OpenAI's most capable model for the hardest end-to-end work, with state-of-the-art performance in computer use, browsing, software engineering, science, and professional tasks. Astra is designed to carry long, multistep workflows across code, browsers, and professional software through to a finished result.
Added Sep 3, 2026
Context Window
1.1M
Max Output
128.0K
Input Price (Auto)
$10.00/1M
Output Price (Auto)
$50.00/1M
Cache Read (Auto)
$1.00/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
49.6
Coding Index
76.7
Agentic Index
51.0
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
64.6%
Better than 95% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
33.6%
Better than 72% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1459 Elo
Better than 84% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1468 Elo
Better than 84% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
30.4%
Better than 98% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
79.7%
Better than 86% of models compared
Reasoning
HLE
Humanity's Last Exam
52.7%
Better than 97% of models compared
CritPt
Research-level physics reasoning
31.7%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
49.5%
Better than 94% of models compared
SciCode
Python programming for scientific computing
54.2%
Better than 73% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
62.6%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
51.3%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
93.9%
Better than 98% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
79.7%
Better than 86% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
52.1%
Last updated Sep 24, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare GPT 6 Astra with similar models from the same provider or model family.
GPT Astra Latest
openai/gpt-astra-latestCompatibility alias that routes to GPT 6 Astra, the latest supported GPT Astra model.
GPT 6 Astra Pro
openai/gpt-6-astra-proGPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.
GPT 6 Luna
openai/gpt-6-lunaGPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, suited for high-volume chat, classification, and lightweight agent workflows.
GPT 6 Luna Pro
openai/gpt-6-luna-proGPT-6 Luna Pro uses the same underlying model as GPT-6 Luna with Pro reasoning mode enabled for higher-quality responses on complex tasks.
GPT 6 Sol
openai/gpt-6-solGPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, reasoning, coding, and agentic workflows.
GPT 6 Sol Pro
openai/gpt-6-sol-proGPT-6 Sol Pro uses the same underlying model as GPT-6 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.