Docs
Providers

Hosted Providers

Managed provider and gateway setup for Facio.

Hosted providers cover direct model APIs, gateways, and subscription routers. Most use an API key plus an optional default API base from the provider registry.

Provider reference

ProviderConfig keyKey nameDefault API baseNotes
AnthropicanthropicANTHROPIC_API_KEYNative SDK defaultRoutes Claude models and supports prompt caching.
OpenAIopenaiOPENAI_API_KEYSDK defaultRoutes GPT/OpenAI models and supports max-completion-token style models.
OpenRouteropenrouterOPENROUTER_API_KEYhttps://openrouter.ai/api/v1Gateway provider; routes many model families.
Azure OpenAIazure_openaiCustom keyRequired apiBaseModel is the deployment name. Requires key and Azure endpoint.
AWS BedrockbedrockAWS_BEARER_TOKEN_BEDROCK or AWS authNative Bedrock runtimeUses Bedrock Converse through AWS configuration.
Hugging FacehuggingfaceHF_TOKENhttps://router.huggingface.co/v1OpenAI-compatible inference router.
BytePlusbyteplusBYTEPLUS_API_KEYhttps://ark.ap-southeast.bytepluses.com/api/v3OpenAI-compatible VolcEngine international endpoint.
BytePlus Coding Planbyteplus_coding_planBYTEPLUS_CODING_PLAN_API_KEYhttps://ark.ap-southeast.bytepluses.com/api/coding/v3Coding-plan gateway, strips provider prefix before sending.
OpenCode Goopencode_goOPENCODE_GO_API_KEYhttps://opencode.ai/zen/go/v1Subscription gateway with a models endpoint at /models.
DeepSeekdeepseekDEEPSEEK_API_KEYhttps://api.deepseek.comOpenAI-compatible.
GeminigeminiGEMINI_API_KEYhttps://generativelanguage.googleapis.com/v1beta/openai/Google's OpenAI-compatible endpoint.
Zhipu AIzhipuZAI_API_KEYhttps://open.bigmodel.cn/api/paas/v4Also exposes ZHIPUAI_API_KEY to provider tooling.
DashScopedashscopeDASHSCOPE_API_KEYhttps://dashscope.aliyuncs.com/compatible-mode/v1Qwen-compatible routing with provider thinking options.
MoonshotmoonshotMOONSHOT_API_KEYhttps://api.moonshot.ai/v1Kimi models use provider-specific temperature behavior.
MiniMaxminimaxMINIMAX_API_KEYhttps://api.minimax.io/v1OpenAI-compatible.
MistralmistralMISTRAL_API_KEYhttps://api.mistral.ai/v1OpenAI-compatible.
GroqgroqGROQ_API_KEYhttps://api.groq.com/openai/v1Often used for transcription; can also route LLM calls.

Quickstart envs

The Docker quickstart maps these simple host env names into Facio provider config:

Host .envFacio config target
OPENROUTER_API_KEYproviders.openrouter.apiKey
ANTHROPIC_API_KEYproviders.anthropic.apiKey
OPENAI_API_KEYproviders.openai.apiKey
FACIO_MODELagents.defaults.model

Other providers can be configured through Placet settings, config.json, the management API, or nested FACIO_... config environment variables.

Provider selection examples

GoalExample setting
Use Anthropic by model namemodel: anthropic/claude-opus-4-7, provider: auto
Force OpenRouterprovider: openrouter, model can be an OpenRouter-routable model ID.
Use Azure deploymentprovider: azure_openai, model equals the Azure deployment name, apiBase is the Azure endpoint.
Use OpenCode Goprovider: opencode_go, apiKey set, model selected from OpenCode Go's model catalog.

Subagent and media routes

Facio can use separate defaults for different work classes:

SettingPurpose
subagent_model / subagent_providerBackground research or coding helpers.
vision_model / vision_providerFallback when images need a vision-capable model.
image_model / image_providerDefault model for image generation tools.
video_model / video_providerDefault model for video generation tools.

Keep these empty until the main route works; then add overrides for cost, capability, or latency reasons.

On this page