Microsoft
EfficientRETIREDAUTO PROFILEPriced via OpenRouter

WizardLM-2 8x22B

text->text

WizardLM-2 8x22B is a community fine-tune. Behaviour and benchmarks track the upstream base model the fine-tune was trained from. Available via Microsoft. 65,535-token context. Efficient pricing. Inherits weights from an upstream open-weights base; benchmarks track the base model unless the fine-tuner publishes their own.

WizardLM-2 8x22B is a efficient AI model from Microsoft. It costs $0.6200 per million input tokens and $0.6200 per million output tokens (blended $0.6200/M), with a 65,535-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.6200/M
per million input tokens
OUTPUT
$0.6200/M
per million output tokens
BLENDED 70/30
$0.6200/M
unchanged since 3 May
CONTEXT
65,535
tokens

The last price on OpenRouter's listing; the model left the feed by 3 Nov 2026.

What it is good at
  • Persona/tuning beyond the base model
  • Persona/style adherence beyond the base model
  • Specific domain (RP, instruction, etc.) tuning
  • Inherits base-model capability
Typical use cases
  • Roleplay and creative chat
  • Domain-specific assistants
  • Custom persona deployments

Benchmarks

vs. best public score
Scores inherited from Mixtral 8x22B (WizardLM-2 base) — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU78%
Multitask academic knowledge across 57 subjects. No source recorded yet.
MATH42%
High-school competition math problems. No source recorded yet.
Python function synthesis from docstrings. No source recorded yet.
LMArena Elo1230 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Microsoft

See all 8 →

Frequently asked questions

How much does WizardLM-2 8x22B cost?

WizardLM-2 8x22B costs $0.6200 per million input tokens and $0.6200 per million output tokens, for a blended reference rate of $0.6200 per million tokens.

What is WizardLM-2 8x22B's context window?

WizardLM-2 8x22B supports up to 65,535 tokens of context in a single request.

What is WizardLM-2 8x22B best for?

WizardLM-2 8x22B is well suited to Persona/tuning beyond the base model, Persona/style adherence beyond the base model and Specific domain (RP, instruction, etc.) tuning.

Who makes WizardLM-2 8x22B?

WizardLM-2 8x22B is developed and served by Microsoft.

Terms used on this page