WizardLM-2 8x22B

Microsoftmicrosoft/wizardlm-2-8x22bProviders: 1
Inputi$0.62per 1M tokens
Outputi$0.62per 1M tokens
Contexti66K65,535 tokens
ReleasedApr 16, 2024Max output: 8K

About this model

WizardLM-2 8x22B is an AI model from Microsoft, made available through the API on April 16, 2024. It can read up to 65,535 tokens in one request, roughly 123 pages of text, and write up to 8,000 tokens in a single answer.

Through the API it costs $0.62 per million input tokens and $0.62 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.

Its weights are openly published (microsoft/WizardLM-2-8x22B), so it can also be downloaded and run on your own hardware.

Quality scores

Rankings →
  • GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.43.4%#104 of 116

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
Novitabf16
$0.62$0.6266K100.0%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call WizardLM-2 8x22B through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "microsoft/wizardlm-2-8x22b", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $0.496
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.032
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $260

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
$0.60$2.40256KCompare with ⇄
GLM 5Z.ai (Zhipu)
$0.60$1.92200KCompare with ⇄
$0.60$61MCompare with ⇄
Kimi K2 ThinkingMoonshot AI
$0.60$2.50256KCompare with ⇄
Qwen3 Coder PlusAlibaba Qwen
$0.65$3.251MCompare with ⇄
Gemma 2 27BGoogle DeepMind
$0.65$0.658KCompare with ⇄

News about Microsoft

See all →

Frequently asked questions

How much does WizardLM-2 8x22B cost?
WizardLM-2 8x22B costs $0.62 per million input tokens and $0.62 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.496.
What is the context window of WizardLM-2 8x22B?
WizardLM-2 8x22B can read up to 65,535 tokens in one request, about 123 pages of text. It can write up to 8,000 tokens in a single answer.
Is WizardLM-2 8x22B open source?
Yes. Its weights are published (microsoft/WizardLM-2-8x22B), so you can download it and run it on your own hardware, or use it through one of 1 API providers.
Who makes WizardLM-2 8x22B?
WizardLM-2 8x22B is made by Microsoft. It became available through the API on April 16, 2024.
Can WizardLM-2 8x22B read images?
No. WizardLM-2 8x22B only accepts text as input.
What are the alternatives to WizardLM-2 8x22B?
Models with a similar price from other companies include Nemotron 3 Ultra, GLM 5 and Palmyra X5. You can compare them side by side on this page.