DEEPSEEK_V4.1

DeepSeek setup

Create a DeepSeek key to use DeepSeek V4.1 Flash: 1M context, thinking mode, tool calling and image input. Both OpenAI Chat Completions and Codex Responses are supported.

The model id in requests must be exactly deepseek-v4.1-flash; any other id returns a 400.

Weekdays 09:00–12:00 and 14:00–18:00 (Taipei time) are busy hours and deduct twice the off-peak credits; all other hours and weekends are off-peak. A request that starts or ends inside busy hours counts as busy. See the pricing page for the actual rates.

Model IDs

Copy these model IDs into config files, API request bodies, or any OpenAI-compatible client that asks for a model name. Each group needs the matching key type.

DeepSeekNeeds a DeepSeek key

BEFORE YOU START

Prepare your API key

1. Open the API key page

After signing in, open the API key page to create or copy a key. It looks like sk-or-v1-xxxxxxxxxxxx. Treat it like a password.

Create API key

3. Confirm the Base URL

https://api.bruceai.net/v1

Use https://api.bruceai.net/v1; /v1/models, /v1/chat/completions and /v1/responses are supported.

2. Create a key for the provider you want

Click Create API key, give it a name you will recognize, then pick the key type by the models you plan to call:

OpenAI key: Serves gpt-6-astra, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna and gpt-5.5. Works with Codex, GitHub Copilot and any OpenAI-compatible client.
Grok key: Serves grok-4.6 and grok-4.5. Works with Grok Build, Codex and any OpenAI-compatible client.
DeepSeek key: Serves deepseek-v4.1-flash: 1M context, thinking mode, tool calling and image input. Works with Codex and any OpenAI-compatible client.

A key only serves its own provider's models. Sending a GPT model id with a Grok key, or a Grok id with an OpenAI key, is refused with a 400. Create one key per provider if you use several.

Do not share your API key with anyone, and do not commit it to GitHub, GitLab, or any public repository.

Choose your system first

The commands below switch to the system you choose.

STEP 01

Create a DeepSeek key

This key serves deepseek-v4.1-flash only; it cannot call GPT or Grok models. Create separate keys for other providers.

STEP 02

Check the model list

macOS / Linux

bash

curl https://api.bruceai.net/v1/models \
  -H "Authorization: Bearer sk-or-v1-your-key"

The returned model id should be deepseek-v4.1-flash.

STEP 03

Send a Chat Completions request

macOS / Linux

bash

curl -N https://api.bruceai.net/v1/chat/completions \
  -H "Authorization: Bearer sk-or-v1-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4.1-flash","messages":[{"role":"user","content":"hi"}],"stream":true}'

STEP 04

OpenAI SDK examples

Python

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-or-v1-your-key",
    base_url="https://api.bruceai.net/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "hi"}],
)
print(response.choices[0].message.content)

Node.js

typescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-or-v1-your-key",
  baseURL: "https://api.bruceai.net/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [{ role: "user", content: "hi" }],
});
console.log(response.choices[0].message.content);

STEP 05

Use it in Codex

Keep the DeepSeek config in its own CODEX_HOME so it neither touches your ~/.codex nor mixes with your OpenAI key setup. Create the folder and config.toml first:

If you would rather not edit files by hand, use the one-click import on the CC Switch page in the sidebar to add the DeepSeek key to CC Switch and switch there.

New to nano? Follow these steps to edit, save, and exit

1Edit: after running the nano command in the previous step, paste the entire code block below into the editor. Use Command+V in macOS Terminal; on Linux, use Ctrl+Shift+V or right-click and select Paste. Do not use Ctrl+V because nano treats it as Page Down.
2Make changes: move the cursor with the arrow keys, then remove text with Backspace or Delete. Replace any placeholder that says your key with your own API key, keeping the existing quotes and brackets.
3Save: hold Control and press the letter O (Ctrl+O, not the number 0). When “File Name to Write” appears at the bottom, leave the filename unchanged and press Enter.
4Exit: after nano returns to the editor, press Ctrl+X to return to the terminal. If “Save modified buffer?” appears, the changes are not saved yet; press Y, then Enter to save and exit.

macOS / Linux

bash

mkdir -p ~/.codex-bruceai-deepseek
nano ~/.codex-bruceai-deepseek/config.toml

toml

model_provider = "DeepSeek"
model = "deepseek-v4.1-flash"
disable_response_storage = true

[model_providers.DeepSeek]
name = "DeepSeek"
base_url = "https://api.bruceai.net/v1"
wire_api = "responses"
requires_openai_auth = true

STEP 06

Write auth.json and start

Create ~/.codex-bruceai-deepseek/auth.json, paste your DeepSeek key, then start Codex.

macOS / Linux

bash

nano ~/.codex-bruceai-deepseek/auth.json
# paste: { "OPENAI_API_KEY": "sk-or-v1-your-key" }

CODEX_HOME="$HOME/.codex-bruceai-deepseek" codex --model deepseek-v4.1-flash

Standard Responses requests are supported. If Codex's remote compaction fails with a 502, start a new conversation or disable remote_compaction_v2 and restart.

STEP 07

Troubleshooting

400 / unsupported_model: the model id must be deepseek-v4.1-flash, not DeepSeek-V4.1-Flash, deepseek-chat or another name.

401 / invalid token: make sure the key is complete, has no extra spaces, starts with sk-or-v1- and is a DeepSeek key.

404: make sure the Base URL includes /v1 and call /chat/completions, /responses or /models.