Last refreshed 2026-09-24. Next refresh: weekly.
Why use DeepSeek V4 Pro on Featherless?
Featherless offers DeepSeek V4 Pro with pay-as-you-go pricing at $1.60/1M input tokens. Featherless is a serverless inference provider for a large catalog of third-party open text-generation models (40,000+).
Compare DeepSeek V4 Pro across 6 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport FEATHERLESS_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.featherless.ai/v1",deepseek-ai/DeepSeek-V4-ProRequest example
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)Gotchas
- Use provider model ID "deepseek-ai/DeepSeek-V4-Pro", not the LLMReference slug "deepseek-v4-pro".
- Use exact Featherless catalog id in modelProvider.providerModelId (HF-style org/name). Not interchangeable with LLM Reference slugs.
- The examples expect FEATHERLESS_API_KEY; rename it only if your application config maps the new variable.
Compare DeepSeek V4 Pro Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| DeepSeek Platform | $0.43 | $0.87 |
| Fireworks AI | $1.74 | $3.48 |
| OpenRouter | $0.44 | $0.87 |
| Vercel AI Gateway | $0.43 | $0.87 |
| Novita AI | $1.60 | $3.20 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.60 |
| Output tokens | $3.20 |
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.