WizardLM 2 8x22B
Summary
WizardLM 2 8x22B is an open-weight language model from Microsoft, released on 15 Apr 2024. It accepts text and generates text, with a 66K-token context window and up to 8K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $0.62 per million input tokens and $0.62 per million output tokens (Novita AI), across 1 provider we track.
Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Microsoft |
|---|---|
| Release date | 15 Apr 2024 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 66K (65,535 tokens) [models.dev] |
| Max output | 8K tokens [models.dev] |
| Knowledge cutoff | 30 Apr 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | microsoft/WizardLM-2-8x22B |
WizardLM 2 8x22B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Novita AI microsoft/wizardlm-2-8x22b | $0.62 | $0.62 | – | 66K | models.dev, 19 Nov 2026 |
Frequently asked questions
What is the context window of WizardLM 2 8x22B?
WizardLM 2 8x22B has a context window of 65,535 tokens (66K) and can generate up to 8,000 tokens in a single response, according to models.dev.
How much does the WizardLM 2 8x22B API cost?
WizardLM 2 8x22B is listed from $0.62 per million input tokens and $0.62 per million output tokens (Novita AI). Prices last verified 19 Nov 2026.
Is WizardLM 2 8x22B open source?
WizardLM 2 8x22B is an open-weight model: its weights are published on Hugging Face as microsoft/WizardLM-2-8x22B. Check the license terms before commercial use.
When was WizardLM 2 8x22B released?
Microsoft released WizardLM 2 8x22B on 15 Apr 2024, according to models.dev.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Llama-3.1-70B-Instruct | Meta | 23 Jul 2024 | 131K | $0.72 | $0.72 | Open |
| Mixtral 8x22B Instruct | Mistral AI | 17 Apr 2024 | 66K | $2 | $6 | Open |
| Llama 3.1 Euryale 70B v2.2 | Sao10k | 28 Aug 2024 | 131K | $0.85 | $0.85 | Open |
| Command R | Cohere | 30 Aug 2024 | 128K | $0.15 | $0.60 | Open |
| Llama Guard 3 8B | Meta | 23 Jul 2024 | 131K | $0.48 | $0.03 | Open |
| Hermes 2 Pro Llama 3 8B | Nousresearch | 30 Apr 2024 | 131K | $0.14 | $0.14 | Open |
Change history
- No longer listed on openrouter
- Name changed from WizardLM-2 8x22B to WizardLM 2 8x22B
- Release date changed from 16 Apr 2024 to 15 Apr 2024
- Structured output changed from no to yes
- Now listed on Novita AI