API Status

mixtral-8x22b Benchmarks

Provider: deepinfra

Explore real-world latency and throughput results for mixtral-8x22b. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the deepinfra provider hub to compare every tracked model side-by-side.

Visit deepinfra Official Website

Benchmark Overview

Avg Tokens / Second

59.10

Avg Time to First Token (ms)

400.00

Runs Analysed

100

Last Updated

Feb 18, 2026, 09:00 PM

Key Insights

  • mixtral-8x22b streams at 59.10 tokens/second on average across the last 100 benchmark runs.

  • Performance fluctuated by 63.10 tokens/second (106.8% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 400.00 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Feb 18, 2026, 09:00 PM based on 100 total samples.

Performance Distribution

Distribution of throughput measurements showing performance consistency across benchmark runs.

Performance Over Time

Historical performance trends showing how throughput has changed over the benchmarking period.

mixtral-8x22b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
deepinframixtral-8x22b59.1014.4077.50400.00

Frequently Asked Questions

The latest rolling average throughput is 59.10 tokens per second with an average time to first token of 400.00 ms across 100 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 18, 2026, 09:00 PM.

Related Links