OpenAI
GPT-6 Astra
OpenAI frontier flagship with Critical-tier autonomous cybersecurity, extreme token efficiency, and 72.6% on OSWorld 2.0.
Intelligence
86.2 #4
AAQI 61.0
Output speed
82 t/s
TTFT 143 ms · ITL 12.2 ms/tok
Blended price (3:1)
$20 /1M
In $10/M · Out $50/M
Context
1.1M
≈ 2,750 A4 pages · max out 131072
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
GPT-6 Astra
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.
API deployment
Compare hosts & latency
Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Groq
Cerebras
Together AI
DeepInfra
Fireworks AI
AWS Bedrock
Azure AIScores by Source
Category Scores
Benchmark Results
Model Details
Release date
Sep 3, 2026
Parameters
Not disclosed
License
Proprietary
Context Window
1,100,000 tokens
Input Price
$10/M
Output Price
$50/M
Output Speed
82 t/s
Time to First Token
143 ms
Estimated monthly bill
Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...
Cite & embed
GitHub Markdown badge
[](https://llmpodium.com/models/gpt-6-astra)BibTeX
@misc{llmpodium2026gpt6astra,
title = {Benchmark Analysis and Intelligence Evaluation of GPT-6 Astra},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/gpt-6-astra}
}Head-to-head
More from OpenAI
Alternative Models
Closest alternatives to GPT-6 Astra based on capabilities, pricing, and benchmark scores.
