- Add fireworks-models.ts with static catalog of 24 serverless LLM models
- Add dynamic model discovery from Fireworks API with pagination
- Integrate into onboarding (interactive + non-interactive flows)
- Add fireworks-api-key auth choice and --fireworks-api-key CLI flag
- Add FIREWORKS_API_KEY to envMap for auto-detection
- Add Fireworks to resolveImplicitProviders
- Add docs/providers/fireworks.md documentation
- Update docs navigation and CLI reference
Model IDs use full format: accounts/fireworks/models/<model>
Default model: deepseek-v3p2 (DeepSeek V3.2)
Venice AI is a privacy-focused AI inference provider with support for
uncensored models and access to major proprietary models via their
anonymized proxy.
This integration adds:
- Complete model catalog with 25 models:
- 15 private models (Llama, Qwen, DeepSeek, Venice Uncensored, etc.)
- 10 anonymized models (Claude, GPT-5.2, Gemini, Grok, Kimi, MiniMax)
- Auto-discovery from Venice API with fallback to static catalog
- VENICE_API_KEY environment variable support
- Interactive onboarding via 'venice-api-key' auth choice
- Model selection prompt showing all available Venice models
- Provider auto-registration when API key is detected
- Comprehensive documentation covering:
- Privacy modes (private vs anonymized)
- All 25 models with context windows and features
- Streaming, function calling, and vision support
- Model selection recommendations
Privacy modes:
- Private: Fully private, no logging (open-source models)
- Anonymized: Proxied through Venice (proprietary models)
Default model: venice/llama-3.3-70b (good balance of capability + privacy)
Venice API: https://api.venice.ai/api/v1 (OpenAI-compatible)
