Scheduled for retirement on Jan 11, 2028. Still available at the prices below until then.
Context
1.1M
Max output
128K
Serving providers
5
Cheapest input
$10.00 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
61 t/s
tokens / second
Time to first token
280.05s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.5 | default | — | |||||||||||||
| Automation Bench | 0.7 | default | — | |||||||||||||
| CritPt | 32% | default | — | |||||||||||||
| GDPval (normalized)Frozen Aug 18, 2026 | 54% | default | — | |||||||||||||
| GPQA Diamond | 96% | default | — | |||||||||||||
| Harvey Lab | 0.1 | default | — | |||||||||||||
| Humanity's Last Exam | 55% | default | — | |||||||||||||
| IT-Bench SRE | 49% | default | — | |||||||||||||
| Long-Context Reasoning | 81% | default | — | |||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.3 | default | — | |||||||||||||
| MMMU-Pro | 87% | default | — | |||||||||||||
| Omniscience | 43.4 | default | — | |||||||||||||
| Omniscience Accuracy | 0.6 | default | — | |||||||||||||
| Omniscience Non Hallucination | 0.5 | default | — | |||||||||||||
| SciCode | 56% | default | — | |||||||||||||
| Terminal Bench40 | 0.6 | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 88% | default | — | |||||||||||||
| ||||||||||||||||
| τ-bench Banking | 41% | default | — | |||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing detail
cost beyond the standard rate · source: models.devLong context (>200K)
$20.00 / $75.00
input / output · per 1M
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Azure | $10.00 | $50.00 | 1 | |||||||||||||||||||||
Standardazure/gpt-6-astra
| ||||||||||||||||||||||||
| Amazon Bedrock | $10.00 | $50.00 | 1 | |||||||||||||||||||||
Standardglobal.openai.gpt-6-astra
| ||||||||||||||||||||||||
| OpenAICheapest | $10.00 | $50.00 | 1 | |||||||||||||||||||||
Standardgpt-6-astra
| ||||||||||||||||||||||||
| OpenRouter | $10.00 | $50.00 | 1 | |||||||||||||||||||||
Standardopenai/gpt-6-astra
| ||||||||||||||||||||||||
| VercelVercel reseller quote | $10.00 | $50.00 | 1 | |||||||||||||||||||||
Standardopenai/gpt-6-astra
| ||||||||||||||||||||||||
| OpenRouter (batch) | $5.00 | $25.00 | 1 | |||||||||||||||||||||
Batchopenai/gpt-6-astra:batch
| ||||||||||||||||||||||||
| Vercel (flex)Vercel reseller quote | $5.00 | $25.00 | 1 | |||||||||||||||||||||
Flexopenai/gpt-6-astra
| ||||||||||||||||||||||||
| Vercel (fast)Vercel reseller quote | $20.00 | $100.00 | 1 | |||||||||||||||||||||
Fastopenai/gpt-6-astra-fast
| ||||||||||||||||||||||||
| Vercel is dearest at $20.00 / $100.00 | ||||||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$6,000
estimated / month
Model IDs
copy the exact identifier for your platformopenai/gpt-6-astra:batchopenai/gpt-6-astragpt-6-astraopenai/gpt-6-astraazure/gpt-6-astraglobal.openai.gpt-6-astraopenai/gpt-6-astraopenai/gpt-6-astraopenai/gpt-6-astra-fastopenai/gpt-6-astra
Frequently asked questions
GPT-6 Astra pricing, context and availabilityIs GPT-6 Astra still available?
Yes. GPT-6 Astra is scheduled for retirement on 2028-01-11.
How much does GPT-6 Astra cost?
GPT-6 Astra costs $10.00 per 1M input tokens from OpenAI, and $50.00 per 1M output tokens from OpenAI.
What is the context window of GPT-6 Astra?
GPT-6 Astra accepts up to 1.1M tokens of context and can return up to 128K output tokens.
Which providers serve GPT-6 Astra?
GPT-6 Astra is available from 5 serving providers, each with its own pricing and model ID. OpenAI is currently the cheapest.
What can GPT-6 Astra do?
GPT-6 Astra supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other OpenAI models
compare pricing across the OpenAI lineupPopular comparisons
head-to-head pages featuring GPT-6 Astra
GPT-6 Astra vs Claude Opus 5
GPT-6 Astra vs DeepSeek V4.1 Flash
GPT-6 Astra vs Gemini 3.7 Flash Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI