OpenRouter Chat Model

Access multiple LLM providers through OpenRouter's unified API

Written By Philippe

Last updated 2 days ago

OpenRouter Chat Model

⚠️ Limitations β€” Works with known restrictions, see details below

| Auth | OpenRouter API key via Secure Vault |

Compatibility

FeatureStatus
No streaming support on the platformNot supported
No vision/image inputNot supported β€” Text-only prompts
No tool/function callingNot supported β€” Not available in current implementation

Response caching

Add responseCacheTtlSeconds to the node's options in your workflow JSON to enable OpenRouter response caching:

"options": { "responseCacheTtlSeconds": 300 }

When set, identical repeated requests within the TTL window (1–86400 seconds) return OpenRouter's cached response. Cache hits consume no tokens, so repeated runs of the same prompt cost nothing in API charges.

This option is specific to indie.money β€” workflows imported from elsewhere simply run without caching, and the extra key is ignored by other tools.

Status

This integration works on indie.money with known limitations. See the details above for specifics.