microsoftListed Apr 16, 2024

WizardLM-2 8x22B

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...

Context window65.5K
Max output8K
Provider endpoints2
Benchmark results0
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

2 quotes

OpenRouter

Catalog quote
Input
$0.62
Output
$0.62
USD / 1M tokens
65.5K context8K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmicrosoft/wizardlm-2-8x22b

Novita

via OpenRouter

novita/bf16 · quantization=bf16

Input
$0.62
Output
$0.62
USD / 1M tokens
65.5K context8K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmicrosoft/wizardlm-2-8x22b::novita/bf16

Model specifications

Developer
microsoft
Modality
Language
Context
65,535 tokens
Maximum output
8,000 tokens
Weights
Open weights
Provider listed
Apr 16, 2024
First discovered
Oct 16, 2026

Exact identities

  • openroutermicrosoft/wizardlm-2-8x22b

Sources

Updated Oct 17, 2026

More from microsoft

View all ↗
microsoftListed Sep 3

Microsoft AI: MAI-Transcribe 2

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for…

Audio inputNo reported score
No reported score
$100,000.00in$0.00out/ 1M tokens · USDOpenRouter
microsoftListed Jun 2

Microsoft AI: MAI-Transcribe 1.5

MAI-Transcribe 1.5 is a multilingual speech-to-text model from Microsoft AI. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, with reliable…

Audio inputNo reported score
No reported score
$360,000.00in$0.00out/ 1M tokens · USDOpenRouter
microsoftListed Dec 11

phi-4

Phi-4 is a model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable…

16.4K contextStructured outputOpen weightsNo reported score
No reported score
$0.056in$0.112out/ 1M tokens · USDDeepInfra · via OpenRouter · 6 endpointsdeepinfra/bf16/flex · tier=flex · quantization=bf16