DeepSeek V3.2 API
Run DeepSeek-V3.2 through FastInfra's OpenAI-compatible API.
Pay per token, no subscription, routed to the cheapest available provider.
DeepSeek V3.2 pricing
Billed per token used. Prices sync automatically from wholesale providers.
| Direction | Price per 1M tokens |
|---|---|
| Input | $0.27 |
| Output | $0.40 |
Served by 4 providers
Requests route to DeepInfra by default (cheapest).
Pin a specific provider with the :provider suffix.
| Provider | Upstream model ID |
|---|---|
| openrouter | deepseek/deepseek-v3.2 |
| deepinfra | deepseek-ai/DeepSeek-V3.2 |
| sambanova | DeepSeek-V3.2 |
| siliconflow | deepseek-ai/DeepSeek-V3.2 |
Call DeepSeek V3.2 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-V3.2",
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-V3.2",
"messages": [{"role": "user", "content": "Hello!"}]
}'
DeepSeek V3.2 — common questions
How much does the DeepSeek-V3.2 API cost?
On FastInfra, DeepSeek-V3.2 costs $0.273/1M input, $0.399/1M output tokens. Billing is per token used, with no subscription.
Is DeepSeek-V3.2 compatible with the OpenAI SDK?
Yes. FastInfra exposes DeepSeek-V3.2 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-V3.2?
DeepSeek-V3.2 is available from 4 provider(s): openrouter, deepinfra, sambanova, siliconflow. Requests route to DeepInfra by default (cheapest); append ":provider" to the model ID to pin one.
Related models
Compare side by side: DeepSeek V3.2 vs Deepseek Coder:1.3b · DeepSeek V3.2 vs Deepseek v4 Flash 0731 · DeepSeek V3.2 vs Deepseek v4 Flash