Quick Answer
deepseek-v4-pro-free is not available. TeamoRouter has no model with that ID, so requests that use it are rejected with "Model 'deepseek-v4-pro-free' is not available". Use these instead:
- DeepSeek V4 Pro is the paid model
deepseek-v4-pro(model page). - The lower-priced tier is V4 Flash:
deepseek-v4-flash-free(still billed). Details are on its model page.
Endpoint : https://api.agentapiai.com/v1
Model : deepseek-v4-pro (or deepseek-v4-flash-free)
Auth : Bearer sk-teamo-your-key
New accounts start with a $0 balance — top up before your first request. Top up from $5. If a request returns 402 (400 on the OpenAI format) with "wallet balance is insufficient", your balance is empty — your base URL and key are fine. Top up and retry.
Step 1: Get a Key
Create an API key in the TeamoRouter console. It starts with sk-teamo-.
Step 2: Verify with curl
curl https://api.agentapiai.com/v1/chat/completions \
-H "Authorization: Bearer $TEAMOROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Introduce yourself in one sentence"}]
}'
The response is a standard OpenAI chat.completion, with the reply in choices[0].message.content. For the lower-priced V4 Flash tier (still billed), change model to deepseek-v4-flash-free.
Step 3: Reuse the OpenAI SDK in Python
from openai import OpenAI
client = OpenAI(
api_key="sk-teamo-your-key",
base_url="https://api.agentapiai.com/v1",
)
r = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Introduce yourself in one sentence"}],
)
print(r.choices[0].message.content)
Existing OpenAI-SDK code only needs the new base_url and key. We sent both examples, with deepseek-v4-pro and deepseek-v4-flash-free, to the gateway on November 2, 2026.
Works in Any OpenAI-Compatible Client
Anything that accepts a custom base URL can use these models:
- DeepSeek Harness (dsh): add TeamoRouter as a provider in
~/.dsh/settings.yaml(setup); - Codex: a TeamoRouter provider in
~/.codex/config.toml(Codex setup guide); - OpenCode / Cline / Cherry Studio: add an OpenAI-compatible provider.
See the DeepSeek V4 Pro Integration Guide.
Price
DeepSeek's official price for V4 Pro (deepseek-v4-pro) is $1.32 per million input tokens and $3.96 per million output tokens at peak, half that off-peak, per DeepSeek's pricing page on November 2, 2026. TeamoRouter's current prices are on the pricing page. For the newer V4.1 Flash, see DeepSeek V4.1 Flash API pricing, peak hours and model ID.
TeamoRouter bills per token from a prepaid balance with no subscription; top up from $5 by card or with USDT, USDC or ETH (how to pay with USDT).
FAQ
Is there a free DeepSeek V4 Pro?
Not on TeamoRouter. The lower-priced DeepSeek tier is V4 Flash, deepseek-v4-flash-free. It's billed at a lower rate, not free; details are on its model page. V4 Pro is the paid deepseek-v4-pro.
I get "Model 'deepseek-v4-pro-free' is not available". What now?
Change the model ID to deepseek-v4-pro (paid) or deepseek-v4-flash-free (lower-priced V4 Flash tier, still billed). Nothing else in your setup needs to change.
Why am I getting a 404?
The base URL is missing /v1. The OpenAI SDK needs https://api.agentapiai.com/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.