NewHow we catch a seller listing the wrong model, and refund you if one does.

Chatbox with MartLLM: one-click import or 1-minute manual setup

Open the one-click chatbox:// import link on this page with Chatbox installed, or add a provider by hand (API Mode "OpenAI API Compatible", API Host https://api.martllm.com/v1); paste your MartLLM key, press Fetch to load models, and start chatting.

One-click import

With Chatbox installed on this device, open:

Add MartLLM to Chatbox

Chatbox asks you to confirm, then adds MartLLM with three models. The link carries no key: open Settings → Model Provider → MartLLM, paste your key from the keys page, and press Check.

If nothing happens when you click, your browser did not hand the link to Chatbox. Use the manual steps.

Manual steps

  1. Make a key on your keys page and add credit.
  2. In Chatbox open Settings → Model Provider and click Add.
  3. Name: MartLLM. API Mode: OpenAI API Compatible. Confirm.
  4. On the new provider's page:
    • API Key: your ull_… key
    • API Host: https://api.martllm.com/v1
    • API Path: leave empty (Chatbox uses /chat/completions) The Preview line should read https://api.martllm.com/v1/chat/completions.
  5. Press Check, then Fetch to load the model list, and keep the models you want (for example deepseek/deepseek-v4.1-flash).
  6. Start a new chat and choose a MartLLM model at the bottom.

Keep API Mode on OpenAI API Compatible (chat completions): that is the setup tested here.

Troubleshooting

  • Check fails with 401: the key is wrong or has a space.
  • 404: the Preview line is not https://api.martllm.com/v1/chat/completions. Clear API Path and set API Host again.
  • Fetch shows nothing: save the key first, then Fetch. You can also add a model by hand with New and the id from the table below.
  • "No such model": the id needs its maker in front, such as deepseek/deepseek-v4.1-flash.
  • 402 insufficient credits: add credit on the credits page.

Keep reading

Models for everyday chat

The import link adds the first three; Fetch loads the rest.

ModelModel id (paste this)Price now
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash$0.0075 in · $0.0282 out / 1M
Gemini 3.5 Flashgoogle/gemini-3.5-flash$0.0075 in · $0.0450 out / 1M
Claude Sonnet 5.5anthropic/claude-sonnet-5.5$0.3600 in · $1.80 out / 1M
GPT-5.5openai/gpt-5.5$1.25 in · $7.50 out / 1M
Kimi K3moonshotai/kimi-k3$0.0384 in · $0.2021 out / 1M
GLM 5.3z-ai/glm-5.3$0.0029 in · $0.0100 out / 1M
Gemma 3 27Bgoogle/gemma-3-27b-it$0.00079 in · $0.0020 out / 1M
Qwen3 VL 235B A22Bqwen/qwen3-vl-235b-a22b-instruct$0.0021 in · $0.0188 out / 1M

Prices at the last hourly build, no fee added · every model →

FAQ

How do I add MartLLM to Chatbox?

Use the one-click import link on this page, or Settings → Model Provider → Add: API Mode OpenAI API Compatible, API Host https://api.martllm.com/v1, your MartLLM key, then Fetch models.

Does the Chatbox import link contain my API key?

No. It adds the provider and three models; you paste your key in Chatbox afterwards.