GPT-6 Astra vs GPT-6 Luna
Compare GPT-6 Astra and GPT-6 Luna side-by-side.
Compare GPT-6 Astra vs GPT-6 Luna live
Run the same image across every model that supports a task and compare their outputs side-by-side.
These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.
Models in this comparison
GPT-6 Astra vs GPT-6 Luna on Vision Evals
GPT-6 Astra scores higher on all six Vision Evals tasks.
The widest gap is Reasoning, where GPT-6 Astra leads 87.2% to 52.1%.
Overall, GPT-6 Astra averages 86.6% (#1 of 57) against 68.6% (#32 of 57) for GPT-6 Luna.
GPT-6 Luna is cheaper ($0.0004 vs $0.030 per sample), while GPT-6 Astra is faster (6.7s vs 11.3s per sample).
GPT-6 Astra vs GPT-6 Luna Comparison Table
Evals updated September 22, 2026Pricing updated September 22, 2026
| Property | GPT-6 Astra | GPT-6 Luna |
|---|---|---|
| Organization | OpenAI | OpenAI |
| Category | closed | closed |
| Modality | multimodal | multimodal |
| Release Date | Sep 2026 | Sep 2026 |
| Context Window | 1.1M | 1.1M |
| Parameters | Undisclosed | |
| License | Proprietary | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $10.00 | |
| Output $/1M | $50.00 | |
| Vision Tasks | ||
| Captioning | Demo | |
| Chart Question Answering | ||
| Classification | Demo | |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | |
| OCR | Demo | |
| Vision Language | ||
| Visual Question Answering | Demo | |
| Promptable Concept Segmentation | Demo | |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort | ||
| Overall | 86.6% | 68.6% |
| Avg cost / sample | $0.030 | $0.0004 |
| Avg speed / sample | 6.67s | 11.27s |
| By task | ||
| Object Detection (low) | 82.1% ±0.8, Mean of 3 runs, range 81.0 to 82.7 | 56.8% ±1.9, Mean of 3 runs, range 54.8 to 58.5 |
| Object Detection (high) | 83.6% ±0.8, Mean of 3 runs, range 82.8 to 84.5 | 64.1% ±0.5, Mean of 3 runs, range 63.6 to 64.5 |
| Counting (low) | 80.2% ±1.4, Mean of 3 runs, range 78.4 to 81.1 | 65.8% ±1.4, Mean of 3 runs, range 64.9 to 67.6 |
| Counting (high) | 81.1% ±1.4, Mean of 3 runs, range 79.7 to 82.4 | 64.4% ±2.0, Mean of 3 runs, range 62.2 to 66.2 |
| Identification (low) | 89.6% ±1.6, Mean of 3 runs, range 87.5 to 90.6 | 81.3% ±0.0, Mean of 3 runs, range 81.3 to 81.3 |
| Identification (high) | 92.7% ±1.6, Mean of 3 runs, range 90.6 to 93.8 | 80.2% ±1.6, Mean of 3 runs, range 78.1 to 81.3 |
| OCR (low) | 91.9% ±0.2, Mean of 3 runs, range 91.6 to 92.1 | 87.9% ±0.6, Mean of 3 runs, range 87.2 to 88.3 |
| OCR (high) | 91.5% ±0.2, Mean of 3 runs, range 91.3 to 91.7 | 88.5% ±0.6, Mean of 3 runs, range 87.9 to 89.2 |
| Data Extraction (low) | 88.7% ±1.0, Mean of 3 runs, range 87.6 to 89.7 | 68.0% ±3.1, Mean of 3 runs, range 65.0 to 71.1 |
| Data Extraction (high) | 91.1% ±1.0, Mean of 3 runs, range 89.7 to 91.8 | 66.7% ±0.5, Mean of 3 runs, range 66.0 to 67.0 |
| Reasoning (low) | 87.2% ±1.0, Mean of 3 runs, range 86.1 to 88.1 | 52.1% ±2.0, Mean of 3 runs, range 49.7 to 53.6 |
| Reasoning (high) | 91.2% ±0.3, Mean of 3 runs, range 90.7 to 91.4 | 60.7% ±1.7, Mean of 3 runs, range 58.9 to 62.3 |
GPT-6 Astra vs GPT-6 Luna: Overview
GPT-6 Astra is a proprietary multimodal reasoning model from OpenAI that accepts text and image input and produces text output. It is positioned as the company's flagship system for long-horizon end-to-end work spanning complex reasoning, software engineering, computer use, browsing, research and document creation. The model exposes a graduated reasoning effort control with low, medium, high, xhigh and max settings, and it accepts a change to that setting partway through a conversation rather than only at request time. It launches as a single tier with no smaller mini or nano variants, carries a context window of roughly 1.05 million tokens with a maximum output of 128,000 tokens, and reports a knowledge cutoff of April 30, 2026.
OpenAI reports evaluation results across agentic, scientific and security benchmarks, including 96.0% on GPQA Diamond, 64.6% on Terminal-Bench Science, 72.6% on OSWorld 2.0, and a perfect score on ExploitBench, along with near saturation on FrontierMath Tier 4 and ARC-AGI-3. The model supports computer use, structured outputs, streaming, programmatic tool calling, multi-agent orchestration, prompt caching and persisted reasoning, and it keeps earlier context windows searchable so it can recover requirements or tool outputs from previous turns. OpenAI describes Astra as the first of its models to cross the Critical cybersecurity capability threshold under its Preparedness Framework.
GPT-6 Luna is the fast, cost-efficient tier of OpenAI's GPT-6 model family, sitting below GPT-6 Sol and the larger GPT-6 Astra model that opened the generation. It is a proprietary multimodal transformer that accepts text and image input and returns text, and it exposes an adjustable reasoning effort setting so the same model can run in a low-latency mode or spend additional inference compute on harder problems. OpenAI positions it for high-volume and latency-sensitive workloads such as conversational assistants, classification, and lightweight agentic pipelines, while noting that at higher reasoning effort it handles software engineering and computer-use tasks that previously required a Sol-tier model.
The model supports a context window of roughly 1,050,000 input tokens with a maximum output of 128,000 tokens, which allows long documents, extended agent traces, and large code repositories to be processed in a single request. OpenAI describes the GPT-6 generation as improving factual reliability and adopting a more concise communication style relative to the GPT-5.6 series, and attributes the efficiency of the Sol and Luna tiers to gains in caching and inference rather than to reduced capability. Architecture details, parameter counts, and training data are not published.
Frequently Asked Questions
On Roboflow's Vision Evals, GPT-6 Astra performed better. It scores higher on all six vision tasks and averages 86.6% (#1 of 57) against 68.6% (#32 of 57) for GPT-6 Luna. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
Yes. On the Vision Evals Reasoning benchmark at low effort, GPT-6 Astra leads with 87.2% against 52.1%. This is the widest gap between the two models across the benchmark's tasks.
GPT-6 Luna is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0004 per sample against $0.030. Actual costs depend on your image sizes, prompts, and output length.
GPT-6 Astra is faster. Across Roboflow's Vision Evals it averaged 6.7s per inference against 11.3s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.