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

Cline with a cheaper API: MartLLM as an OpenAI Compatible provider

In Cline’s settings choose API Provider "OpenAI Compatible", enter Base URL https://api.martllm.com/v1 (with /v1) and your MartLLM key, then pick a Model ID from the list. Set the context window under Model Configuration.

Steps

  1. Make a key on your keys page and add credit.
  2. In VS Code, open the Cline panel and click the gear icon.
  3. Set API Provider to OpenAI Compatible.
  4. Fill in:
    • Base URL: https://api.martllm.com/v1
    • OpenAI Compatible API Key: your ull_… key
    • Model ID: pick moonshotai/kimi-k3 from the list. If it is not shown, choose Use custom model ID… and type it.
  5. Open Model Configuration and set Context Window Size and Max Output Tokens to the numbers on the model's page (martllm.com/models). Turn on Supports Images only for models that take pictures.
  6. Close settings and start a task.

Type the /v1. Current Cline versions use the Base URL exactly as entered and no longer add /v1 for you.

Plan and Act on different models

Cline can use one model to plan and another to act. A strong model for Plan (moonshotai/kimi-k3) and a cheap one for Act (deepseek/deepseek-v4.1-flash) cuts the bill on long tasks, since acting is where most tokens go. Set it under Cline's Plan/Act settings, using the same provider for both.

Prices in Cline's cost counter

Model Configuration has Input Price / 1M tokens and Output Price / 1M tokens. Cline only uses them to show a cost estimate per task. Copy them from the table below if you want that estimate close; your real charge is always in Dashboard → Activity.

Troubleshooting

  • Model list empty, or every request 404s: the Base URL is missing /v1. It must be exactly https://api.martllm.com/v1.
  • 401: the key is wrong or has a trailing space.
  • The model stops using tools, or Cline says a required parameter is missing: pick a model from the first table; small models drift out of Cline's tool format.
  • Context window exceeded: Cline did not know the model's size. Set Context Window Size in Model Configuration.
  • 402 insufficient credits: add credit on the credits page. For a hard ceiling, set a spend limit on the key.

Keep reading

Models that handle Cline well

Cline drives everything through tool calls, so these all support them. The first is in the steps.

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 →

Cheaper models for Plan mode or small tasks

ModelModel id (paste this)Price now
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
Qwen 3 Coder 480bqwen/qwen3-coder$0.0030 in · $0.0099 out / 1M
DeepSeek V3.2deepseek/deepseek-v3.2$0.0026 in · $0.0038 out / 1M
GPT-OSS 120Bopenai/gpt-oss-120b$0.000069 in · $0.00030 out / 1M
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking$0.0059 in · $0.0248 out / 1M

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

FAQ

What base URL does Cline need for MartLLM?

https://api.martllm.com/v1, typed in full with /v1, under API Provider "OpenAI Compatible". Cline uses the Base URL exactly as entered.

Which MartLLM models work best with Cline?

Models with reliable tool calls and long context, such as the Claude, GLM, Kimi, DeepSeek and Qwen Coder models listed on the guide with their live prices.