DeepSeek V4 Pro Free API Quickstart: curl + Python in Five Minutes | TeamoRouter

Quick Answer

deepseek-v4-pro-free is TeamoRouter's free DeepSeek V4 Pro tier: 200 requests per day, reset daily, OpenAI-compatible endpoint, no payment info required. The only prerequisite for a five-minute start is an API key.

Endpoint : https://api.teamorouter.ai/v1
Model    : deepseek-v4-pro-free
Auth     : Bearer sk-teamo-your-key

Two runnable examples below — swap in your key and go.

Step 1: Get a Key

Register at TeamoRouter and create an API key (starts with sk-teamo-). New accounts automatically get deepseek-v4-pro-free and deepseek-v4-flash-free at 200/day each.

Step 2: Verify with curl

curl https://api.teamorouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $TEAMOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro-free",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence"}]
  }'

You get a standard OpenAI chat.completion (reply in choices[0].message.content). A 200 means endpoint, key, and model ID are all correct.

Step 3: Reuse the OpenAI SDK in Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-teamo-your-key",
    base_url="https://api.teamorouter.ai/v1",
)
r = client.chat.completions.create(
    model="deepseek-v4-pro-free",
    messages=[{"role": "user", "content": "Introduce yourself in one sentence"}],
)
print(r.choices[0].message.content)

Existing OpenAI-SDK code works by pointing base_url at the endpoint — near-zero migration.

Works in Any OpenAI-Compatible Client

deepseek-v4-pro-free is tool-agnostic — anything supporting a custom base URL can use it:

• dsh (DeepSeek Harness): DEEPSEEK_BASE_URL + DEEPSEEK_API_KEY;
• Codex: a TeamoRouter provider in ~/.codex/config.toml (base_url ending in /v1, see the Codex setup guide) + OPENAI_API_KEY;
• OpenCode / Cline / Cherry Studio: add an OpenAI-compatible provider.

See the DeepSeek V4 Pro Integration Guide.

Quota Exhausted: A One-Word Switch

The free quota is 200 requests per account per day, counted by request (one full turn = 1), not tokens. When it runs out, swap the model ID — paid models have no account-level limit:

# free → paid, only the model field changes
r = client.chat.completions.create(
    model="deepseek-v4-pro",   # drop the -free
    messages=[{"role": "user", "content": "continue"}],
)

Paid pricing for deepseek-v4-pro and deepseek-v4-flash: see the pricing page. For the newer V4.1 Flash release, see DeepSeek V4.1 Flash API pricing, peak hours and model ID. You can also top up your TeamoRouter balance with USDT: click Pay with crypto in the top-up dialog and pay with USDT, USDC or ETH from Binance, OKX or any exchange app — no browser wallet needed, and the checkout shows which networks your amount supports (BEP20 works from $5). See how to pay with USDT.

FAQ

How is the free quota counted?

deepseek-v4-pro-free and deepseek-v4-flash-free each give 200/day, per-account, reset daily. See 200 Requests a Day.

Is the free tier the same capability as paid?

Yes — only rate limits differ. deepseek-v4-pro currently resolves to DeepSeek-V4-Pro-0813.

Why am I getting a 404?

The base URL is missing /v1. The OpenAI SDK needs https://api.teamorouter.ai/v1.

Why a 401?

The key was copied incompletely or deleted. Confirm it starts with sk-teamo- and has no whitespace.

Does it support streaming?

Yes — add "stream": true.

Register at TeamoRouter and get free V4 Pro running in five minutes.