Integrations
Updated
Any tool that accepts a custom OpenAI base URL works with BroadNet Inference. Set the base URL to https://inference.broadnet.ai/v1, use your BroadNet API key, and pick a model ID such as broadnet/deepseek-v4.1-flash, broadnet/glm-5.3, broadnet/qwen3.8-27b or broadnet/gemma-4-26b-a4b. The guides below give the exact settings for each tool.

| Setting | Value |
|---|---|
| Base URL | https://inference.broadnet.ai/v1 |
| API key | Your BroadNet key (from the console) |
| Model ID | broadnet/deepseek-v4.1-flash, broadnet/glm-5.3, broadnet/qwen3.8-27b, broadnet/gemma-4-26b-a4b |
Tool guides
- Run Aider on unlimited DeepSeek V4.1 Flash
Aider connects to any OpenAI-compatible API. Set OPENAI_API_BASE to https://inference.broadnet.ai/v1 and OPENAI_API_KEY to your BroadNet key, then run aider --model openai/broadnet/deepseek-v4.1-flash. The openai/ prefix selects Aider's OpenAI-compatible route. On an unlimited plan key, DeepSeek V4.1 Flash tokens are not metered, so long repository sessions stay at a flat price.
- Use LangChain with BroadNet Inference
Install langchain-openai and create ChatOpenAI with base_url set to https://inference.broadnet.ai/v1, api_key set to your BroadNet key, and a BroadNet model ID such as broadnet/glm-5.3. Invoke, stream and tool-calling chains then run over chat completions. Avoid Responses-only features, and leave max_tokens room for reasoning.
- Use Cline with BroadNet Inference (OpenAI Compatible provider)
In Cline settings, set API Provider to OpenAI Compatible, Base URL to https://inference.broadnet.ai/v1, API Key to your BroadNet key, and Model to a BroadNet ID such as broadnet/glm-5.3 or broadnet/deepseek-v4.1-flash. Then set the context window under Model Configuration so Cline knows how much it can send.
- Use Roo Code with BroadNet Inference (OpenAI Compatible)
Roo Code was shut down on 15 May 2026, so new setups should use Cline or the community fork Zoo Code. In existing installs, set API Provider to OpenAI Compatible, Base URL to https://inference.broadnet.ai/v1, API Key to your BroadNet key, and Model to broadnet/glm-5.3. Roo Code needs native tool calling, so pick a model with tools.
- Use Continue with BroadNet Inference (config.yaml and apiBase)
In ~/.continue/config.yaml, add a model with provider openai, model set to a BroadNet ID such as broadnet/glm-5.3, apiBase set to https://inference.broadnet.ai/v1 and apiKey set to your BroadNet key. Add capabilities tool_use for Agent mode and set contextLength and maxTokens under defaultCompletionOptions.
- Add BroadNet Inference to opencode as a custom provider
In opencode.jsonc, add a broadnet entry under providers with package @opencode/ai/providers/openai-compatible, settings.baseURL set to https://inference.broadnet.ai/v1 and env set to BROADNET_API_KEY. Map short model keys to BroadNet IDs with modelID, such as broadnet/glm-5.3, then pick the model with /models. Older V1 configs using npm @ai-sdk/openai-compatible and options.baseURL still work.
- Connect Open WebUI to BroadNet Inference
In Open WebUI, go to Settings > Connections in the admin section, click Add Connection under Manage OpenAI API Connections, set URL to https://inference.broadnet.ai/v1 and API Key to your BroadNet key, then add model IDs such as broadnet/glm-5.3 to the Model IDs allowlist and save.
- Add BroadNet Inference to LibreChat as a custom endpoint
In librechat.yaml, add an entry under endpoints.custom with name BroadNet, apiKey set to an environment reference such as BROADNET_API_KEY, baseURL https://inference.broadnet.ai/v1, and models.default listing BroadNet IDs like broadnet/glm-5.3. Put the key in .env, mount the file into the container on Docker, and restart LibreChat. LibreChat adds /chat/completions to the base URL itself.
- Use BroadNet Inference in n8n (OpenAI credential, Base URL)
In n8n, create an OpenAI credential with your BroadNet key as API Key and Base URL set to https://inference.broadnet.ai/v1. In the OpenAI Chat Model node, switch Model from From List to ID, enter a BroadNet ID such as broadnet/glm-5.3, and turn off Use Responses API so n8n calls chat completions.
