Deepseek v4 Pro API
Run deepseek/deepseek-v4-pro through FastInfra's OpenAI-compatible API.
Pay per token, no subscription, routed to the cheapest available provider.
Deepseek v4 Pro pricing
Billed per token used. Prices sync automatically from wholesale providers.
| Direction | Price per 1M tokens |
|---|---|
| Input | $1.23 |
| Output | $2.45 |
Served by 5 providers
Requests route to OpenRouter by default (cheapest).
Pin a specific provider with the :provider suffix.
| Provider | Upstream model ID |
|---|---|
| openrouter | deepseek/deepseek-v4-pro |
| fireworks | accounts/fireworks/models/deepseek-v4-pro |
| together | deepseek-ai/DeepSeek-V4-Pro |
| deepinfra | deepseek-ai/DeepSeek-V4-Pro |
| siliconflow | deepseek-ai/DeepSeek-V4-Pro |
Call Deepseek v4 Pro in 30 seconds
Works with any OpenAI SDK — change the base URL and API key only.
Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")
response = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl
curl https://api.fastinfra.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'Deepseek v4 Pro — common questions
How much does the deepseek/deepseek-v4-pro API cost?
On FastInfra, deepseek/deepseek-v4-pro costs $1.2264/1M input, $2.4528/1M output tokens. Billing is per token used, with no subscription.
Is deepseek/deepseek-v4-pro compatible with the OpenAI SDK?
Yes. FastInfra exposes deepseek/deepseek-v4-pro through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.
Which providers serve deepseek/deepseek-v4-pro?
deepseek/deepseek-v4-pro is available from 5 provider(s): openrouter, fireworks, together, deepinfra, siliconflow. Requests route to OpenRouter by default (cheapest); append ":provider" to the model ID to pin one.
Related models
Compare side by side: Deepseek v4 Pro vs Deepseek Coder:1.3b · Deepseek v4 Pro vs Deepseek v4 Flash 0731 · Deepseek v4 Pro vs Deepseek v4 Flash