Configuration field reference 

Configurations define use-case presets with model selection and parameters.

Configuration list with model assignments

Configuration list showing linked model, use-case type, and parameters.

Required 

identifier (config)

identifier (config)
Type
string
Required

true

Unique slug (e.g., blog-summarizer).

name (config)

name (config)
Type
string
Required

true

Display name (e.g., Blog Post Summarizer).

model

model
Type
reference
Required

true

Reference to the model to use.

system_prompt

system_prompt
Type
text
Required

true

System message that sets the AI's behavior.

Optional 

temperature

temperature
Type
float
Default
0.7

Creativity (0.0 = deterministic, 2.0 = creative).

max_tokens (config)

max_tokens (config)
Type
integer
Default
(model default)

Maximum response length in tokens.

top_p

top_p
Type
float
Default
1.0

Nucleus sampling (0.0-1.0).

frequency_penalty

frequency_penalty
Type
float
Default
0.0

Reduces word repetition (-2.0 to 2.0).

presence_penalty

presence_penalty
Type
float
Default
0.0

Encourages topic diversity (-2.0 to 2.0).

use_case_type

use_case_type
Type
string
Default
chat

Task type: chat, completion, embedding, translation.

fallback_chain

fallback_chain
Type
JSON (text column)
Default
(empty)

JSON object with a single key, configurationIdentifiers, whose value is the ordered list of other configuration identifiers to retry against when the primary fails with a retryable error (connection error, HTTP 5xx, or HTTP 429 rate-limit). Non-retryable errors bubble up unchanged. Streaming requests do not trigger fallback — chunks cannot be replayed against a different provider.

Example payload:

{"configurationIdentifiers": ["claude-sonnet", "ollama-local"]}
Copied!

Identifiers are matched case-insensitively; leave empty to disable fallback. See Fallback chain.