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
85.7%
n=14
Last 30 days
87.5%
n=16
Median response time
12,735ms
n=14
Based on 189 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)
16
OK responses (30d)
14
Total calls (7d)
14
OK responses (7d)
12
Tokonomix benchmark verdicts
Gemini 3.8 Flash adds multimodal tools and structured output capabilities
Gemini 3.8 Flash has gained significant functional expansion with the addition of multiple capabilities previously unavailable. The model now supports tools and parallel tool calling, enabling function-based interactions. Vision, PDF input, and audio input capabilities have been added, making this a fully multimodal offering. Structured output is now available through both JSON mode and JSON schema enforcement, addressing developer needs for reliable formatting. Reasoning capabilities and prompt caching have also been introduced, though performance metrics for these features are not yet available. The model maintains its flash designation, suggesting continued emphasis on speed and efficiency. This represents a substantial evolution from a text-only model to a comprehensive multimodal platform. Users gain access to document understanding, image processing, and audio analysis within a single model. The parallel tools feature allows for more efficient multi-step operations. These additions position Gemini 3.8 Flash as a versatile option for applications requiring diverse input modalities and structured interactions. Developers should evaluate the quality of these newly added capabilities in their specific use cases.
Quality
—
Latency p50
—
Test runs
0