Speed analysis
Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.
Quality scores
How this model compares to the rest of the field on each prompt category, from a pairwise fit over the same prompts. The raw judge score sits underneath each number.
Win rate per category: how often this model beats a field-average model on a prompt from that category. 50% is average, not a failing grade. It is not a percentage of correct answers.
Pricing
What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.
Tokens per second
Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.
Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.
Capabilities
Availability
Availability
How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.
Last 7 days
—
Last 30 days
100.0%
n=1
Median response time
2,550ms
n=1
Based on 171 measurements over the last 30 days.
Technical details
Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.
Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.
Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.
Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.
Total calls (30d)
1
OK responses (30d)
1
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
GPT-6-Astra adds multimodal tools, maintains reasoning performance
GPT-6-Astra receives a significant capability expansion in this benchmark window, introducing tools, vision, JSON mode, PDF input, reasoning, JSON schema, parallel tools, and prompt caching. These additions transform the model from a text-only system into a fully multimodal platform with structured output capabilities and developer-friendly features. The reasoning capability, in particular, positions GPT-6-Astra as a competitive option for complex problem-solving tasks that require step-by-step logic. Vision and PDF input support broaden the model's applicability to document analysis and image understanding workflows. The addition of parallel tools and prompt caching suggests OpenAI is prioritizing developer experience and cost efficiency for production deployments. JSON schema support alongside JSON mode provides stricter output validation for enterprise applications. While no performance metrics are available for comparison between windows, the stable positioning with the previous verdict's strong reasoning characterization indicates these are additive improvements rather than replacements. Users should evaluate these new capabilities against their specific use cases, particularly for applications requiring multimodal understanding or structured data extraction.
Quality
—
Latency p50
—
Test runs
0