weightsapi.INFERENCEConsole
Navigation
MODEL REFERENCE

Mixtral 8×22B

Multilingual generation and function-calling workflows.

No KYC

No identity-document upload or KYC step in the current sign-in flow. Access and usage remain linked to your account.

No added content filters

WeightsAPI adds no content filter at the gateway. A model’s own training can still lead it to refuse a request.

INPUT / 1M$0.60
OUTPUT / 1M$0.60
SERVICE CONTEXT*64K
MEASURED SPEEDnot measured

API model IDmistralai/Mixtral-8x22B-Instruct-v0.1

Native context65,536 tokens

QuantizationNot verified

LicenseApache 2.0

Best for#

Multilingual generation and function-calling workflows.

Choose another model when#

Image input and contexts over 64k.

Deployment details#

Use the exact model ID and publisher source shown above. The listed WeightsAPI rates apply to input and output tokens. Confirm deployment availability, serving precision and context before sending traffic; published model specifications do not establish service performance. Check service status.

License and provenance#

Review the official model card before deployment. The license may impose additional terms. Open weights do not imply identical licenses.

Call this model#

Use the exact model ID shown above with the Chat Completions endpoint. The service does not add a content-filtering layer. Model behavior still reflects its original training.

Request example

curl https://weightsapi.com/v1/chat/completions \
  -H "Authorization: Bearer $WEIGHTSAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistralai/Mixtral-8x22B-Instruct-v0.1",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true
}'