AionLabs: Aion-RP 1.0 (8B)
/v1/chat/completionsAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.
Request body
Parameters supported by this model. Values, defaults, and limits are read from the model registry.
Model identifier. Set to aion-labs/aion-rp-llama-3.1-8b.
Default: aion-labs/aion-rp-llama-3.1-8b
Conversation messages in system, user, or assistant order.
Maximum number of tokens the model may generate in the response.
Range: −∞ to 32768
Sampling temperature. Lower values are more deterministic; higher values are more creative.
Range: 0 to 2
Default: 1
Nucleus sampling threshold. Use this or temperature, but usually not both.
Range: 0 to 1
When true, returns incremental Server-Sent Events instead of one completed response.
Default: false
Response Schema
Fields returned by this model API response.
Generated completion choices.
Unique chat completion identifier.
Model that generated the response.
Token usage when available.
Model capabilities
Capabilities declared by the model registry.
Default: chat
Maximum context window accepted by this model.
Default: 32768 tokens
Execution mode declared by the model registry.
Default: sync

