Share feedback
Answers are generated based on the documentation.

Model Providers

docker-agent supports multiple AI model providers. Choose the right one for your use case, or use multiple providers in the same configuration.

Supported Providers

  • OpenAI — GPT-5, GPT-5-mini, GPT-4o. The most widely used AI models.
  • Anthropic — Claude Sonnet 4.5, Claude Opus 4.7. Excellent for coding and analysis.
  • Google Gemini — Gemini 2.5 Flash, Gemini 3 Pro. Fast and cost-effective.
  • AWS Bedrock — access Claude, Nova, Llama, and more through AWS infrastructure.
  • Docker Model Runner — run models locally with Docker. No API keys, no costs.
  • Provider Definitions — define reusable provider configurations with shared defaults for any provider type.

Quick Comparison

ProviderKeyLocal?Strengths
OpenAIopenaiNoBroad model selection, tool calling, multimodal
AnthropicanthropicNoStrong coding, extended thinking, large context
GooglegoogleNoFast inference, competitive pricing, multimodal
AWS Bedrockamazon-bedrockNoEnterprise features, multiple models, AWS integration
Docker Model RunnerdmrYesNo API costs, data privacy, offline capable

Additional Built-in Providers

docker-agent also includes built-in aliases for these providers:

ProviderAliasAPI Key / Env Variable
OpenCode Zenopencode-zenOPENCODE_API_KEY
OpenCode Goopencode-goOPENCODE_API_KEY
MistralmistralMISTRAL_API_KEY
xAI (Grok)xaiXAI_API_KEY
NebiusnebiusNEBIUS_API_KEY
MiniMaxminimaxMINIMAX_API_KEY
BasetenbasetenBASETEN_API_KEY
OVHcloudovhcloudOVH_AI_ENDPOINTS_ACCESS_TOKEN
GroqgroqGROQ_API_KEY
Fireworks AIfireworksFIREWORKS_API_KEY
DeepSeekdeepseekDEEPSEEK_API_KEY
CerebrascerebrasCEREBRAS_API_KEY
Together AItogetherTOGETHER_API_KEY
Hugging FacehuggingfaceHF_TOKEN
Cloudflare Workers AIcloudflare-workers-aiCLOUDFLARE_API_TOKEN + CLOUDFLARE_ACCOUNT_ID
Moonshot AImoonshotMOONSHOT_API_KEY
Vercel AI GatewayvercelAI_GATEWAY_API_KEY
Cloudflare AI Gatewaycloudflare-ai-gatewayCLOUDFLARE_API_TOKEN + CLOUDFLARE_ACCOUNT_ID + CLOUDFLARE_GATEWAY_ID
RequestyrequestyREQUESTY_API_KEY
OpenRouteropenrouterOPENROUTER_API_KEY
Azure OpenAIazureAZURE_API_KEY + base_url
OllamaollamaNone (local; optional base_url)
GitHub Copilotgithub-copilotGITHUB_TOKEN (PAT with copilot scope)
# Use built-in providers inline
agents:
  root:
    model: mistral/mistral-large-latest
Tip

Multi-provider teams

Use expensive models for complex reasoning and cheaper/local models for routine tasks. See the example below.

Using Multiple Providers

Different agents can use different providers in the same configuration:

models:
  claude:
    provider: anthropic
    model: claude-sonnet-4-5
    max_tokens: 64000
  gpt:
    provider: openai
    model: gpt-5
  local:
    provider: dmr
    model: ai/qwen3

agents:
  root:
    model: claude # coordinator uses Claude
    sub_agents: [coder, helper]
  coder:
    model: gpt # coder uses GPT-5
  helper:
    model: local # helper runs locally for free