Skip to main content

​
What it’s good for

Widest model selection available — access Claude, GPT-4, Llama, Mistral, and hundreds more through one API key. Good for trying different models without managing separate accounts, or for accessing models not directly supported by Spaceduck’s other providers.

​
Requirements

​
Configure in Spaceduck

​
Chat

1

Set your API key

In Settings > Chat, select OpenRouter as the provider, then enter your API key.Or via CLI:
spaceduck config secret set /ai/secrets/openrouterApiKey
2

Select a model

In Settings > Chat:
  • Provider: OpenRouter
  • Model: use the OpenRouter model ID, e.g.:
    • anthropic/claude-3.5-sonnet
    • meta-llama/llama-3.1-70b-instruct
    • mistralai/mistral-large-latest
Or via CLI:
spaceduck config set /ai/provider openrouter
spaceduck config set /ai/model "anthropic/claude-3.5-sonnet"
Browse available models and pricing at openrouter.ai/models.
3

Verify

Send a message in the chat. You should see a streaming response.

​
Embeddings

OpenRouter does not provide an embeddings API. If you want semantic recall, pair OpenRouter with a separate embedding provider: This is the two-server pattern — chat on OpenRouter, embeddings elsewhere.

​
Test and troubleshoot

ProblemCauseFix
401 UnauthorizedInvalid API keyCheck your key at openrouter.ai/keys
402 Payment RequiredInsufficient creditsAdd credits at openrouter.ai/credits
Model not foundWrong model ID formatUse the full org/model-name format from OpenRouter’s model list
429 Too Many RequestsRate limit hitWait and retry, or use a different model