Create Chat Completion
Generates a model response for the given conversation. This endpoint is fully compatible with the OpenAI Chat Completions API.
Authorizations
API key from your Subconscious dashboard
Body
The model to use for completion.
subconscious/tim-qwen3.6-27b "subconscious/tim-qwen3.6-27b"
The conversation history. Each message has a role and content.
[
{
"role": "user",
"content": "What is the capital of France?"
}
]If true, responses are streamed as Server-Sent Events. Each event is a ChatCompletionChunk object. The stream ends with data: [DONE].
Maximum number of tokens to generate in the response.
An alternative to max_tokens. Maximum number of tokens to generate.
Sampling temperature between 0 and 2. Lower values make output more focused and deterministic, while higher values make it more creative.
0 <= x <= 2Nucleus sampling parameter. Only considers tokens whose cumulative probability exceeds this threshold.
0 <= x <= 1Penalizes tokens based on their frequency in the text so far.
-2 <= x <= 2Penalizes tokens based on whether they appear in the text so far.
-2 <= x <= 2Up to 4 sequences where the model will stop generating.
Constrains the response format. Use {"type": "json_object"} for valid JSON or {"type": "json_schema", "json_schema": {...}} for schema-constrained output.
Options for streaming responses.
Subconscious extension. Controls model-specific features like thinking mode.
Response
Successful completion
A unique identifier for the completion.
"chatcmpl-abc123"
The object type.
chat.completion Unix timestamp of when the completion was created.
1716000000
The model used for the completion.
"subconscious/tim-qwen3.6-27b"