Archived
This model has been discontinued by the provider. Historical data is preserved.
No longer available since October 11, 2026.
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.
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=7
Median response time
676ms
n=7
Based on 149 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)
7
OK responses (30d)
7
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
Quality rebounds 12.9 points to 85.1 as factual performance recovers
Qwen3-Coder-30B-A3B-Instruct has demonstrated a significant recovery in this benchmark window, climbing from 72.2 to 85.1 in overall quality score. The most dramatic improvement came from factual performance, which surged from a critically low 14 to a respectable 71, addressing the collapse that defined the previous period. Coding performance remains rock-solid at 92, maintaining consistency across both windows, while multilingual capabilities continue to excel at 92. The reasoning category, which scored a perfect 100 previously, was not tested in the current window, and creative writing was also absent from this evaluation period. Latency increased moderately from 2544ms to 2898ms at the median, representing approximately a 14% slowdown. This trade-off between speed and quality suggests potential model adjustments or infrastructure changes. With five test runs in both windows, the sample size provides reasonable confidence in these results. Users can expect strong coding and multilingual capabilities with much-improved factual accuracy compared to the previous window, though the latency increase may impact time-sensitive applications. The model appears to have stabilized after its previous quality drop.
Quality
85.1
Latency p50
2,898 ms
Test runs
5