weightsapi.INFERENCEConsole
Navigation
MODEL REFERENCE

Dolphin Mistral 24B Venice Edition

Conversations and characters with application-controlled instructions, from Dolphin and Venice.

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$0.20
OUTPUT / 1M$0.90
SERVICE CONTEXT*128K
MEASURED SPEED— not measured

API model IDdphn/Dolphin-Mistral-24B-Venice-Edition

Published context131,072 tokens

QuantizationNot verified

LicenseApache 2.0 ↗

Best for#

Character-based conversations and assistants whose tone and instructions are controlled by the application. Dolphin developed this edition with Venice to emphasize user control.

Choose another model when#

You need audio, video or independently validated image understanding. The authors describe this model as uncensored; that does not guarantee that every request will receive an answer.

Deployment details#

The current upstream version 1.2 includes text and image input and a configured context of 131,072 positions. Confirm WeightsAPI’s serving limit and precision for the deployment. Measured throughput is not available.

Shared inference is billed at the input and output prices shown on this page, in USD per million tokens. The same rates apply throughout WeightsAPI’s service context window; no cache or batch discount applies to this standard rate. Confirm the deployed context before using the listed 131,072-token service ceiling. See pricing and service status before use.

License and provenance#

These are weights published by Dolphin, not an unchanged Mistral release. The publisher declares Apache 2.0 in the model card. The version 1.2 update documents the added vision and longer context.

Call this model#

Once a priced deployment is enabled, use dphn/Dolphin-Mistral-24B-Venice-Edition with Chat Completions. WeightsAPI adds no gateway content filter. Application instructions, model behavior and the serving configuration can still affect responses, including refusals.

Sign-in, one confirmed top-up of at least USD 100 and enough available credit are required for AI access. Published prices do not activate a model: check service status for deployment availability.

Request example

curl https://weightsapi.com/v1/chat/completions \
  -H "Authorization: Bearer $WEIGHTSAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "dphn/Dolphin-Mistral-24B-Venice-Edition",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true
}'
Content checked 2026-09-04 · View changelog ↗