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
35 models
  • Claude Sonnet 5.5AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$2Output / 1M$10Show model details

    Claude Sonnet 5.5 handles everyday coding, tool-based workflows, visual analysis, and polished writing with a 1M-token context window. This version skips up-front thinking and can reason between tool calls for faster responses; use Thinking for deeper planning and complex problems.

    Model ID
    anthropic/claude-sonnet-5.5
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Sonnet 5.5 ThinkingAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$2Output / 1M$10Show model details

    Claude Sonnet 5.5 with adaptive thinking for complex coding, multi-step tool use, visual analysis, and detailed planning. Supports a 1M-token context window and five reasoning effort levels, with stronger thinking available when a task needs it.

    Model ID
    anthropic/claude-sonnet-5.5:thinking
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Opus 5.5AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$4Output / 1M$20Show model details

    Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.

    Model ID
    anthropic/claude-opus-5.5
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Fable 5.1AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$10Output / 1M$50Show model details

    Claude Fable 5.1 improves on Fable 5 across agentic coding, long-running workflows, front-end and visual code generation, finance, analysis, and knowledge work, with more concise plans and summaries. Anthropic retains prompts and outputs for 30 days; Zero Data Retention is not available.

    Model ID
    anthropic/claude-fable-5.1
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Opus 5AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Claude Opus 5 is Anthropic's flagship model for advanced coding, long-running agentic tasks, research, and complex knowledge work.

    Model ID
    anthropic/claude-opus-5
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Sonnet 5AnthropicCapabilities: Tools, Vision, Structured output, PDF inputContext1MInput / 1M$2Output / 1M$10Show model details

    Claude Sonnet 5 supports coding, agentic workflows, long-context reasoning, computer use, and practical knowledge work.

    Model ID
    anthropic/claude-sonnet-5
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Sonnet 5 ThinkingAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$2Output / 1M$10Show model details

    Claude Sonnet 5 with adaptive thinking enabled for complex coding, planning, and agentic work.

    Model ID
    anthropic/claude-sonnet-5:thinking
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Fable 5AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$10Output / 1M$50Show model details

    Anthropic Claude Fable 5 for long-running coding, research, and knowledge-work tasks. Anthropic retains prompts and outputs for 30 days under its Covered Models policy; Zero Data Retention is not available.

    Model ID
    anthropic/claude-fable-5
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Fable LatestAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$10Output / 1M$50Show model details

    Compatibility alias for Claude Fable 5.1. Anthropic retains prompts and outputs for 30 days under its Covered Models policy; Zero Data Retention is not available.

    Model ID
    anthropic/claude-fable-latest
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Opus 4.8AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Anthropic Claude Opus 4.8 with text, image, and file inputs and a 1M-token context window.

    Model ID
    anthropic/claude-opus-4.8
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Opus 4.8 ThinkingAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Anthropic Claude Opus 4.8 with thinking enabled.

    Model ID
    anthropic/claude-opus-4.8:thinking
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude 4.7 OpusAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Claude Opus 4.7 is a major upgrade for advanced software engineering, long-running complex tasks, and high-resolution vision understanding.

    Model ID
    anthropic/claude-opus-4.7
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude 4.7 Opus ThinkingAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Claude Opus 4.7 with thinking enabled (default budget: 16k tokens).

    Model ID
    anthropic/claude-opus-4.7:thinking
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Opus LatestAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$4Output / 1M$20Show model details

    Compatibility alias that routes to the newest version of Claude Opus. Currently routes to Claude Opus 5.5.

    Model ID
    anthropic/claude-opus-latest
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Sonnet LatestAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$2Output / 1M$10Show model details

    Compatibility alias that routes to the newest version of Claude Sonnet. Currently routes to Claude Sonnet 5.5 Thinking.

    Model ID
    anthropic/claude-sonnet-latest
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Sonnet 4.6AnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$3Output / 1M$15Show model details

    Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long-context reasoning, agent planning, and design. Supports up to a 1M-token context window at Sonnet pricing.

    Model ID
    anthropic/claude-sonnet-4.6
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude Sonnet 4.6 ThinkingAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$3Output / 1M$15Show model details

    Claude Sonnet 4.6 with extended thinking enabled for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows and complex problem solving.

    Model ID
    anthropic/claude-sonnet-4.6:thinking
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude 4.6 OpusAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Claude Opus 4.6 supports advanced coding, agentic workflows, and long-context analysis with up to a 1M-token context window.

    Model ID
    anthropic/claude-opus-4.6
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude 4.6 Opus ThinkingAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Claude Opus 4.6 with adaptive thinking enabled (default effort: high).

    Model ID
    anthropic/claude-opus-4.6:thinking
    Discovery tier
    Frontier
    Context window
    1,000,000 tokens
    Benchmarks, speed and comparisons
  • Claude 4.6 Opus Thinking LowAnthropicCapabilities: Reasoning, Tools, Vision, Structured output, PDF inputContext1MInput / 1M$5Output / 1M$25Show model details

    Claude Opus 4.6 with adaptive thinking (effort: low).

    Model ID
    anthropic/claude-opus-4.6:thinking:low
    Discovery tier
    Frontier
    Context window
    1,000,000 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.