Uncensored

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

← Back to leaderboard

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...

Uncensored ranks #151 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.55 blended per million tokens, it is cheaper than 66% of models with published API pricing. Its 128,000-token context window is 2.0× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 128000
Max output: 8192

Pricing

Input / 1M: 0.20
Output / 1M: 0.90
Blend / 1M: 0.55

Quality

Quality index:

Provider

Provider: Cognitivecomputations
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.55per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.55
10,000,000$5.50
100,000,000$55.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

Closest API price