Using DeepSeek V4 Pro on Featherless

Quick Start

1. 1
   Create an account at Featherless and generate an API key.
2. 2
   Use the Featherless SDK or REST API to call deepseek-ai/DeepSeek-V4-Pro — see the documentation for request format.
3. 3
   You'll be billed $1.60/1M input, $3.20/1M output tokens. See full pricing.

Code Examples

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.featherless.ai/v1",
    api_key=os.environ["FEATHERLESS_API_KEY"],
)
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Pricing on Featherless

Capabilities

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.