WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model, an instruct finetune of Mixtral 8x22B optimized for complex reasoning and instruction-following tasks. Its authors report highly competitive performance compared to leading proprietary models and consistently better results than other open-source models.
$0.31
$0.31
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model, an instruct finetune of Mixtral 8x22B optimized for complex reasoning and instruction-following tasks. Its authors report highly competitive performance compared to leading proprietary models and consistently better results than other open-source models.
On NagaAI, WizardLM 2 8x22B costs $0.31 per 1M input tokens and $0.31 per 1M output tokens. You pay only for what you use, with no subscription.
WizardLM 2 8x22B reads up to 65.5k tokens in one request, counting the prompt and the answer together.
Yes. WizardLM 2 8x22B can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
