NOUMENOpen app
NOUMEN

Every model.One place.

Explore the models available through Noumen. Compare capabilities, context windows, and reference pricing, then see which models people use most and how they score on public benchmarks.

Just landed

Recently added

The newest models available through Noumen, ready to use in the app and the API.

Provider
Capability
Sort
5 models
  • Solar Mini 4upstageCapabilities: Tools, Structured outputContext524.3KInput / 1M$0.05Output / 1M$0.2Show model details

    Upstage's compact 35B-parameter mixture-of-experts model with 3B active parameters and a 524K context window. Built for fast, cost-efficient agentic tasks, with strong Korean and English support.

    Model ID
    upstage/solar-mini4
    Discovery tier
    Efficient
    Context window
    524,288 tokens
    Benchmarks, speed and comparisons
  • Solar Mini 4 ThinkingupstageCapabilities: Reasoning, Tools, Structured outputContext524.3KInput / 1M$0.05Output / 1M$0.2Show model details

    Solar Mini 4 with reasoning enabled for agentic tasks and harder analysis across a 524K-token context window.

    Model ID
    upstage/solar-mini4:thinking
    Discovery tier
    Efficient
    Context window
    524,288 tokens
    Benchmarks, speed and comparisons
  • Solar Pro 4upstageCapabilities: Tools, Structured outputContext524.3KInput / 1M$0.03Output / 1M$0.12Show model details

    Upstage's Solar Pro 4 is a long-context language model for agentic workflows, office productivity, document-intensive work, and coding. This variant keeps reasoning disabled for faster direct responses.

    Model ID
    upstage/solar-pro4
    Discovery tier
    Efficient
    Context window
    524,288 tokens
    Benchmarks, speed and comparisons
  • Solar Pro 4 ThinkingupstageCapabilities: Reasoning, Tools, Structured outputContext524.3KInput / 1M$0.03Output / 1M$0.12Show model details

    Upstage's Solar Pro 4 with reasoning enabled for harder agentic workflows, document-intensive work, coding, planning, and analysis across a 524K-token context window.

    Model ID
    upstage/solar-pro4:thinking
    Discovery tier
    Efficient
    Context window
    524,288 tokens
    Benchmarks, speed and comparisons
  • Solar Pro 3upstageCapabilities: Text generationContext131.1KInput / 1M$0.15Output / 1M$0.6Show model details

    Upstage's Solar Pro 3 is a Mixture-of-Experts (MoE) language model with 102B total parameters and 12B active parameters per forward pass, optimized for Korean with strong English and Japanese support.

    Model ID
    upstage/solar-pro-3
    Discovery tier
    Efficient
    Context window
    131,072 tokens
    Benchmarks, speed and comparisons

Reference pricing in USD per 1M tokens, as published by model providers. Discovery tiers describe model metadata, rather than benchmark rankings.