Kimi K3 on Fireworks: Frontier Intelligence You Can Own

Model Library/Deep Cogito/Cogito v1 Preview Llama 70B
Deep Cognito Model Logo

Cogito v1 Preview Llama 70B

Ready
Deploy on Demand
model path:accounts/fireworks/models/cogito-v1-preview-llama-70b

The Cogito LLMs are instruction tuned generative models that are also hybrid reasoning models

Cogito v1 Preview Llama 70B API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Cogito v1 Preview Llama 70B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
4/7/2025
Kind
Base model
Provider
Deep Cogito
Hugging Face
deepcogito/cogito-v1-preview-llama-70B

Specification

Calibrated
No
Mixture-of-Experts
No
Parameters
70.5B

Supported Functionality

Fine-tuning
Not supported
Serverless
Not supported
Context Length
131k tokens
Function Calling
Supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported