GPT-6 Astra

OpenAI's most capable model for the hardest end-to-end work.

gpt-6-astra
STABLEGet StartedView uptime
1,050,000 context
Released September 3, 2026
Starting at $9.00/M (10% off) input tokens (tiered)
Starting at $45.00/M (10% off) output tokens (tiered)
Streaming
Vision
Tools
Reasoning
JSON Output
Structured JSON
Web Search
No ratings yetSign in to rate
10% offthis model via OpenAI

All Providers for GPT-6 Astra

PassingRight routes requests to the best providers that are able to handle your prompt size and parameters.

Context: 1.1M
Input
$10
/M tokens
Cache Read
$1
/M tokens
Output
$50
/M tokens
Cache Write 5m
$12.5
/M tokens
Cache Write 1h
$12.5
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤272K tokens
$10
$1
$50
>272K tokens
$20
$2
$75
Get Started
Context: 1.1M
Input
$10
/M tokens
Cache Read
$1
/M tokens
Output
$50
/M tokens
Cache Write 5m
$12.5
/M tokens
Cache Write 1h
$12.5
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤272K tokens
$10
$1
$50
>272K tokens
$20
$2
$75
+ $0.010 per search
Get Started
Context: 1.1M10% off
Input
$10$9
/M tokens
Cache Read
$1$0.9
/M tokens
Output
$50$45
/M tokens
Cache Write 5m
$12.5$11.25
/M tokens
Cache Write 1h
$12.5$11.25
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤272K tokens
$10$9
$1$0.9
$50$45
>272K tokens
$20$18
$2$1.8
$75$67.5
+ $0.010$0.009 per search
Get Started

Frequently asked questions

What is GPT-6 Astra?

OpenAI's most capable model for the hardest end-to-end work. You can access it through PassingRight's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GPT-6 Astra cost?

Pricing for GPT-6 Astra on PassingRight starts at $10.00 per million input tokens and $50.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of GPT-6 Astra?

GPT-6 Astra supports a context window of up to 1,050,000 tokens on its largest provider deployment.

Which providers serve GPT-6 Astra?

GPT-6 Astra is served by AWS Mantle, Azure, OpenAI through PassingRight. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GPT-6 Astra support tool calling and structured outputs?

Yes. GPT-6 Astra supports both tool (function) calling and strict JSON output schema (upstream-enforced) through PassingRight.

When was GPT-6 Astra released?

GPT-6 Astra was released on September 3, 2026.