Microsoft: WizardLM-2 8x22B

Public pricingIntelligence 79/100Medium memoryTool use

WizardLM-2 8x22B is a text model for general chat, analysis, and production use. It combines steady general-purpose performance with a 66K tokens context window and a balanced-cost profile. Use it for general chat, analysis, and production workloads when quality, speed, and cost matters. It is a practical choice for teams that need reliable output, flexible deployment, and room to scale.

Input

$0.62/1M

Output

$0.62/1M

Cached

$0.05/1M

Batch

$0.25/1M

Calculate your WizardLM-2 8x22B bill.

Set your workload — see cost at your exact volume.

What would WizardLM-2 8x22B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

WizardLM-2 8x22B at a glance.

Memory

65,535

tokens

Max reply

8,000

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

mistral

Released

Apr 2024

Training cutoff

Jan 2024

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • mt_bench

    9.1

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick WizardLM-2 8x22B

  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

WizardLM-2 8x22B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, WizardLM-2 8x22B costs roughly $71 per month. Input is $0.62 /1M tokens and output is $0.62 /1M tokens.
WizardLM-2 8x22B has a 65,535-token context window (medium memory — a long report or a codebase file). That means you can fit about 12,288 words of input and history in a single call.
Beyond text generation, WizardLM-2 8x22B supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
WizardLM-2 8x22B was released in April 2024, with training data cut off around January 2024.
Models in a similar class include Phi 4, Kimi K2 Thinking, GPT Audio Mini. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare WizardLM-2 8x22B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard