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
Evaluation results from judge-model scoring across diverse task categories. Scores reflect coherence, accuracy and instruction-following.
Pricing history
Direct provider rates per million tokens, plus a typical-conversation cost estimate.
Pricing over time
Input & output per 1M tokens · step-line = price changes
$0.6700
input / 1M
— stable
$0.6700
output / 1M
— stable
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=82
Median response time
123,720ms
n=82
Based on 472 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)
82
OK responses (30d)
82
Total calls (7d)
0
OK responses (7d)
0
Tokonomix benchmark verdicts
Quality drops 9.7 points to 88.0, factual performance weakens significantly
Meta-Llama-3.3-70B-Instruct on OVH AI Endpoints shows a concerning quality decline in this benchmark window, falling from 97.7 to 88.0 overall. The most dramatic shift appears in factual performance, which scored just 57 compared to strong performance in other categories. Creative writing maintains its previous excellence at 95, while multilingual capabilities remain perfect at 100. Reasoning performance is now tracked at 100, representing solid logical processing. The coding category, which scored 98 in the previous window, is no longer represented in current results, making direct comparison difficult. Latency remains essentially stable at 7649ms compared to 7683ms previously, indicating no performance regression in response times. This quality drop of nearly 10 points is substantial and warrants attention, particularly given the weak factual accuracy score that pulls down the overall rating. Users relying on this model for fact-based tasks should be aware of this limitation, while those focused on creative, multilingual, or reasoning applications can expect continued strong performance. The consistency in test runs at 5 samples suggests these results are preliminary but indicative of current capabilities.
Quality
88.0
Latency p50
7,649 ms
Test runs
5