Skip to content
OpenSmartRoute
All vendors
C

Vendor

Cognitive Computations models

1 model in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.

Models

1

0 routable here

Cheapest (blended)

$0.38

Uncensored

Median list price

$0.38

3:1 input to output per 1M tokens

Strongest

-

no published benchmarks

Every Cognitive Computations model

Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.

ModelReleasedContextInput / 1MOutput / 1MIntelligenceCapabilities
Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-editionJul 9, 2025128K$0.20$0.90-
open weights

Frequently asked

What is the cheapest Cognitive Computations model?
Uncensored at $0.20 per 1M input tokens and $0.90 per 1M output tokens (vendor list price).
Which Cognitive Computations model has the largest context window?
Uncensored accepts 128K tokens of context.
How do I route to Cognitive Computations models with OpenSmartRoute?
Declare a target in targets.yaml with metadata.model set to the catalogue id (for example cognitivecomputations/dolphin-mistral-24b-venice-edition); the router scores it against every other target on cost, quality, latency and your policies for each request.

Route Cognitive Computations with everything else

OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Cognitive Computations flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.