Unbiased models

Unbiased builds Pareto, a multimodal composite model for research, coding and agentic workflows. Zeplik carries it with vision, tool calling and a 262K-token window.

Ask a Unbiased model now

All 2 Unbiased models

Pricing at a glance

Frequently asked questions

Which Unbiased models can I use on Zeplik?

Zeplik carries 2 Unbiased models: Pareto 26.10 Preview and Pareto. They all run in the same chat, so you do not need a separate Unbiased account or API key.

How much do Unbiased models cost on Zeplik?

Output tokens run from 38.4 to 90.0 credits per million depending on which Unbiased model you pick (raw provider rates $3.20 to $7.50 per million). 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.

Which Unbiased model has the largest context window?

Pareto 26.10 Preview, at 1.0M tokens (1,048,576). The context window covers the conversation plus any documents you attach.

Do Unbiased models support images and tool calling?

All 2 accept image input, and all of them support tool calling.

Do I need a paid plan to use Unbiased models on Zeplik?

Both need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.

What is the newest Unbiased model on Zeplik?

Pareto 26.10 Preview, released October 2026. Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Other providers

• OpenAI (100)
• Qwen (53)
• Google (42)
• Anthropic (29)
• Mistral (26)
• Z.ai (18)
• DeepSeek (15)
• NVIDIA (11)
• All models