DeepSeek V4 Flash 0731 on Fireworks AI

Name: DeepSeek V4 Flash 0731 on Fireworks AI
Brand: DeepSeek
SKU: deepseek-v4-flash-0731-fireworks-ai

DeepSeek V4 · DeepSeek

Provisioned

Open Source

Last refreshed 2026-10-19. Next refresh: weekly.

Why use DeepSeek V4 Flash 0731 on Fireworks AI?

Fireworks AI offers DeepSeek V4 Flash 0731. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.

Compare DeepSeek V4 Flash 0731 across 4 providers to find the best fit for your use case

Input / 1M

Output / 1M

Cache

Not sourced

Batch

Not sourced

Setup recipe

Python + curl

Install

pip install openai

Auth

export FIREWORKS_API_KEY=...

Call

import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["FIREWORKS_API_KEY"],

Model ID

accounts/fireworks/models/deepseek-v4-flash-0731

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FIREWORKS_API_KEY"],
    base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
    model="accounts/fireworks/models/deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

Use provider model ID "accounts/fireworks/models/deepseek-v4-flash-0731", not the LLMReference slug "deepseek-v4-flash-0731".
Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.

Compare DeepSeek V4 Flash 0731 Across Providers

Provider	Input (per 1M)	Output (per 1M)
OpenRouter	$0.13	$0.39
Vercel AI Gateway	$0.08	$0.15
Together AI	$0.14	$0.28
Fireworks AI	—	—

Capabilities

Reasoning

About DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is the official (post-preview) DeepSeek V4 Flash release, launched on the DeepSeek API in public beta on 2026-07-31 with upgraded agent capabilities. DeepSeek says it keeps the same architecture and size as the April preview. MIT-licensed open weights are on Hugging Face as DeepSeek-V4-Flash-0731.

Get Started

Model Card Docs Portal Pricing

Model Specs

Released2026-07-31

ArchitectureMixture of Experts