The right model for every task. Try Nexus
Docs
Log in
Get started
Deepseek logo

DeepSeek-V4-Flash-0731

Ready
model path:accounts/fireworks/models/deepseek-v4-flash-0731
Deploy on demandFine-tune

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.

DeepSeek-V4-Flash-0731 API Features

Fine-tuning

Docs

DeepSeek-V4-Flash-0731 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-Flash-0731 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
31 JUL, 2026
Kind
Base model
Provider
Deepseek
Huggingface
deepseek-ai/DeepSeek-V4-Flash-0731

Specifications

Calibrated
No
Mixture-of-Experts
Yes
Parameters
304B

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-Flash-0731 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.