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

Continue (VS Code / JetBrains) with MartLLM: config.yaml that works

In ~/.continue/config.yaml add a model with provider: openai, apiBase: https://api.martllm.com/v1, your key from a .env secret, and useLegacyCompletionsEndpoint: false so autocomplete goes to chat completions (plus useResponsesApi: false to keep GPT-5 models on chat completions too).

Fastest: one command

npx uberllm init --tool continue

It makes a key in your browser, saves it to ~/.continue/.env and adds two MartLLM models to ~/.continue/config.yaml, keeping the models you already have. The file is backed up first, and npx uberllm init --undo puts it back. What it changes. To do it by hand, follow the steps below.

Steps

  1. Make a key on your keys page and add credit.
  2. Save the key where Continue looks for secrets, in ~/.continue/.env:
ULL_API_KEY=ull_your_key

The editor extensions do not see variables from your shell, so use this file (or .continue/.env in the project).

  1. Open ~/.continue/config.yaml and add the models:
name: My Config
version: 1.0.0
schema: v1

models:
  - name: moonshotai/kimi-k3 (MartLLM)
    provider: openai
    model: moonshotai/kimi-k3
    apiBase: https://api.martllm.com/v1
    apiKey: ${{ secrets.ULL_API_KEY }}
    useResponsesApi: false
    useLegacyCompletionsEndpoint: false
    capabilities: [tool_use]
    roles: [chat, edit, apply]

  - name: deepseek/deepseek-v4.1-flash (MartLLM)
    provider: openai
    model: deepseek/deepseek-v4.1-flash
    apiBase: https://api.martllm.com/v1
    apiKey: ${{ secrets.ULL_API_KEY }}
    useResponsesApi: false
    useLegacyCompletionsEndpoint: false
    capabilities: [tool_use]
    roles: [chat, edit, apply]
  1. Reload the window and pick the model in Continue's model menu.

The two route lines

Continue picks a route per model, and these two lines keep every MartLLM model on chat completions:

  • useLegacyCompletionsEndpoint: false: autocomplete otherwise uses the old /v1/completions route, which MartLLM does not serve (404). This one is required.
  • useResponsesApi: false: Continue sends any model whose name contains gpt-5 (or o1, o3…) to the Responses API, even with a custom apiBase. MartLLM serves that route too, so this line is no longer needed to avoid errors; it keeps all your models on the one route the config was tested on.

Autocomplete

Add a separate fast model with the autocomplete role:

  - name: Autocomplete (MartLLM)
    provider: openai
    model: deepseek/deepseek-v4.1-flash
    apiBase: https://api.martllm.com/v1
    apiKey: ${{ secrets.ULL_API_KEY }}
    useResponsesApi: false
    useLegacyCompletionsEndpoint: false
    roles: [autocomplete]

Autocomplete through a chat model works, but quality varies by model more than with chat. Try two or three from the fast table below. It sends many small requests, so keep an eye on Dashboard → Activity the first day.

Troubleshooting

  • 404 on chat: apiBase does not end in /v1.
  • 404 on autocomplete only: useLegacyCompletionsEndpoint: false is missing.
  • 401: the secret is not found. Check the name matches (ULL_API_KEY) and the .env file is in one of the places above, then reload the window.
  • Agent mode does nothing: add capabilities: [tool_use].
  • 402 insufficient credits: add credit on the credits page.

Keep reading

Chat, edit and agent models

Tool calls supported. The first two are in the config below.

ModelModel id (paste this)Price now
Kimi K3moonshotai/kimi-k3$0.0384 in · $0.2021 out / 1M
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash$0.0075 in · $0.0282 out / 1M
GLM 5.3z-ai/glm-5.3$0.0029 in · $0.0100 out / 1M
Claude Sonnet 5.5anthropic/claude-sonnet-5.5$0.3600 in · $1.80 out / 1M
Qwen 3 Coder 480bqwen/qwen3-coder$0.0030 in · $0.0099 out / 1M
GPT-5.5openai/gpt-5.5$1.25 in · $7.50 out / 1M
Claude Opus 5.5anthropic/claude-opus-5.5$0.6780 in · $3.39 out / 1M
DeepSeek V4 Prodeepseek/deepseek-v4-pro$0.0634 in · $0.1268 out / 1M
MiniMax M3minimax/minimax-m3$0.0230 in · $0.0920 out / 1M

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

Fast, cheap models for autocomplete

Autocomplete fires on every pause in typing, so price per call matters most.

ModelModel id (paste this)Price now
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash$0.0075 in · $0.0282 out / 1M
Qwen 3 Coder 480bqwen/qwen3-coder$0.0030 in · $0.0099 out / 1M
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite$0.0013 in · $0.0075 out / 1M
Mistral Small 3.2 24B Instructmistralai/mistral-small-3.2-24b-instruct$0.0130 in · $0.0360 out / 1M
GPT-OSS 120Bopenai/gpt-oss-120b$0.000069 in · $0.00030 out / 1M

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

FAQ

How do I use MartLLM in Continue?

Add a model to config.yaml with provider: openai, apiBase: https://api.martllm.com/v1, apiKey from a .env secret, and useLegacyCompletionsEndpoint: false (useResponsesApi: false keeps GPT-5 models on chat completions too).

Why does Continue autocomplete give 404 with MartLLM?

Continue uses the legacy /v1/completions route for autocomplete unless the model sets useLegacyCompletionsEndpoint: false. MartLLM serves chat completions only.