- Use the Vercel AI SDK with BroadNet Inference
Install ai and @ai-sdk/openai-compatible, then call createOpenAICompatible with name broadnet, baseURL https://inference.broadnet.ai/v1 and your BroadNet key as apiKey. Pass a BroadNet model ID such as broadnet/glm-5.3 to the provider, and use generateText or streamText as usual. Keep the key on the server, and give reasoning models a generous maxOutputTokens.
- Route LiteLLM to BroadNet Inference (SDK and proxy)
In LiteLLM, prefix the BroadNet model ID with openai/, as in openai/broadnet/glm-5.3, and set api_base to https://inference.broadnet.ai/v1 with your BroadNet key as api_key. In the proxy, put the same values under litellm_params in config.yaml and give the model a short model_name.
- Run the OpenAI Agents SDK on BroadNet Inference
Create an AsyncOpenAI client with base_url https://inference.broadnet.ai/v1 and your BroadNet key, wrap it in OpenAIChatCompletionsModel with a model ID such as broadnet/glm-5.3, and pass that model to your Agent. Call set_tracing_disabled(True) unless you have a separate OpenAI key for tracing.
- Transcribe WhatsApp voice notes in n8n
Use eight n8n nodes: a WhatsApp Trigger on Messages, an If node that keeps audio, WhatsApp Download for the media URL, an HTTP Request that fetches the .ogg file, Read/Write Files to save it, ffmpeg in Execute Command to make WAV, Read/Write Files to load the WAV, and an HTTP Request to /v1/audio/transcriptions. It needs self-hosted n8n with ffmpeg.
- Use Zed with BroadNet Inference as an OpenAI-compatible provider
In Zed's settings.json, add a provider under language_models.openai_compatible, for example broadnet, with api_url set to https://inference.broadnet.ai/v1 and available_models listing BroadNet IDs such as broadnet/glm-5.3 with max_tokens set to the context size. Zed reads the key from BROADNET_API_KEY, or you can save it in Agent Settings.
- Use Kilo Code with BroadNet Inference (OpenAI Compatible provider)
In Kilo Code, open Settings, go to Providers and click Custom provider. Choose Provider API OpenAI Compatible, set Base URL to https://inference.broadnet.ai/v1, paste your BroadNet key, and add a model ID such as broadnet/glm-5.3 by hand. In kilo.json, use npm @ai-sdk/openai-compatible with options.baseURL and set limit.context and limit.output.
- Add BroadNet Inference to goose as a custom provider
In goose, add a custom provider with type OpenAI Compatible, API URL https://inference.broadnet.ai/v1/chat/completions, your BroadNet key and available models such as broadnet/glm-5.3. Use goose Desktop's Add Custom Provider button, goose configure in the terminal, or a JSON file in ~/.config/goose/custom_providers/. goose relies on tool calling, so start with GLM 5.3 or Qwen3.8 27B.
- Use Pydantic AI with BroadNet Inference (OpenAICompatibleProvider)
Install pydantic-ai-slim[openai], then build OpenAIChatModel with a BroadNet model ID such as broadnet/glm-5.3 and an OpenAICompatibleProvider whose base URL is https://inference.broadnet.ai/v1 and whose API key is your BroadNet key. Pass the model to Agent. Use OpenAIChatModel, not the Responses model, because BroadNet serves chat completions. Pydantic AI's docs say OpenAIProvider with base_url is meant for OpenAI itself.
- Use CrewAI with BroadNet Inference as a custom OpenAI endpoint
Create the model with crewai's LLM class, passing model set to a BroadNet ID such as broadnet/glm-5.3, custom_openai=True, base_url set to https://inference.broadnet.ai/v1 and api_key set to your BroadNet key. Then give that LLM to each Agent. CrewAI uses its native OpenAI client and chat completions, so no LiteLLM install is needed.
- Use LlamaIndex with BroadNet Inference through OpenAILike
Install llama-index-llms-openai-like and create OpenAILike with model set to a BroadNet ID such as broadnet/glm-5.3, api_base set to https://inference.broadnet.ai/v1, your BroadNet key, context_window set to the model's real context, is_chat_model=True, and is_function_calling_model=True only for GLM 5.3 or Qwen3.8 27B. Set it as Settings.llm to use it everywhere.
