BroadRouter
Get started

Use Continue with BroadNet Inference (config.yaml and apiBase)

Updated

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.

Continue is an open-source AI assistant for VS Code and JetBrains. It reaches OpenAI-compatible servers through its openai provider with an apiBase override, as shown in Continue’s OpenAI provider docs. BroadNet Inference fits that pattern: same request shape, different base URL and model IDs.

Setup

  1. Get a BroadNet key from the console. See API keys.
  2. Open the local config. It lives at ~/.continue/config.yaml on macOS and Linux and %USERPROFILE%\.continue\config.yaml on Windows. In the IDE, open the configs dropdown above the chat input and click the gear icon next to Local Config.
  3. Add the models.
name: My Config
version: 0.0.1
schema: v1
models:
  - name: BroadNet GLM 5.3
    provider: openai
    model: broadnet/glm-5.3
    apiBase: https://inference.broadnet.ai/v1
    apiKey: your-broadnet-key
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
    defaultCompletionOptions:
      contextLength: 1048576
      maxTokens: 8000
  - name: BroadNet Qwen3.8 27B
    provider: openai
    model: broadnet/qwen3.8-27b
    apiBase: https://inference.broadnet.ai/v1
    apiKey: your-broadnet-key
    capabilities:
      - tool_use
      - image_input
    defaultCompletionOptions:
      contextLength: 262144
      maxTokens: 8000
  1. Save and pick the model in the model selector in the Continue panel.

Keep the file out of version control, because it holds the key.

What the fields do

  • provider: openai makes Continue send standard chat-completions requests.
  • apiBase replaces the default OpenAI address. Don’t append /chat/completions; Continue adds the path.
  • capabilities overrides Continue’s autodetection. Its reference says tool_use is required for Agent mode and image_input enables image uploads. Continue can’t detect these for custom IDs, so set them.
  • contextLength and maxTokens sit under defaultCompletionOptions. Reasoning counts toward maxTokens on BroadNet, so leave room.
  • roles defaults to chat, edit, apply and summarize. We left out autocomplete: these models reason before answering, which suits chat and edits better than keystroke-level completion.

Which model to pick

Use Model Why
Chat and Agent mode broadnet/glm-5.3 Tools and structured output, 1M context
Screenshots, Arabic broadnet/qwen3.8-27b Tools and image input, 262K context
Long chats on a flat plan broadnet/deepseek-v4.1-flash Unlimited plans, 1M context; tools not listed

For DeepSeek V4.1 Flash, drop tool_use unless your own test shows tool calls work, and set contextLength: 1048576. Prices for every model are on the pricing page. The GLM 5.3 model page has its limits.

Troubleshooting

  • 401. Check apiKey. A wrong, expired or out-of-allowance pay-as-you-go key returns 401.
  • Model errors on the first request. model must be the exact BroadNet ID, with the broadnet/ prefix. GLM 5.3, Qwen3.8 27B and DeepSeek V4.1 Flash need a top-up; the $5 starting credit covers BroadNet Gemma 4 VL 26B and the two Transcribe models.
  • Empty or cut-off replies. Raise maxTokens. Why answers come back empty.
  • 429. A pay-as-you-go key allows 30 requests a minute and 4 at once. Agent mode makes many calls in a row; add backoff in your workflow or space out runs. See errors and retries.
  • Several agents at once on a plan key. Each unlimited plan session runs one request at a time. Give each parallel agent its own session.
  • Wrong endpoint. Continue’s docs mention useLegacyCompletionsEndpoint and useResponsesApi. Don’t set the legacy option; BroadNet serves /v1/chat/completions. Continue uses /responses by default only for OpenAI’s o-series and GPT-5 models, so BroadNet IDs use chat completions without extra settings.

Questions

Where is Continue's config.yaml?

The local file is ~/.continue/config.yaml on macOS and Linux and %USERPROFILE%\.continue\config.yaml on Windows. You can also open it from the gear icon next to Local Config in the configs dropdown.

Why can't I use Agent mode with my BroadNet model?

Continue needs the tool_use capability for Agent mode. Add capabilities with tool_use to the model entry, and pick a model BroadNet lists with tools, such as broadnet/glm-5.3.

Why does Continue return an empty answer?

The reasoning used up maxTokens before the answer started. Raise maxTokens under defaultCompletionOptions to a few thousand.

Should I use config.json or config.yaml for Continue?

Use config.yaml. Continue's docs label config.json and its reference as deprecated, and all current examples use YAML with schema v1.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity