Completion
LLM completion request and response.
chatchatStreamlistModelsembeddingsSchema
| Field | Type | Notes |
|---|---|---|
| model* | string | Model identifier (e.g., 'gpt-4', 'claude-3'). |
| messages* | json | Array of message objects (role, content). |
| temperature | number | Sampling temperature (0.0-2.0). |
| max_tokens | integer | Maximum tokens to generate. |
| top_p | number | Nucleus sampling parameter. |
| frequency_penalty | number | Penalize frequent tokens. |
| presence_penalty | number | Penalize already-present tokens. |
| stop | json | Stop sequences. |
| stream | boolean | Whether to stream responses. |
API
Loading manifest…