Pareto 26.10 Preview

Pareto

Pareto is an experimental multimodal composite model from Unbiased AI for research, coding, agentic workflows, and general-purpose tasks. It runs several frontier and open models for each request and returns a single selected or synthesized answer. This experimental release supports text and image input, tool calling, a 262K-token context window, and up to 131K output tokens. Its underlying model mix and behavior may change as it is evaluated. Request content may be retained for abuse prevention and security monitoring for up to 30 days, and is not used for model training without explicit consent.

Decider 0.8B FP8

Mapika's Decider, quantized and hosted by LLM Tech, answers typed Choice, Score and Noul questions about application state. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It returns probabilities and decisions without generating text; only input tokens are billed.

Decider 2B FP8

Mapika's Decider, quantized and hosted by LLM Tech, answers typed Choice, Score and Noul questions about application state. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It returns probabilities and decisions without generating text; only input tokens are billed.

Decider 4B NVFP4

Mapika's Decider, quantized and hosted by LLM Tech, answers typed Choice, Score and Noul questions about application state. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It returns probabilities and decisions without generating text; only input tokens are billed.

Ling 3.1 Flash

Ling 3.1 Flash is inclusionAI's hybrid reasoning model for coding, tool use, planning, and long-context agent workflows. It has 560B total parameters with 25B active parameters per token. Thinking is enabled by default and can be turned off in settings.

GPT 6.1 Sol

GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It supports text and image input, tool calling, structured outputs, and reasoning from low through max.