WizardLM-2 8x22B
microsoft/wizardlm-2-8x22b
WizardLM-2 8x22B is a 22B open-weight model, ranking #213 of 235 on the TryAii Score. It's served by 1 independent host from $0.62/$0.62 per million input/output tokens. It's on the slow side at about 8 tokens/sec.
Prompt $/1M
$0.620
Completion $/1M
$0.620
Context
65,535 tok
Best provider
8 tok/s · Novita
Specs
- Model id
- microsoft/wizardlm-2-8x22b
- Display name
- WizardLM-2 8x22B
- Modality
- text->text
- Tokenizer
- Mistral
- Instruct type
- vicuna
- Context length
- 65,535
- Max completion
- 8,000
- Prompt $/1M
- $0.620
- Completion $/1M
- $0.620
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Novitafastest | 8 |
| microsoftfastest | — |