DeepSeek V3.2 API
deepseek/deepseek-v3.2
Call DeepSeek V3.2 through UberLLM’s OpenAI-compatible API — from $0.0600/M input and $0.0900/M output, routed automatically to the cheapest healthy provider. deepseek · 163,840 token context. No inference markup.
DeepSeek V3.2 pricing & providers
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| Surplus Intelligencebest | $0.0600 | $0.0900 |
| OpenRouter | $0.2690 | $0.4000 |
How to use DeepSeek V3.2 with the OpenAI SDK
Already using OpenAI or OpenRouter? Change one line — the base URL — and call DeepSeek V3.2 with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1",
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v3.2",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)DeepSeek V3.2 API — FAQ
How much does the DeepSeek V3.2 API cost?
DeepSeek V3.2 costs from $0.0600 per million input tokens and $0.0900 per million output tokens through UberLLM, which routes to the cheapest healthy provider. There is no inference markup.
How do I call DeepSeek V3.2 via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "deepseek/deepseek-v3.2". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is DeepSeek V3.2 OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including DeepSeek V3.2 — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.