Provider catalog
Providers
The daemon owns the hydrated provider catalog and sends it to TUI and React before provider setup and model selection flows render.
How Provider Loading Works
Zorai starts with built-in providers, then merges valid custom providers from custom-auth.yaml. Invalid custom entries are reported as non-blocking diagnostics and do not remove valid custom providers or built-in providers.
Model fetching for main agents and sub-agents uses the same daemon lookup path, so a custom provider that appears in the catalog is also available to model validation and sub-agent spawning.
Built-In Providers And Models
| Provider | ID | Default model | Available models |
|---|---|---|---|
| Featherless | featherless | meta-llama/Llama-3.3-70B-Instruct | Manual/default model only. |
| Anthropic | anthropic | claude-opus-4-7 | claude-opus-4-7, claude-opus-4-6, claude-opus-4-5-20251101, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-sonnet-4-6, claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-3-7-sonnet-20250219, claude-haiku-4-5-20251001, claude-3-5-haiku-20241022, claude-3-opus-20240229, claude-3-haiku-20240307. |
| OpenAI / ChatGPT | openai | gpt-5.5 | gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.3-codex, gpt-5.2-codex, gpt-5.2, gpt-5.1-codex-max, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1, gpt-5-codex, gpt-5-codex-mini, gpt-5, codex-mini-latest, o3, o4-mini, plus remote model fetch. |
| xAI | xai | grok-4 | grok-4, grok-code-fast-1, plus remote model fetch. |
| Azure OpenAI | azure-openai | User deployment | Remote Azure model fetch. |
| GitHub Copilot | github-copilot | gpt-5.4 | gpt-5.4, gpt-5.5, claude-haiku-4.5, claude-opus-4.5, claude-opus-4.6, claude-opus-4.6-fast, claude-sonnet-4, claude-sonnet-4.5, claude-sonnet-4.6, gemini-2.5-pro, gemini-3-flash-preview, gemini-3.1-pro-preview, gpt-4.1, gpt-4o, gpt-5-mini, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2, gpt-5.2-codex, gpt-5.3-codex, gpt-5.4-mini, grok-code-fast-1, raptor-mini, goldeneye. |
| Qwen | qwen | qwen-max | qwen-max, qwen-plus, qwen-turbo, qwen-long, plus remote model fetch. |
| Qwen DeepInfra | qwen-deepinfra | Qwen/Qwen2.5-72B-Instruct | Remote model fetch. |
| Kimi | kimi | moonshot-v1-32k | moonshot-v1-32k, moonshot-v1-8k, moonshot-v1-128k, plus remote model fetch. |
| Kimi Coding Plan | kimi-coding-plan | kimi-for-coding | kimi-for-coding, kimi-k2.6, kimi-k2.5, kimi-k2-turbo-preview. |
| Z.AI | z.ai | glm-4-plus | glm-4-plus, glm-5.1, glm-5, glm-4, glm-4-air, glm-4-flash. |
| Z.AI Coding Plan | z.ai-coding-plan | glm-5 | glm-5, glm-5.1, glm-4-plus, glm-4, glm-4-air, glm-4-flash. |
| Arcee | arcee | trinity-large-thinking | trinity-large-thinking, plus remote model fetch. |
| NVIDIA | nvidia | minimaxai/minimax-m2.7 | minimaxai/minimax-m2.7, plus remote model fetch. |
| Nous Portal | nous-portal | nousresearch/hermes-4-70b | nousresearch/hermes-4-70b, nousresearch/hermes-4-405b, nousresearch/hermes-3-llama-3.1-70b, nousresearch/hermes-3-llama-3.1-405b, plus remote model fetch. |
| OpenRouter | openrouter | arcee-ai/trinity-large-thinking | Remote model fetch. |
| Cerebras | cerebras | llama-3.3-70b | Remote model fetch. |
| Together | together | meta-llama/Llama-3.3-70B-Instruct-Turbo | Remote model fetch. |
| Groq | groq | llama-3.3-70b-versatile | llama-3.3-70b-versatile, llama-3.1-8b-instant, plus remote model fetch. |
| Ollama | ollama | llama3.1 | llama3.1, llama3.2, qwen2.5, codellama, plus local model fetch. |
| Chutes | chutes | deepseek-ai/DeepSeek-R1 | Remote model fetch. |
| Hugging Face | huggingface | meta-llama/Llama-3.3-70B-Instruct | Manual/default model only. |
| MiniMax | minimax | MiniMax-M1-80k | MiniMax-M2.7, MiniMax-M2.5. |
| MiniMax Coding Plan | minimax-coding-plan | MiniMax-M2.7 | MiniMax-M2.7, MiniMax-M2.5. |
| Alibaba Coding Plan | alibaba-coding-plan | qwen3.6-plus | qwen3.6-plus, qwen3-coder-plus, qwen3-coder-next, glm-5, kimi-k2.6, kimi-k2.5, MiniMax-M2.5. |
| Xiaomi MiMo Token Plan | xiaomi-mimo-token-plan | mimo-v2-pro | mimo-v2-pro, mimo-v2-omni, mimo-v2.5-pro, mimo-v2.5, mimo-v2.5-tts, mimo-v2.5-tts-voiceclone, mimo-v2.5-tts-voicedesign. |
| OpenCode Zen | opencode-zen | claude-sonnet-4-5 | claude-opus-4-6, claude-sonnet-4-5, claude-sonnet-4, gpt-5.4, gpt-5.3-codex, minimax-m2.5, glm-5, kimi-k2.6, kimi-k2.5, plus remote model fetch. |
| Custom fallback | custom | User-defined | Manual model entry. |
Remote-fetch providers can return more models than the static defaults shown here. Those results come from the upstream provider at runtime and are merged into the model picker without changing the built-in catalog.
Custom Providers
Use Custom Providers to add named providers with static models, remote model fetch, custom auth method, transport mode, and modality metadata.