--- title: Hermes Agent x Qwen guide | RunAPI description: Use Qwen with Hermes Agent through RunAPI. Compare current model IDs, endpoints, and prices, then follow the matching configuration workflow. url: https://runapi.ai/hermes-qwen.md canonical: https://runapi.ai/hermes-qwen locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/hermes-qwen zh-CN: https://runapi.ai/zh-CN/hermes-qwen es: https://runapi.ai/es/hermes-qwen ja: https://runapi.ai/ja/hermes-qwen de: https://runapi.ai/de/hermes-qwen fr: https://runapi.ai/fr/hermes-qwen pt-BR: https://runapi.ai/pt-BR/hermes-qwen ko: https://runapi.ai/ko/hermes-qwen it: https://runapi.ai/it/hermes-qwen nl: https://runapi.ai/nl/hermes-qwen pl: https://runapi.ai/pl/hermes-qwen tr: https://runapi.ai/tr/hermes-qwen zh-TW: https://runapi.ai/zh-TW/hermes-qwen zh-HK: https://runapi.ai/zh-HK/hermes-qwen ar: https://runapi.ai/ar/hermes-qwen x-default: https://runapi.ai/hermes-qwen model_line: qwen --- > HTML version: https://runapi.ai/hermes-qwen > Site index for agents: https://runapi.ai/llms.txt [Hermes Agent](https://runapi.ai/hermes-agent.md) / [Qwen](https://runapi.ai/models/qwen.md) # Hermes Agent x Qwen Qwen language models from Alibaba are open-weight Mixture-of-Experts and dense LLMs with 131K to 256K context. Most of them accept image input and offer a thinking mode. Through RunAPI they share one API key and per-token billing, and any OpenAI SDK can call them at https://runapi.ai/v1. These are Qwen's language models, separate from the Qwen Image, Qwen 2, and Qwen 3 image generation models. - [Get API Key](https://runapi.ai/login) - [View Hermes Agent Docs](https://runapi.ai/docs/guides) 6 variants · from $0.25 / 1M tokens · Commercial OK ## Prompt Prerequisite: `npx runapi mcp install` ```text You have access to RunAPI chat models for Qwen. Available Qwen models: - qwen3.5-122b-a10b: Open-weight Qwen3.5 vision MoE (10B active); 256K context; OpenAI-compatible API chat endpoints: /v1/chat/completions - qwen3.5-27b: Dense open-weight Qwen3.5 vision model; 256K context, hybrid thinking; OpenAI-compatible API chat endpoints: /v1/chat/completions - qwen3.5-35b-a3b: Small open-weight Qwen3.5 vision MoE (3B active); 256K context; OpenAI-compatible API chat endpoints: /v1/chat/completions - qwen3.5-397b-a17b: Flagship open-weight Qwen3.5 vision MoE (17B active); 256K context; OpenAI-compatible API chat endpoints: /v1/chat/completions - qwen3.6-27b: Dense open-weight Qwen3.6 vision model for agentic coding; 256K context; OpenAI-compatible API chat endpoints: /v1/chat/completions - qwen3.6-35b-a3b: First open-weight Qwen3.6 model, a vision MoE with 3B active; 256K context; OpenAI-compatible API chat endpoints: /v1/chat/completions Use the model ID and chat endpoint that match the user's request. Example request: Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it. Verify the active model with: hermes model;hermes doctor ``` ## Prompt models Use RunAPI with Qwen through this guide. Available Qwen models: - `qwen3.5-122b-a10b`: Open-weight Qwen3.5 vision MoE (10B active); 256K context; OpenAI-compatible API - `qwen3.5-27b`: Dense open-weight Qwen3.5 vision model; 256K context, hybrid thinking; OpenAI-compatible API - `qwen3.5-35b-a3b`: Small open-weight Qwen3.5 vision MoE (3B active); 256K context; OpenAI-compatible API - `qwen3.5-397b-a17b`: Flagship open-weight Qwen3.5 vision MoE (17B active); 256K context; OpenAI-compatible API - `qwen3.6-27b`: Dense open-weight Qwen3.6 vision model for agentic coding; 256K context; OpenAI-compatible API - `qwen3.6-35b-a3b`: First open-weight Qwen3.6 model, a vision MoE with 3B active; 256K context; OpenAI-compatible API Use qwen3.5-122b-a10b when it matches the task: Open-weight Qwen3.5 vision MoE (10B active); 256K context; OpenAI-compatible API. ## Public Versions and Endpoints | Model ID | Version | Endpoints | Price | | --- | --- | --- | --- | | `qwen3.5-122b-a10b` | Open-weight Qwen3.5 vision MoE (10B active); 256K context; OpenAI-compatible API | /v1/chat/completions | $0.40 / 1M tokens | | `qwen3.5-27b` | Dense open-weight Qwen3.5 vision model; 256K context, hybrid thinking; OpenAI-compatible API | /v1/chat/completions | $0.30 / 1M tokens | | `qwen3.5-35b-a3b` | Small open-weight Qwen3.5 vision MoE (3B active); 256K context; OpenAI-compatible API | /v1/chat/completions | $0.25 / 1M tokens | | `qwen3.5-397b-a17b` | Flagship open-weight Qwen3.5 vision MoE (17B active); 256K context; OpenAI-compatible API | /v1/chat/completions | $0.60 / 1M tokens | | `qwen3.6-27b` | Dense open-weight Qwen3.6 vision model for agentic coding; 256K context; OpenAI-compatible API | /v1/chat/completions | $0.60 / 1M tokens | | `qwen3.6-35b-a3b` | First open-weight Qwen3.6 model, a vision MoE with 3B active; 256K context; OpenAI-compatible API | /v1/chat/completions | $0.38 / 1M tokens | ## Verify Poll until the task reaches a terminal status ``` hermes model hermes doctor ``` ## Configuration Use `runapi/` with OpenClaw, or configure the RunAPI custom endpoint and select `` with Hermes Agent. `/v1/chat/completions` ``` providers: runapi: api: "https://runapi.ai/v1" key_env: RUNAPI_API_KEY transport: chat_completions default_model: model: provider: custom:runapi default: ``` ## Get Started in 3 Steps 1. **Choose a model ID.** Select a public catalog model ID and review its endpoint and current starting price. 2. **Configure RunAPI.** Add the provider configuration for this agent. 3. **Verify the result.** Run the agent status and model-selection commands shown below. ## What to Build with Hermes Agent + Qwen **Agent coding and reasoning** Let your agent plan, write, and review code or work through multi-step problems with the model's reasoning. **Long document analysis and extraction** Summarize reports, contracts, or codebases and pull structured fields out of long documents. **Tool-calling workflows** Connect the model to functions and APIs so your agent can look up data and take actions between replies. ## Why Use Qwen Through RunAPI + Hermes Agent **6 variants, one API key** Use one RunAPI connection to choose among the live model variants without changing your integration. **Clear usage pricing** See current catalog pricing before you send a request, with no subscription or minimum spend required. **Direct responses** Synchronous calls return the result in the same response, so your agent can use it immediately without task polling. ## Hermes Agent + Qwen Questions ### Which Qwen model should I start with? Start with qwen3.6-27b or qwen3.6-35b-a3b, the newest Qwen models on RunAPI, for chat, coding, and image input. Use qwen3.5-397b-a17b when you want the largest Qwen3.5 model, and qwen3-coder-next for coding agents that do not need a thinking step. ### Which Qwen models accept images? All Qwen3.5 and Qwen3.6 models and both Qwen3-VL-235B-A22B versions accept images. Send them as image_url parts in a Chat Completions request. qwen3-coder-next is text-only. ### How does thinking work on Qwen models? The Qwen3.5 and Qwen3.6 models are hybrid and have thinking and non-thinking modes. qwen3-vl-235b-a22b-thinking always thinks, while qwen3-vl-235b-a22b-instruct and qwen3-coder-next answer without a thinking step. ### Which API do I use to call Qwen on RunAPI? Use the OpenAI-compatible Chat Completions endpoint at https://runapi.ai/v1/chat/completions with your RunAPI API key and a Qwen model ID. Any OpenAI SDK works after you change the base URL. ### Are the Qwen language models open-weight? Yes. Alibaba releases these Qwen models with open weights under the Apache 2.0 license. RunAPI gives you API access, so you do not have to host them on your own GPUs. ### How is the Qwen line different from Qwen Image? The Qwen line holds the language models, which read text and images and return text. Qwen Image, Qwen 2, and Qwen 3 are separate RunAPI lines that generate and edit images. ### Which model ID should I use? Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version. ### Does this guide configure a chat model? Yes. This Model Line supports a client-facing LLM protocol. ## More Hermes Agent Guides - [Hermes Agent x Claude](https://runapi.ai/hermes-claude.md) - Anthropic · Text · from $0.06 / 1M tokens - [Hermes Agent x DeepSeek](https://runapi.ai/hermes-deepseek.md) - DeepSeek · Text · from $0.30 / 1M tokens - [Hermes Agent x ElevenLabs](https://runapi.ai/hermes-elevenlabs.md) - ElevenLabs · Audio & Music · from $0.04 / minute - [Hermes Agent x Embedding](https://runapi.ai/hermes-embedding.md) - OpenAI · Text · from $0.02 / 1M tokens ## Start using Qwen with Hermes Agent - [Get API Key](https://runapi.ai/login) - [Read Quickstart](https://runapi.ai/docs/guides) ## Building with a