Uncensored
Cognitive Computations · Open weights · Released Jul 9, 2025 · cognitivecomputations/dolphin-mistral-24b-venice-edition
128K contextStructured outputOpen weights
Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 Venice | $0.20 | $0.90 | — | 128K | fp16 | 1.4s | 100 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
About
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...
Specifications
Context window128,000
Max output8,192
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 9, 2025
Knowledge cutoff2024-04-30
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensors
Embed badge
[](https://modelindex.ai/models/cognitivecomputations/dolphin-mistral-24b-venice-edition)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks44 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.