WizardLM-2 8x22B with Jev
WizardLM-2 8x22B is a model from Microsoft, released 2024-04-16. It costs $0.620 per million input tokens and $0.620 per million output tokens, reads up to 66K tokens of context, and writes up to 8,000 tokens in one reply. Through llm11, set model to microsoft/wizardlm-2-8x22b.
- Input price
- $0.620 / 1M
- Output price
- $0.620 / 1M
- Context window
- 66K tokens
- Max output
- 8K tokens
- Released
- 2024-04-16
- Accepts
- text
Read from the live catalogue and refreshed daily. At blended list price, 55% of the 332 priced models we can call cost more.
Using WizardLM-2 8x22B with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. WizardLM-2 8x22B does the answering when Jev sends it work, or when you name it yourself. At list price WizardLM-2 8x22B falls in the llm11-balanced band, but no pack routes to it because Microsoft is not one of the labs the packs draw from. You can still pin it: pass microsoft/wizardlm-2-8x22b as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for WizardLM-2 8x22B with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00043 | $0.434 |
| Question over retrieved documents | 4,000 / 500 | $0.00279 | $2.79 |
| Long document summary | 30,000 / 1,000 | $0.019 | $19.22 |
Cheaper models to try
The catalogue has no benchmark score for WizardLM-2 8x22B, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Cohere Command A+ | $0.300 | $1.50 | 192K | |
| Qwen Qwen3.5 Plus 2026-02-15 | $0.260 | $1.56 | 1M | |
| Google Gemini 3.1 Flash Lite | $0.250 | $1.50 | 1.05M | |
| Google Gemini 3.1 Flash Lite Preview | $0.250 | $1.50 | 1.05M |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="microsoft/wizardlm-2-8x22b",
messages=[{"role": "user", "content": "Hello"}],
)More from Microsoft
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Phi 4 | $0.070 | $0.140 | 16K |
Questions
- What is WizardLM-2 8x22B with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. WizardLM-2 8x22B does the answering when Jev sends it work, or when you name it yourself. At list price WizardLM-2 8x22B falls in the llm11-balanced band, but no pack routes to it because Microsoft is not one of the labs the packs draw from. You can still pin it: pass microsoft/wizardlm-2-8x22b as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is WizardLM-2 8x22B a System One model?
- No. WizardLM-2 8x22B answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does WizardLM-2 8x22B cost?
- $0.620 per million input tokens and $0.620 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00279, so a thousand of them is about $2.79. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the WizardLM-2 8x22B context window?
- 65,535 tokens, with up to 8,000 tokens in a single reply.
- Does WizardLM-2 8x22B support tool calling and structured output?
- The catalogue lists structured output, but it does not list tool calling and reasoning controls.
- Can I use WizardLM-2 8x22B through llm11?
- Yes. Set model to microsoft/wizardlm-2-8x22b on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to WizardLM-2 8x22B?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price WizardLM-2 8x22B falls in the llm11-balanced band, but no pack routes to it because Microsoft is not one of the labs the packs draw from. You can still pin it: pass microsoft/wizardlm-2-8x22b as model and routing steps aside while verification still runs.
- What is a cheaper alternative to WizardLM-2 8x22B?
- Nearest in price and below it: Cohere Command A+ at $0.300 in and $1.50 out, Qwen Qwen3.5 Plus 2026-02-15 at $0.260 in and $1.56 out and Google Gemini 3.1 Flash Lite at $0.250 in and $1.50 out. The catalogue has no benchmark score for WizardLM-2 8x22B, so this is a price ordering. It does not claim these answer as well.