

OpenAI positions GPT-6 Astra for demanding reasoning, coding, research and professional document creation.

Official model information ↗ · 2026-10-14

GPT-6 Astra Platform specifications

SpecificationGPT-6 Astra
Model IDgpt-6-astra
ProviderOpenAI
API/v1/chat/completions · /v1/responses
Context window1,050,000 tokens
Maximum output128,000 tokens
Declared capabilitiesTools · Streaming · Reasoning · Structured output
Protocol & capability details

Protocol & capabilities

openai · gpt-6-astra

Context limit
1050000
Maximum output
128000

tools · stream · reasoning · structured_output

Compare GPT-6 Astra with related models

SpecificationGPT-6 Astragpt-5.4GPT-5.5
ProviderOpenAIOpenAIOpenAI
Input → outputTextTextTextTextTextText
Selection basisCurrent modelSame openai protocol · Same billing unitsSame openai protocol · Same billing units
Context / max output1,050,000 / 128,0001,050,000 / 128,0001,050,000 / 128,000
Starting price$1 / 1M tokens$0.5 / 1M tokens$1 / 1M tokens

Choose by the input types, output settings and billing unit your workflow needs. Try the same prompt across models to compare results for your own use case.

Integrate GPT-6 Astra into your app

Keep the native request format and point your application to the platform API. Prepare a key with model access, then review status and charges in your usage records.

View API examples

GPT-6 Astra API · Common Questions

Everything you need to know about API access, pricing and model capabilities.

How is GPT-6 Astra billed?

Charges depend on the recorded token usage and your account rates. Input, output and supported cache or reasoning categories are listed separately in the pricing table. The calculator uses public USD prices; the final usage receipt determines the charge.

How do I get an API key?

Choose “Get API access” to open the integration guide. Sign in to your NewRouters account, prepare a key with access to this model and copy an API example.

Which API endpoints can I use?

Supported endpoints: /v1/chat/completions、/v1/responses. Choose an endpoint in the API examples to see its native request format.

Does the model support streaming?

The current model route declares streaming support. Use the native endpoint’s streaming option and consume its events. Usage already completed may still be billed if the connection is interrupted.

Can I use tools or structured output?

Tools: supported. Structured output: supported. Request fields follow the selected native endpoint.

Where can I check usage and charges?

Keep the request ID and open your account’s LLM usage records to inspect request status, token counts and charges. Prompt and answer content are not a conversation history in this view.

Explore LLM Use Cases

All LLM models ↗

Integration topics / Documentation

All documentation ↗