team? We're here to help with enterprise setup, integrations, and technical questions. [Contact Us](https://runapi.ai/contact.md) --- ## More from RunAPI - [Home](https://runapi.ai/.md) ### Product - [Model Catalog](https://runapi.ai/models.md) - [Pricing](https://runapi.ai/pricing.md) - [Providers](https://runapi.ai/models#all-models) ### Developers - [Documentation](https://runapi.ai/docs/guides) - [SDKs](https://runapi.ai/sdk.md) - [CLI](https://runapi.ai/cli.md) - [MCP Server](https://runapi.ai/mcp.md) - [x402](https://runapi.ai/x402.md) ### Guides - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Cursor API Setup](https://runapi.ai/cursor-api-setup.md) - [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md) ### Company - [Enterprise](https://runapi.ai/contact.md) - [Contact](https://runapi.ai/contact.md) ### Legal - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "Hermes Agent x Qwen", "applicationCategory": "DeveloperApplication", "description": "Use Qwen with Hermes Agent through RunAPI. Compare current model IDs, endpoints, and prices, then follow the matching configuration workflow.", "url": "https://runapi.ai/hermes-qwen" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "Which Qwen model should I start with?", "acceptedAnswer": { "@type": "Answer", "text": "Start with qwen3.6-27b or qwen3.6-35b-a3b, the newest Qwen models on RunAPI, for chat, coding, and image input. Use qwen3.5-397b-a17b when you want the largest Qwen3.5 model, and qwen3-coder-next for coding agents that do not need a thinking step." } }, { "@type": "Question", "name": "Which Qwen models accept images?", "acceptedAnswer": { "@type": "Answer", "text": "All Qwen3.5 and Qwen3.6 models and both Qwen3-VL-235B-A22B versions accept images. Send them as image_url parts in a Chat Completions request. qwen3-coder-next is text-only." } }, { "@type": "Question", "name": "How does thinking work on Qwen models?", "acceptedAnswer": { "@type": "Answer", "text": "The Qwen3.5 and Qwen3.6 models are hybrid and have thinking and non-thinking modes. qwen3-vl-235b-a22b-thinking always thinks, while qwen3-vl-235b-a22b-instruct and qwen3-coder-next answer without a thinking step." } }, { "@type": "Question", "name": "Which API do I use to call Qwen on RunAPI?", "acceptedAnswer": { "@type": "Answer", "text": "Use the OpenAI-compatible Chat Completions endpoint at https://runapi.ai/v1/chat/completions with your RunAPI API key and a Qwen model ID. Any OpenAI SDK works after you change the base URL." } }, { "@type": "Question", "name": "Are the Qwen language models open-weight?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Alibaba releases these Qwen models with open weights under the Apache 2.0 license. RunAPI gives you API access, so you do not have to host them on your own GPUs." } }, { "@type": "Question", "name": "How is the Qwen line different from Qwen Image?", "acceptedAnswer": { "@type": "Answer", "text": "The Qwen line holds the language models, which read text and images and return text. Qwen Image, Qwen 2, and Qwen 3 are separate RunAPI lines that generate and edit images." } }, { "@type": "Question", "name": "Which model ID should I use?", "acceptedAnswer": { "@type": "Answer", "text": "Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version." } }, { "@type": "Question", "name": "Does this guide configure a chat model?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. This Model Line supports a client-facing LLM protocol." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "Use Qwen with Hermes Agent", "step": [ { "@type": "HowToStep", "position": 1, "name": "Choose a model ID", "text": "Select a public catalog model ID and review its endpoint and current starting price.", "url": "https://runapi.ai/hermes-qwen#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Configure RunAPI", "text": "Add the provider configuration for this agent.", "url": "https://runapi.ai/hermes-qwen#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Verify the result", "text": "Run the agent status and model-selection commands shown below.", "url": "https://runapi.ai/hermes-qwen#how-step-3" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "Hermes Agent", "item": "https://runapi.ai/hermes-agent" }, { "@type": "ListItem", "position": 3, "name": "Qwen", "item": "https://runapi.ai/hermes-qwen" } ] } ] ```