- Add BroadNet Inference to Dify with the OpenAI-API-compatible plugin
In Dify, install the OpenAI-API-compatible plugin from Integrations, Model Provider, then click Add Model. Choose type LLM, enter a BroadNet model ID such as broadnet/glm-5.3, your BroadNet key and API Base URL https://inference.broadnet.ai/v1. Set Completion mode to Chat, the real context size, an output limit with room for reasoning, and Tool Call only for GLM 5.3 or Qwen3.8 27B.
- Use Jan with BroadNet Inference as a custom OpenAI-compatible provider
In Jan, open Settings, Model Providers and click Add Provider. Choose OpenAI-compatible, name it BroadNet, set Base URL to https://inference.broadnet.ai/v1 and paste your BroadNet key. Then add chat models by hand with the + button, for example broadnet/glm-5.3, and turn on Tools or vision for each model under its capabilities.
- Connect SillyTavern to BroadNet Inference (Custom OpenAI-compatible)
In SillyTavern's API Connections panel, choose Chat Completion, then Custom (OpenAI-compatible) as the Chat Completion Source. Set Custom Endpoint to https://inference.broadnet.ai/v1, paste your BroadNet key, type a model ID such as broadnet/qwen3.8-27b in Enter a Model ID, click Connect, then Test Message. Set Max Response Length to 1,000 tokens or more.
- Use Spring AI with BroadNet Inference (OpenAI base-url)
Add spring-ai-starter-model-openai, then set spring.ai.openai.base-url to https://inference.broadnet.ai/v1, spring.ai.openai.api-key to your BroadNet key and spring.ai.openai.chat.model to a BroadNet ID such as broadnet/glm-5.3. Set spring.ai.openai.chat.max-tokens with room for reasoning. Spring AI 2.x uses the openai-java SDK, which appends /chat/completions to the base URL.
- Call BroadNet Inference from Go with the openai-go SDK
Install github.com/openai/openai-go/v3 and create the client with option.WithBaseURL("https://inference.broadnet.ai/v1") and option.WithAPIKey set to your BroadNet key. Call client.Chat.Completions.New with a BroadNet model ID such as broadnet/glm-5.3 as a plain string. Use chat completions, not the Responses API, and set MaxTokens with room for reasoning.
- Build LangGraph agents on BroadNet Inference
Install langgraph and langchain-openai, then create ChatOpenAI with model set to a BroadNet ID such as broadnet/glm-5.3, base_url set to https://inference.broadnet.ai/v1 and api_key set to your BroadNet key. Bind your tools to it and use it in a StateGraph node, or pass it to langchain's create_agent. Use GLM 5.3 or Qwen3.8 27B, the models BroadNet lists with tools.
- Use Haystack pipelines and agents with BroadNet Inference
Install haystack-ai and create OpenAIChatGenerator with api_base_url set to https://inference.broadnet.ai/v1, api_key set to a Secret read from BROADNET_API_KEY, and model set to a BroadNet ID such as broadnet/glm-5.3. Use it in pipelines or a Haystack Agent. Pass max_tokens in generation_kwargs, and use GLM 5.3 or Qwen3.8 27B when the generator has tools.
- Use Semantic Kernel with BroadNet Inference
In Python, create AsyncOpenAI with base_url https://inference.broadnet.ai/v1 and your BroadNet key, then pass it as async_client to OpenAIChatCompletion with ai_model_id set to a BroadNet ID such as broadnet/glm-5.3. In C#, call AddOpenAIChatCompletion with an endpoint Uri, which Microsoft marks experimental (SKEXP0010). Use GLM 5.3 or Qwen3.8 27B for plugins.
- Use Mastra agents with BroadNet Inference
In a Mastra Agent, set model to an object with url https://inference.broadnet.ai/v1, apiKey from BROADNET_API_KEY and id broadnet/broadnet/glm-5.3. Mastra treats the first part of the id as a provider name and strips it, so the doubled prefix sends broadnet/glm-5.3 to BroadNet. Custom URLs use chat completions by default. Use GLM 5.3 or Qwen3.8 27B for tools.
- Get structured output with Instructor on BroadNet Inference
Wrap an OpenAI client that has base_url https://inference.broadnet.ai/v1 and your BroadNet key with instructor.from_openai, then call chat.completions.create with response_model set to your Pydantic class and model set to broadnet/glm-5.3 or broadnet/qwen3.8-27b. Those are the two models BroadNet lists with tools and structured output. Mode.TOOLS is the default; Mode.JSON_SCHEMA also works.
