deepinfraunavailable

Back to Model Explorer

DeepinfraReference only — not currently available on AvalAI

WizardLM-2 8x22B API on AvalAI

deepinfra/microsoft/WizardLM-2-8x22B

WizardLM-2 8x22B is an AI model from Deepinfra that is not currently available on AvalAI; this page is retained as a technical reference.

Open dashboardCompare

Price display scale

Input price$0.48 / 1M tokens

Output price$0.48 / 1M tokens

Context window65,536 tokens

Maximum output65,536 tokens

Release date2024-04-16

Knowledge cutoff2024-04-30

Note

This page is retained for reference and comparison. Choose an available model from the model catalog before integrating.

Capabilities and endpoints

• —

Third-party model parameters

Third-party reference data does not change AvalAI endpoint support; use the capabilities and endpoints above.

• frequency_penalty
• max_tokens
• presence_penalty
• repetition_penalty
• response_format
• seed
• stop
• temperature
• top_k
• top_p

Third-party model data

Source: OpenRouter

Independent sources supplement this context; AvalAI remains authoritative for pricing, availability, and endpoint support.

Reviewed snapshot 2026-07-31

Provider count

—

Context window range

65,535

Maximum output range

8,000

OpenRouter model input rate range

$0.62 / 1M

OpenRouter model output rate range

$0.62 / 1M

OpenRouter fee

5.5% credit purchase fee · OpenRouter fee details

Effective input price range after fee

$0.6541 / 1M

Effective output price range after fee

$0.6541 / 1M

Frequently asked questions

What is the WizardLM-2 8x22B API on AvalAI?

WizardLM-2 8x22B is not currently callable through AvalAI; this page provides reference specifications only.

How much does the WizardLM-2 8x22B API cost on AvalAI?

WizardLM-2 8x22B is not currently callable through AvalAI; the recorded reference price is $0.48 per 1M input tokens and $0.48 per 1M output tokens.

What is the token cost for WizardLM-2 8x22B?

Current AvalAI pricing for WizardLM-2 8x22B is $0.48 / 1M tokens for input and $0.48 / 1M tokens for output.

What is the WizardLM-2 8x22B context window?

The recorded maximum input context for WizardLM-2 8x22B is 65,536 tokens.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)
• OpenRouter marketplace · Last checked: 2026-07-31