NewJoin us for the Forge keynote livestream on November 3rd
DocsLog inGet started
Deepseek logo

DeepSeek-V4-Pro-0813

Ready
model path:accounts/fireworks/models/deepseek-v4-pro-0813
Deploy on demandFine-tune

DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.

DeepSeek-V4-Pro-0813 API Features

Fine-tuning

Docs

DeepSeek-V4-Pro-0813 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

On-demand Deployment

Docs

On-demand deployments allow you to use DeepSeek-V4-Pro-0813 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
13 AUG, 2026
Kind
Base model
Provider
Deepseek
Huggingface
deepseek-ai/DeepSeek-V4-Pro-0813

Specifications

Calibrated
No
Mixture-of-Experts
Yes
Parameters
1.6T

Supporting Functionality

Fine-tuning
Supported
Serverless
Not Supported
Context Length
1040k tokens
Function Calling
Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported

DeepSeek-V4-Pro-0813 FAQs

Only on serverless, starting on September 25, 2026. On-demand deployment will continue to be available. Migrate serverless workloads to DeepSeek V4.1 Flash.

DeepSeek-V4-Pro-0813 API & Playground | Fireworks AI