Skip to content
OpenSmartRoute
Model catalogue
C

Cognitivecomputations

Uncensored

cognitivecomputations/dolphin-mistral-24b-venice-edition

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

C

Uncensored

open weights

Cognitivecomputations cognitivecomputations/dolphin-mistral-24b-venice-edition

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

Input $/1M
$0.20
Output $/1M
$0.90
Context
128K
Max output
8K
Released
Jul 9, 2025
Modalities
text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# targets.yaml - declare a target that runs Uncensored
targets:
  - id: dolphin-mistral-24b-venice-edition
    kind: llm
    name: Uncensored
    metadata:
      model: cognitivecomputations/dolphin-mistral-24b-venice-edition          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: false
      context_window: 128000
    cost:
      usd_per_1k_tokens: 0.000550

More from Cognitivecomputations

Other models by the same vendor in the catalogue.

No other models listed.