Microsoft: WizardLM 2 8x22B

Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks

Source-linked Open weights Apache-2.0 Released 2024-04-15

API record Report

InputT

OutputT

Input price$0.493/M

Output price$0.493/M

Context65.536K

Max output8K

Providers4

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering WizardLM 2 8x22B
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
NanoGPT	`microsoft/wizardlm-2-8x22b`	65.536K	8.192K	$0.493	$0.493	$0.246	Not listed	Docs ↗
Kilo Gateway	`microsoft/wizardlm-2-8x22b`	65.535K	8K	$0.62	$0.62	—	Not listed	Docs ↗
Novita AI	`microsoft/wizardlm-2-8x22b`	65.535K	8K	$0.62	$0.62	—	JSON	Docs ↗
OpenRouter	`microsoft/wizardlm-2-8x22b`	65.535K	8K	$0.62	$0.62	—	Not listed	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.493/M

Across 4 priced providers

Median input $0.62/M

Midpoint of listed rates

Highest input $0.62/M

1.3× the lowest listed rate

Output range $0.493 – $0.62

Per million output tokens

NanoGPT $0.493/MLowest

Kilo Gateway $0.62/M

Novita AI $0.62/M

OpenRouter $0.62/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 65.535K to 65.536K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No

× Tool calling No

× Structured output No

× Attachments No

× Vision input No

✓ Open weights Yes

Creator: Microsoft
Model family: Not documented
Knowledge cutoff: Not documented
License: Apache-2.0
Release date: 2024-04-15
Model ID: microsoft/wizardlm-2-8x22b

Weights: Hugging Face archive ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Oct 19, 2026Context Length65535 → 65536

Oct 19, 2026Price Completion0.62 → 0.493

Oct 19, 2026Price Prompt0.62 → 0.493

Oct 19, 2026Context Length65536 → 65535

Oct 19, 2026Price Completion0.493 → 0.62

Oct 19, 2026Price Prompt0.493 → 0.62

Oct 18, 2026Context Length65535 → 65536

Oct 18, 2026Price Completion0.62 → 0.493

Oct 18, 2026Price Prompt0.62 → 0.493

Oct 18, 2026Context Length65536 → 65535

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Oct 24, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Models.devcatalog ↗NanoGPT documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗Novita AI documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://modelbench.lol/api/v1/models/microsoft/wizardlm-2-8x22b

curl

curl "https://modelbench.lol/api/v1/models/microsoft/wizardlm-2-8x22b"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is WizardLM 2 8x22B?

Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks. It is published by Microsoft and catalogued here from Models.dev.

How much does WizardLM 2 8x22B cost?

Listed input pricing starts at $0.493 per million tokens from NanoGPT, rising to $0.62 across 4 listed providers.

What is the context length of WizardLM 2 8x22B?

WizardLM 2 8x22B accepts up to 65.536K tokens of context and returns up to 8K output tokens.

Which providers serve WizardLM 2 8x22B?

4 providers list this model: NanoGPT, Kilo Gateway, Novita AI, OpenRouter.

Are the weights for WizardLM 2 8x22B open?

Yes. The weights are published and downloadable from Hugging Face archive under the Apache-2.0 license.

When was WizardLM 2 8x22B released?

The catalog records a release date of 2024-04-15, last verified Oct 24, 2026.

More models from Microsoft

View all →

Microsoft: Phi 4

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

16.384K ctx $0.07/M in MAI-Code-1-Flash

Microsoft coding model built for fast, efficient assistance in everyday developer workflows

256K ctx microsoft/HARC

No provider description available.

Not documented ctx microsoft/HARC-Qwen2.5-7B-Instruct

No provider description available.

Not documented ctx