Integration

Coding Agents

BasicRouter works with coding agents and AI development tools that support OpenAI-compatible or Anthropic-compatible API endpoints. Use routing aliases such as mwf/coding-auto so BasicRouter can route to the best available coding model without requiring developers to change tool configuration.

Generic OpenAI-compatible setup

Use this setup for Cursor, Codex, Hermes, OpenClaw, Continue, Aider, Cline, LangChain-based agents, LlamaIndex-based agents, and custom OpenAI-compatible agent runtimes.

export OPENAI_BASE_URL="https://api.basicrouter.ai/api/v1"
export OPENAI_API_KEY="$BASICROUTER_API_KEY"
export OPENAI_MODEL="mwf/coding-auto"

Generic Anthropic-compatible setup

Use this setup for Claude-compatible clients and tools that expect Anthropic Messages format.

export ANTHROPIC_BASE_URL="https://api.basicrouter.ai/api/anthropic"
export ANTHROPIC_API_KEY="$BASICROUTER_API_KEY"
export ANTHROPIC_MODEL="mwf/coding-auto"

Recommended agent models

Use case	Recommended alias	Requirements
General coding	`mwf/coding-auto`	Tool calling, streaming, strong coding ability.
Fast coding chat	`mwf/coding-fast`	Low latency and streaming.
Large repo analysis	`mwf/coding-long`	Long context and stable output.
Cost-sensitive coding assistant	`mwf/low-cost`	Lower price and acceptable coding quality.
UI screenshot / vision coding	`mwf/vision-chat`	Vision input and text output.

Cursor quick guide

Use the OpenAI-compatible endpoint.

Base URL: https://api.basicrouter.ai/api/v1
API Key:  BASICROUTER_API_KEY
Model:    mwf/coding-auto

Recommended steps:

Open Cursor settings.
Add or enable OpenAI-compatible API key configuration.
Set the OpenAI base URL override to https://api.basicrouter.ai/api/v1.
Add a custom model such as mwf/coding-auto, mwf/coding-fast, or mwf/coding-long.
Use a model that supports streaming and tool calling for best agent behavior.

Troubleshooting:

Issue	Suggested fix
Model not shown	Add the model name manually as a custom model.
Tool calling fails	Use a model with `tool_calling: true` in the Models page.
Streaming interrupted	Retry with backoff or use a routing alias with fallback.
401 error	Check the API key and base URL.
404 model error	Confirm the model is enabled for the account.

Claude Code quick guide

Use the Anthropic-compatible gateway endpoint.

export ANTHROPIC_BASE_URL="https://api.basicrouter.ai/api/anthropic"
export ANTHROPIC_API_KEY="$BASICROUTER_API_KEY"
export ANTHROPIC_MODEL="mwf/coding-auto"

BasicRouter supports this Anthropic-compatible path for Claude Code and Anthropic SDK compatibility:

POST /api/v1/messages

Recommended requirements:

Requirement	Reason
Anthropic Messages-compatible request shape	Claude Code expects Anthropic-style messages.
Streaming support	Claude Code relies on streaming UX.
Tool calling support	Required for agentic coding workflows.
Long context	Useful for repository-level tasks.
Stable fallback	Useful for long-running coding sessions.

Codex quick guide

Use BasicRouter as a custom OpenAI-compatible model provider.

Example provider configuration:

[model_providers.basicrouter]
name = "BasicRouter"
base_url = "https://api.basicrouter.ai/api/v1"
env_key = "BASICROUTER_API_KEY"
wire_api = "responses"

model_provider = "basicrouter"
model = "mwf/coding-auto"

Environment variable:

export BASICROUTER_API_KEY="br_xxx"

Recommended models:

Model	Use case
`mwf/coding-auto`	Default coding agent model.
`mwf/coding-long`	Large repository context.
`mwf/coding-fast`	Fast iteration and small changes.

Troubleshooting:

Issue	Suggested fix
Auth error	Confirm `env_key` points to `BASICROUTER_API_KEY`.
Model not found	Add the alias in BasicRouter Console or use a direct model ID.
Responses API error	Use `wire_api = "responses"` only for models and endpoints that support Responses.
Chat Completions-only model	Switch to a chat-compatible wire API if the client supports it.

Hermes quick guide

Use the OpenAI-compatible endpoint unless your Hermes deployment is configured for another protocol.

export OPENAI_BASE_URL="https://api.basicrouter.ai/api/v1"
export OPENAI_API_KEY="$BASICROUTER_API_KEY"
export OPENAI_MODEL="mwf/coding-auto"

Recommended model policy:

Hermes workload	Model
General code generation	`mwf/coding-auto`
Low-latency task execution	`mwf/coding-fast`
Long-context repo scan	`mwf/coding-long`
Cost-sensitive background tasks	`mwf/low-cost`

OpenClaw quick guide

Use the OpenAI-compatible endpoint for OpenAI-style agent runtime configuration.

export OPENAI_BASE_URL="https://api.basicrouter.ai/api/v1"
export OPENAI_API_KEY="$BASICROUTER_API_KEY"
export OPENAI_MODEL="mwf/coding-auto"

If OpenClaw supports multiple providers, configure BasicRouter as an OpenAI-compatible provider and use BasicRouter routing aliases for model selection.

{
  "provider": "openai-compatible",
  "base_url": "https://api.basicrouter.ai/api/v1",
  "api_key_env": "BASICROUTER_API_KEY",
  "model": "mwf/coding-auto"
}

Agent compatibility checklist

Capability	Required for
Streaming	Good terminal/editor UX.
Tool calling	Agentic coding, file edits, command execution.
Long context	Large repositories and multi-file changes.
Structured outputs	Planning, task decomposition, automated workflows.
Vision input	UI screenshot analysis and design-to-code workflows.
Fallback	Production stability and long-running tasks.