Zed Editor
Zed is a high-performance editor with built-in AI assistant support. It can connect to any OpenAI-compatible API, making DeepIntShield a natural fit for universal model access across providers, plus governance features like virtual keys and built-in observability.

1. Configure DeepIntShield Provider
Section titled “1. Configure DeepIntShield Provider”Add DeepIntShield to Zed’s language_models.openai_compatible configuration. This is typically in your Zed settings (JSON) or workspace config.
"language_models": { "openai_compatible": { "DeepIntShield": { "api_url": "http://localhost:8080/openai", "available_models": [ { "name": "anthropic/claude-sonnet-4.5", "max_tokens": 200000, "max_output_tokens": 4096, "capabilities": { "tools": true, "images": true, "parallel_tool_calls": true, "prompt_cache_key": false } }, { "name": "openai/gpt-4o", "max_tokens": 128000, "max_output_tokens": 4096, "capabilities": { "tools": true, "images": true, "parallel_tool_calls": true, "prompt_cache_key": false } }, { "name": "openai/gpt-5", "max_tokens": 256000, "max_output_tokens": 4096, "capabilities": { "tools": true, "images": true, "parallel_tool_calls": true, "prompt_cache_key": false } } ] } }}Replace http://localhost:8080/openai with your DeepIntShield gateway URL + /openai.
2. Model Capabilities
Section titled “2. Model Capabilities”| Field | Description |
|---|---|
tools | Enable tool/function calling |
images | Enable image input (vision) |
parallel_tool_calls | Support multiple tool calls in one response |
prompt_cache_key | Enable prompt caching (set false if not supported) |
Use DeepIntShield model IDs in provider/model format (e.g. openai/gpt-5, anthropic/claude-sonnet-4.5). Ensure these models are configured in DeepIntShield.
3. Reload Workspace
Section titled “3. Reload Workspace”After changing the configuration, reload the workspace so Zed recognizes and reloads the provider list.
Virtual Keys
Section titled “Virtual Keys”When DeepIntShield has virtual key authentication enabled, add an api_key field to the DeepIntShield provider config (check Zed’s documentation for the exact field name — it may vary by version):
"DeepIntShield": { "api_url": "http://localhost:8080/openai", "api_key": "bf-your-virtual-key-here", "available_models": [...]}This lets you enforce usage limits, budgets, and access control per user or team. For team deployments, create a separate virtual key for each team or environment — each key can have its own rate limits, budgets, and provider access rules configured in the DeepIntShield dashboard.
Model Selection
Section titled “Model Selection”Zed lets you assign models to different AI features. Use DeepIntShield model IDs in provider/model format to access any configured provider:
- Use powerful models like
openai/gpt-5oranthropic/claude-sonnet-4-5-20250929for complex code generation and refactoring - Use fast models like
groq/llama-3.3-70b-versatilefor quick completions and inline suggestions
Using Multiple Providers
Section titled “Using Multiple Providers”DeepIntShield routes requests to the correct provider based on the model name. Use the provider/model-name format to access any configured provider through the single OpenAI-compatible endpoint:
anthropic/claude-sonnet-4-5-20250929openai/gpt-5gemini/gemini-2.5-promistral/mistral-large-latestSupported Providers
Section titled “Supported Providers”DeepIntShield supports the following providers with the provider/model-name format:
openai, azure, gemini, vertex, bedrock, mistral, groq, cerebras, cohere, perplexity, xai, ollama, openrouter, huggingface, nebius, parasail, replicate, vllm, sgl
Observability
Section titled “Observability”All Zed requests through DeepIntShield are logged. Monitor them at http://localhost:8080/logs — filter by provider, model, or search through conversation content to track usage.
Next Steps
Section titled “Next Steps”- Provider Configuration — Configure AI providers in DeepIntShield
- Virtual Keys — Set up usage limits and access control