Skip to content
  1. Status
  2. Announcements
  3. Docs
  4. Support
  5. About
  6. Partners
  7. Enterprise
  8. Careers
  9. Pricing
  10. Privacy
  11. Terms
  12.  
    13. © 2025 OpenRouter, Inc
    Favicon for Clarifai

    Clarifai

    Browse models provided by Clarifai (Terms of Service)

    3 models

    Tokens processed on OpenRouter

    • Arcee AI: Trinity MiniTrinity Mini

      Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.

      by arcee-ai131K context$0.045/M input tokens$0.15/M output tokens
    OpenAI: gpt-oss-120bgpt-oss-120b

    gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

    by openai131K context$0.09/M input tokens$0.36/M output tokens
  13. OpenAI: gpt-oss-20bgpt-oss-20b

    gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

    by openai131K context$0.045/M input tokens$0.18/M output tokens