- Use DSPy with BroadNet Inference (set model_type="chat")
Create dspy.LM with the model "openai/broadnet/glm-5.3", model_type="chat", api_base set to https://inference.broadnet.ai/v1 and your BroadNet api_key, then pass it to dspy.configure. The model_type="chat" part matters. DSPy 3.5 defaults OpenAI-prefixed models to the Responses API, which BroadNet doesn't serve. In our mock-server test, leaving it out sent the call to /v1/responses, which got a 404, and BroadNet's live endpoint also answers that path with a 404.
- Evaluate BroadNet models with promptfoo
In promptfooconfig.yaml, add a provider with id openai:chat:broadnet/glm-5.3 and a config that sets apiBaseUrl to https://inference.broadnet.ai/v1 and apiKeyEnvar to BROADNET_API_KEY. Use the openai:chat prefix so promptfoo always calls Chat Completions, the endpoint BroadNet serves. Set max_tokens yourself, since promptfoo's default output limit is 1,024 tokens.
- Run smolagents on BroadNet Inference with OpenAIModel
Create smolagents' OpenAIModel with model_id set to a BroadNet ID such as broadnet/glm-5.3, api_base set to https://inference.broadnet.ai/v1 and api_key set to your BroadNet key, then pass it to CodeAgent or ToolCallingAgent. CodeAgent writes Python instead of native tool calls, so it can run on DeepSeek V4.1 Flash. ToolCallingAgent needs GLM 5.3 or Qwen3.8 27B.
- Connect Flowise to BroadNet Inference (OpenAI Custom Model)
In a Flowise chatflow, add the OpenAI Custom Model chat model node. Connect an OpenAI API credential that holds your BroadNet key, type a BroadNet model ID such as broadnet/glm-5.3 in Model Name, and under Additional Parameters set Base Path to https://inference.broadnet.ai/v1. The node uses chat completions. Pick GLM 5.3 or Qwen3.8 27B for agents that call tools.
- Connect Langflow to BroadNet Inference
In Langflow, add the OpenAI component from the OpenAI bundle. Type a BroadNet ID such as broadnet/glm-5.3 into Model Name, paste your BroadNet key, and in the advanced settings set OpenAI API Base to https://inference.broadnet.ai/v1. Don't use the OpenAI Compatible model provider. It lists models from /v1/models, and BroadNet's lists only the transcription models.
Calling the API directly
- Use the OpenAI Python SDK with BroadNet Inference
Point the official OpenAI Python SDK at BroadNet Inference with one base_url change. Install, set your key, make a first request and stream the answer.
- Use the OpenAI Node.js SDK with BroadNet Inference
Point the official OpenAI Node.js and TypeScript SDK at BroadNet Inference by setting baseURL. Install it, make a first request, stream tokens and log request IDs.
- Try BroadNet Inference in your browser, no account
Test Arabic speech-to-text, document reading and Gemma 4 chat in BroadNet's browser playground with no sign-up or card, then move the same request to the API.
- First request to BroadNet Inference with curl
Make your first BroadNet Inference calls with curl - a chat completion, a streamed reply and an audio transcription - and read the response, usage and errors.
Questions
Does my tool work if it is not listed?
Probably. Any tool with an "OpenAI-compatible" or "custom OpenAI base URL" setting works: set the base URL to https://inference.broadnet.ai/v1, paste your BroadNet key and type a model ID such as broadnet/deepseek-v4.1-flash.
Which model should coding agents use?
DeepSeek V4.1 Flash. It has a 1,048,576-token context and is the model on the unlimited plans, so agents that resend large files are not metered per token. Run one plan session per agent working in parallel. If your tool depends on native tool_calls, test it first: BroadNet documents tool calling for GLM 5.3 and Qwen3.8 27B, not for DeepSeek V4.1 Flash.
Why does my tool show an empty answer?
Reasoning models think before they answer, and the thinking counts toward max_tokens. Raise the tool's max-tokens setting to 2,000 or more. Details.
Why do I get HTTP 429?
Pay-as-you-go keys allow 30 requests a minute and 4 in flight. A plan session runs one request at a time. Lower the tool's parallelism or add sessions. Errors and retries.