microsoft Open weights

WizardLM-2 8x22B pricing & benchmarks

Released Apr 16, 2024 · served by 1 provider

Input / 1M tokens$0.620
Output / 1M tokens$0.620
Context window66K
Cached input
1M in + 300K out$0.81

What WizardLM-2 8x22B is

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...

Providers and prices for WizardLM-2 8x22B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Novitacheapest $0.620 $0.620 66K bf16 100.0%

FAQ

How much does the WizardLM-2 8x22B API cost?

$0.620 per 1M input tokens and $0.620 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.81.

Is WizardLM-2 8x22B free?

No. It is a paid model starting at $0.620 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for WizardLM-2 8x22B?

Novita at $0.620 input / $0.620 output per 1M tokens (bf16 quantization).

Can I self-host WizardLM-2 8x22B?

Yes — weights are published as microsoft/WizardLM-2-8x22B on Hugging Face, so you can run it on your own hardware.