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
4 models
  • Step 5 PreviewstepfunCapabilities: Reasoning, Tools, Vision, Structured output, Video input, Parallel toolsContext1MInput / 1M$1Output / 1M$2.7Show model details

    Step 5 Preview is StepFun's 600B sparse MoE frontier model for production-scale agents, activating 27B parameters per token. It is built for software engineering, long-horizon tool use, research, professional knowledge work, and finance, with native text, image, and video understanding and a 1M-token context window. ⚠️ Note: This model routes through StepFun, so privacy and logging guarantees may be limited.

    Model ID
    stepfun/step-5-preview
    Discovery tier
    Balanced
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Step 3.7 Flash ThinkingstepfunCapabilities: Reasoning, Tools, Vision, Structured output, Video inputContext262.1KInput / 1M$0.2Output / 1M$1.15Show model details

    Step 3.7 Flash Thinking is StepFun's high-efficiency multimodal MoE model with visible reasoning enabled for deeper agentic coding, long-context reasoning, tool use, and native image/video understanding. ⚠️ Note: This model routes through StepFun, so privacy and logging guarantees may be limited.

    Model ID
    stepfun/step-3.7-flash:thinking
    Discovery tier
    Open weights
    Context window
    262,144 tokens
    Benchmarks, speed and comparisons
  • Step 3.5 Flash 2603stepfunCapabilities: ReasoningContext262.1KInput / 1M$0.1Output / 1M$0.3Show model details

    Step 3.5 Flash 2603 is optimized for high-frequency agentic and coding workflows with improved token efficiency and faster reasoning. NOTE: This model runs via StepFun, which may log and train on your prompts.

    Model ID
    stepfun-ai/step-3.5-flash-2603
    Discovery tier
    Open weights
    Context window
    262,144 tokens
    Benchmarks, speed and comparisons
  • Step 3.5 FlashstepfunCapabilities: ReasoningContext262.1KInput / 1M$0.1Output / 1M$0.3Show model details

    StepFun's most capable open-source reasoning model with visible reasoning traces. Built on a sparse Mixture-of-Experts architecture with 196B total parameters and only 11B active per token, it achieves frontier-level performance in math, logic, and agentic coding while reaching up to 350 tokens/sec. Supports 256K context. NOTE: This model runs via StepFun, which may log and train on your prompts.

    Model ID
    stepfun-ai/step-3.5-flash
    Discovery tier
    Open weights
    Context window
    262,144 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.