Model reference · Synced 2025-04-29
WizardLM-2 8x22B
WizardLM-2 8x22B is an AI model from NanoGPT. 66K context window. Capabilities: open weights. Available on 3 providers. Cheapest listing: $0.493 input / $0.493 output per 1M tokens.
Quick facts
- Cheapest input: $0.493 per 1M tokens (NanoGPT)
- Cheapest output: $0.493 per 1M tokens
- Context window: 66K tokens
- Max output: 8K tokens
- Release date: 2025-04-15
- Capabilities: open weights
- Provider count: 3
Provider pricing
Same model, different providers, different prices. Cheapest first.
| Provider | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| NanoGPT | $0.493 | $0.493 | 66K | 2025-04-15 |
| NovitaAI | $0.62 | $0.62 | 66K | 2024-04-24 |
| Kilo Gateway | $0.62 | $0.62 | 66K | 2024-04-24 |
Prices synced daily from models.dev + provider docs.
How to use this model
If you're picking WizardLM-2 8x22B for a project, the three things that matter most:
- Compare it side-by-side with one or two alternatives in the live comparison tool. Pricing differences matter more than benchmarks at scale.
- Pick the cheapest provider that meets your latency / SLA need. Big spread across providers for the same weights.
- Re-evaluate every 3 months. Frontier prices drop fast; a model that's cheapest today may not be in a quarter.
FAQ
How much does WizardLM-2 8x22B cost? $0.493 input / $0.493 output per 1M tokens at the cheapest listing. See the table above for other providers.
What is the context window? 66K tokens.
Which providers offer it? NanoGPT, NovitaAI, Kilo Gateway.
Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.