Dansk LLM

Models

Muse Glimmer 30B

Meta's open model, built for agents: code, tool calls and tasks over many steps.

Model id
muse-glimmer-30b
Context window65,536 tokens (prompt and answer together)
InputText
OutputText
StreamingYes
Prompt cachingYes, automatic
Tool calling (tools)Yes
Thinking (reasoning_effort)Always on, brief by default
Default samplingtemperature 1.0 and top_p 0.95, as Meta recommends
PriceUnder Oversigt (Overview) on the platform
LicenseApache 2.0 and Meta's usage policy

Meta built Muse Glimmer for agents: writing and fixing code, calling tools and solving tasks over many steps, including when a tool fails along the way. It is trained on more than 100 languages. Put "Svar altid på dansk." in the system message if the answer must be in Danish.

Use the model

curl https://api.danskllm.dk/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DANSKLLM_API_KEY" \
  -d '{
    "model": "muse-glimmer-30b",
    "messages": [
      {"role": "system", "content": "Du er en hjælpsom assistent."},
      {"role": "user", "content": "Forklar kort, hvad en API-nøgle er."}
    ]
  }'

Thinking

Muse Glimmer always thinks before it answers. You choose how much with reasoning_effort. More thinking gives better answers on hard tasks, but the answer takes longer and costs more.

reasoning_effortMeans
Not set, "none" or "low"Brief thinking. Fastest and cheapest. The model cannot switch thinking off entirely.
"medium"Ordinary thinking.
"high"Thorough thinking, the model's highest level. Meta recommends it for code and agent tasks.

Other values get status 400 with param: "reasoning_effort".

curl https://api.danskllm.dk/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DANSKLLM_API_KEY" \
  -d '{
    "model": "muse-glimmer-30b",
    "reasoning_effort": "high",
    "messages": [
      {"role": "user", "content": "Write a Python function that finds duplicates in a list."}
    ]
  }'

What to know about thinking:

  • It comes separately. The answer is in content as always. The thinking is in the reasoning field next to it, and in a stream in delta.reasoning. The field is not part of OpenAI's API, so the SDKs don't have it in their types, but it is in the response.
  • It is paid as output. Thinking counts towards completion_tokens.
  • It counts towards max_tokens. If you set max_tokens low, thinking can use all of it, so content is empty and finish_reason is "length". Set max_tokens high, or leave it unset.
  • It takes time. With "high", thinking can run to several thousand tokens, so it can take a while before the answer starts. Use a stream if a user is waiting for the answer.

Coding agents and other tools

Tools that can use an OpenAI-compatible provider, such as Cline, Continue and opencode, are set up like this:

SettingValue
Base URLhttps://api.danskllm.dk/v1
API keyYour key from the platform, dkllm-...
Modelmuse-glimmer-30b
Context window65536
Reasoning effortlow for quick steps, high for hard tasks

Set the context window in the tool to 65,536. Then the tool shortens the conversation before it gets too long, instead of getting 400 with context_length_exceeded.

Tool calls work as with OpenAI: send tools, and the model answers with tool_calls. Send the result back as a message with role: "tool".

By default an account can have 4 requests running at once. See Limits and fair use if your tool sends more at the same time.

More about parameters and streaming.

On this page