WizardLM-2 8x22B
Microsoft · released Apr 16, 2024 · microsoft/WizardLM-2-8x22B
- Type
- Open weights
- Params
- Not published
- Context
- 66K
about 49K words of context
Our take
Written Aug 3, 2026WizardLM-2 is a text-only downloadable model from Microsoft released in 2024 with a flat per-token rate across all tracked hosts. Its licence terms are undisclosed and no quality scores are available, so it suits teams who value predictable cost over measured performance.
Pick this for budget-conscious text-only inference where a flat, predictable rate with no input-output penalty matters more than proven quality scores. Use it if you need a 65,535-token request limit with downloadable weights. Skip it if you need measured benchmark data, clear licence terms for redistribution, or throughput guarantees — only one of three offers lists a speed figure, and that figure is low.
The case for it
- Flat, predictable pricing with no input-output penalty across all three tracked offers.
- Open weights, so you can download and run the model yourself rather than relying solely on hosted inference.
The case against it
- No measured quality data in our catalogue; zero benchmark scores are listed.
- Throughput data is thin or low where present: one offer lists three tokens per second, and two have unverified figures.
- Open weights without a clear licence; redistribution and commercial-use terms are undisclosed.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up WizardLM-2 8x22B — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.62 in / $0.62 out
- Context served
- 66K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.62 / $0.62 | 66K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.62 / $0.62 | 66K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.62 / $0.62 | 66K | 11 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✗ |
| Novita AI | |||
| Novita AIbf16 | ✗ | ✓ | ✗ |
Tool calling: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. JSON output: 2 of 3 listings say yes, 1 publishes no parameter list. Strict schema: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- 1 of 3 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model yet.
Identifiers
- Hugging Face
- microsoft/WizardLM-2-8x22B
- Modality record
- text->text
- Catalogue slug
- microsoft-wizardlm-2-8x22b