Quick Answer
deepseek-v4-pro-free is not available. TeamoRouter has no model with that ID; a request that uses it is rejected with "Model 'deepseek-v4-pro-free' is not available" before it reaches any model.
| What you want | Model ID | Details |
|---|---|---|
| DeepSeek V4 Pro | deepseek-v4-pro (paid) |
Model page |
| Lower-priced DeepSeek tier (still billed) | deepseek-v4-flash-free (V4 Flash) |
Model page |
| Paid V4 Flash | deepseek-v4-flash |
Pricing page |
If you followed an older guide that said deepseek-v4-pro-free, change only the model field. The endpoint (https://api.agentapiai.com/v1) and your key stay the same.
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.
Switch the model ID
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": "hello"}]}'
For the lower-priced V4 Flash tier (still billed), use "model": "deepseek-v4-flash-free". We sent both requests to the gateway on November 2, 2026. More examples, including Python: DeepSeek V4 Pro API quickstart.
How agent loops use requests
Whatever model you pick, an agent such as DeepSeek Harness, Codex or OpenCode makes one model request per step: the model asks to read a file, the tool returns it, the model asks for the next step, and so on. A multi-file refactor can take 10 to 15 requests, and each request resends the conversation so far. That matters both for the -free tier's daily request cap and for token costs: give the agent a clear task with the files it needs, and stop it when it starts going in circles.
Price
DeepSeek's official price for V4 Pro is $1.32 per million input tokens and $3.96 per million output tokens at peak, half that off-peak (DeepSeek pricing, November 2, 2026). TeamoRouter's current prices are on the pricing page. There's no subscription; top up from $5 by card or with USDT, USDC or ETH (how to pay with USDT).
FAQ
Was there ever a free V4 Pro?
Older TeamoRouter guides described a deepseek-v4-pro-free model. It isn't in the model catalog now, and requests with that ID fail. The lower-priced DeepSeek tier is V4 Flash (deepseek-v4-flash-free), and it's billed too, just at a lower rate.
Where do I find details on the lower-priced tier?
On the deepseek-v4-flash-free model page.
Is deepseek-v4-flash-free the same model as deepseek-v4-flash?
It routes to the same V4 Flash model; the difference is how it's billed.