Try MiniMax FastH3 from Fastvideo →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
LLM & ChatActive

Qwen / Qwen3.5-9B-heretic

Qwen3.5-9B-heretic

byqwen

A large language model optimized for chat interactions and logical reasoning tasks. Designed for developers and researchers.

ChatLLMReasoningBf16LLM Tool Call
Model ID
Qwen3.5-9B-heretic
Provider
qwen
Updated
1776065766
Qwen3.5-9B-heretic
3
Comments
Average rating : 5 (2 users)
Providerqwen
ModelQwen3.5-9B-heretic
ChatLLMReasoningBf16
wiro playground—qwen/Qwen3.5-9B-heretic
Reset to defaults

Prompt to send to the model.

Sample outputs

No samples yet

Run this model to create outputs and build up samples.

Updated 1776065766

Qwen3.5-9B-heretic LLM

Overview

The Qwen3.5-9B-heretic LLM is a large language model optimized for chat interactions and logical reasoning. It supports various configuration options to tailor its behavior for specific tasks.

What you can build

This model can be used to build conversational agents, question-answering systems, and reasoning-based applications. It's particularly suited for scenarios requiring nuanced understanding and structured responses.

Inputs

  • Prompt: The input text to process.
  • System Prompt: A guiding prompt that shapes the model's behavior.
  • Thinking Mode: Toggle between thinking modes for enhanced reasoning.
  • User ID (Optional): Unique identifier for maintaining chat history.
  • Session ID (Optional): Identifier for managing multiple user sessions.
  • Temperature: Controls randomness of outputs (0.0 to 5.0).
  • Top P: Controls token sampling from the top p percentage (0.0 to 1.0).
  • Top K: Controls token sampling from the top k most likely tokens (0 to 100).
  • Repetition Penalty: Adjusts likelihood of repeating tokens (0.0 to 5.0).
  • Length Penalty: Influences output length (0.0 to 5.0).
  • Max Tokens: Maximum number of tokens to generate (0 to 800000).
  • Min Tokens: Minimum number of tokens to generate (-1 to 2048).
  • Stop Sequences: Delimiters to halt generation.
  • Seed: Random seed for reproducible outputs.
  • Quantization: Enables quantization for reduced memory usage.
  • Do Sample: Enables/disables random sampling.

Outputs

  • Generated text based on provided prompts and configurations.

Recommended settings

For general use, try setting temperature to 0.7, top_p to 0.95, and enable quantization for faster inference. Adjust max_tokens and repetition_penalty based on task requirements.

Limitations

  • Output quality depends on prompt clarity and model configuration.
  • May occasionally produce irrelevant or nonsensical content without proper guidance.

Safety & compliance

The model enforces ethical guidelines and safety measures to prevent harmful, illegal, or unethical content. It is designed to be respectful and honest in its responses.

API quick start

Run Qwen3.5-9B-heretic with a single API call.

POST https://api.wiro.ai/v1/Run/Qwen/Qwen3.5-9B-heretic
{
  "prompt": "Explain the Second Law of Thermodynamics …",
  "user_id": "...",
  "session_id": "...",
  "enableThinking": "true"
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion