LLM Reference
Fireworks AI

Using DeepSeek V4 Pro on Fireworks AI

Implementation guide · DeepSeek V4 · DeepSeek

ServerlessOpen Source

Fireworks AI exposes DeepSeek V4 Pro through model ID deepseek-v4-pro. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-24. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Fireworks AI and generate an API key.
  2. 2
    Use the Fireworks AI SDK or REST API to call deepseek-v4-pro — see the documentation for request format.
  3. 3
    You'll be billed $1.74/1M input, $3.48/1M output tokens. See full pricing.

Code Examples

Install
pip install openai
API key
FIREWORKS_API_KEY
Model ID
deepseek-v4-pro

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".

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="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Fireworks AI

TypePrice (per 1M)
Input tokens$1.74
Output tokens$3.48

Capabilities

ReasoningJSON / Tool useStructured OutputsPrompt Caching

About DeepSeek V4 Pro

DeepSeek V4 Pro is DeepSeek's flagship open-weights model, released April 24 2026 under the MIT license. Architecture: 1.6T total / 49B active parameters, MoE with Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA) hybrid — requiring only 27% of inference FLOPs vs standard 1M-context transformers — plus Manifold-Constrained Hyper-Connections (mHC) and Muon Optimizer. Context window: 1,000,000 tokens; max output: 384,000 tokens (Think Max mode requires >=384K context). Text-only (no vision/image input). Supports three reasoning modes: Non-Think, Think High, Think Max. Function calling, tool use, and structured outputs supported.

Model Specs

Released2026-04-24
Parameters1.6T
Context1m
ArchitectureMixture of Experts

Provider

Fireworks AI
Fireworks AI

San Mateo, California, United States