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
1,009ms
n=1
Based on 168 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
Significant capability expansion with tools and multimodal input support
This release represents a major functional evolution for gpt-5.6-luna, introducing seven new capabilities that substantially broaden the model's utility. The additions of tools, vision, and pdf_input transform this from a text-only model into a multimodal system capable of processing images and documents. The inclusion of reasoning capabilities suggests enhanced problem-solving potential, while json_mode, json_schema, and parallel_tools indicate improved structured output handling and efficiency for developer workflows. Prompt caching adds performance optimization for repeated queries. These changes position the model as a more versatile option for complex applications requiring multiple input types and structured interactions. However, without performance benchmark data for this window, it's unclear whether these capability additions come with trade-offs in speed, accuracy, or other metrics that users experienced in the previous baseline. The expansion from a focused text model to a feature-rich multimodal system represents a strategic shift that will appeal to users needing comprehensive AI tooling, though those seeking the simplicity of the previous text-focused approach may need to evaluate whether the added complexity aligns with their use cases.
Quality
—
Latency p50
—
Test runs
0