hermes-agent/website/docs/user-guide/features/fallback-providers.md

title, description, sidebar_label, sidebar_position

title	description	sidebar_label	sidebar_position
Fallback Providers	Configure automatic failover to backup LLM providers when your primary model is unavailable.	Fallback Providers	8

Fallback Providers

Hermes Agent has two separate fallback systems that keep your sessions running when providers hit issues:

1. Primary model fallback — automatically switches to a backup provider:model when your main model fails
2. Auxiliary task fallback — independent provider resolution for side tasks like vision, compression, and web extraction

Both are optional and work independently.

Primary Model Fallback

When your main LLM provider encounters errors — rate limits, server overload, auth failures, connection drops — Hermes can automatically switch to a backup provider:model pair mid-session without losing your conversation.

Configuration

Add a fallback_model section to ~/.hermes/config.yaml:

fallback_model:
  provider: openrouter
  model: anthropic/claude-sonnet-4

Both provider and model are required. If either is missing, the fallback is disabled.

Supported Providers

Provider	Value	Requirements
AI Gateway	ai-gateway	AI_GATEWAY_API_KEY
OpenRouter	openrouter	OPENROUTER_API_KEY
Nous Portal	nous	hermes login (OAuth)
OpenAI Codex	openai-codex	hermes model (ChatGPT OAuth)
Anthropic	anthropic	ANTHROPIC_API_KEY or Claude Code credentials
z.ai / GLM	zai	GLM_API_KEY
Kimi / Moonshot	kimi-coding	KIMI_API_KEY
MiniMax	minimax	MINIMAX_API_KEY
MiniMax (China)	minimax-cn	MINIMAX_CN_API_KEY
Kilo Code	kilocode	KILOCODE_API_KEY
Alibaba / DashScope	alibaba	DASHSCOPE_API_KEY
Hugging Face	huggingface	HF_TOKEN
Custom endpoint	custom	base_url + api_key_env (see below)

Custom Endpoint Fallback

For a custom OpenAI-compatible endpoint, add base_url and optionally api_key_env:

fallback_model:
  provider: custom
  model: my-local-model
  base_url: http://localhost:8000/v1
  api_key_env: MY_LOCAL_KEY          # env var name containing the API key

When Fallback Triggers

The fallback activates automatically when the primary model fails with:

• Rate limits (HTTP 429) — after exhausting retry attempts
• Server errors (HTTP 500, 502, 503) — after exhausting retry attempts
• Auth failures (HTTP 401, 403) — immediately (no point retrying)
• Not found (HTTP 404) — immediately
• Invalid responses — when the API returns malformed or empty responses repeatedly

When triggered, Hermes:

1. Resolves credentials for the fallback provider
2. Builds a new API client
3. Swaps the model, provider, and client in-place
4. Resets the retry counter and continues the conversation

The switch is seamless — your conversation history, tool calls, and context are preserved. The agent continues from exactly where it left off, just using a different model.

:::info One-Shot Fallback activates at most once per session. If the fallback provider also fails, normal error handling takes over (retries, then error message). This prevents cascading failover loops. :::

Examples

OpenRouter as fallback for Anthropic native:

model:
  provider: anthropic
  default: claude-sonnet-4-6

fallback_model:
  provider: openrouter
  model: anthropic/claude-sonnet-4

Nous Portal as fallback for OpenRouter:

model:
  provider: openrouter
  default: anthropic/claude-opus-4

fallback_model:
  provider: nous
  model: nous-hermes-3

Local model as fallback for cloud:

fallback_model:
  provider: custom
  model: llama-3.1-70b
  base_url: http://localhost:8000/v1
  api_key_env: LOCAL_API_KEY

Codex OAuth as fallback:

fallback_model:
  provider: openai-codex
  model: gpt-5.3-codex

Where Fallback Works

Context	Fallback Supported
CLI sessions	✔
Messaging gateway (Telegram, Discord, etc.)	✔
Subagent delegation	✘ (subagents do not inherit fallback config)
Cron jobs	✘ (run with a fixed provider)
Auxiliary tasks (vision, compression)	✘ (use their own provider chain — see below)

:::tip There are no environment variables for fallback_model — it is configured exclusively through config.yaml. This is intentional: fallback configuration is a deliberate choice, not something a stale shell export should override. :::

---

Auxiliary Task Fallback

Hermes uses separate lightweight models for side tasks. Each task has its own provider resolution chain that acts as a built-in fallback system.

Tasks with Independent Provider Resolution

Task	What It Does	Config Key
Vision	Image analysis, browser screenshots	auxiliary.vision
Web Extract	Web page summarization	auxiliary.web_extract
Compression	Context compression summaries	auxiliary.compression or compression.summary_provider
Session Search	Past session summarization	auxiliary.session_search
Skills Hub	Skill search and discovery	auxiliary.skills_hub
MCP	MCP helper operations	auxiliary.mcp
Memory Flush	Memory consolidation	auxiliary.flush_memories

Auto-Detection Chain

When a task's provider is set to "auto" (the default), Hermes tries providers in order until one works:

For text tasks (compression, web extract, etc.):

OpenRouter → Nous Portal → Custom endpoint → Codex OAuth →
API-key providers (z.ai, Kimi, MiniMax, Hugging Face, Anthropic) → give up

For vision tasks:

Main provider (if vision-capable) → OpenRouter → Nous Portal →
Codex OAuth → Anthropic → Custom endpoint → give up

If the resolved provider fails at call time, Hermes also has an internal retry: if the provider is not OpenRouter and no explicit base_url is set, it tries OpenRouter as a last-resort fallback.

Configuring Auxiliary Providers

Each task can be configured independently in config.yaml:

auxiliary:
  vision:
    provider: "auto"              # auto | openrouter | nous | codex | main | anthropic
    model: ""                     # e.g. "openai/gpt-4o"
    base_url: ""                  # direct endpoint (takes precedence over provider)
    api_key: ""                   # API key for base_url

  web_extract:
    provider: "auto"
    model: ""

  compression:
    provider: "auto"
    model: ""

  session_search:
    provider: "auto"
    model: ""

  skills_hub:
    provider: "auto"
    model: ""

  mcp:
    provider: "auto"
    model: ""

  flush_memories:
    provider: "auto"
    model: ""

Every task above follows the same provider / model / base_url pattern. Context compression uses its own top-level block:

compression:
  summary_provider: main                             # Same provider options as auxiliary tasks
  summary_model: google/gemini-3-flash-preview
  summary_base_url: null                             # Custom OpenAI-compatible endpoint

And the fallback model uses:

fallback_model:
  provider: openrouter
  model: anthropic/claude-sonnet-4
  # base_url: http://localhost:8000/v1               # Optional custom endpoint

All three — auxiliary, compression, fallback — work the same way: set provider to pick who handles the request, model to pick which model, and base_url to point at a custom endpoint (overrides provider).

Provider Options for Auxiliary Tasks

Provider	Description	Requirements
"auto"	Try providers in order until one works (default)	At least one provider configured
"openrouter"	Force OpenRouter	OPENROUTER_API_KEY
"nous"	Force Nous Portal	hermes login
"codex"	Force Codex OAuth	hermes model → Codex
"main"	Use whatever provider the main agent uses	Active main provider configured
"anthropic"	Force Anthropic native	ANTHROPIC_API_KEY or Claude Code credentials

Direct Endpoint Override

For any auxiliary task, setting base_url bypasses provider resolution entirely and sends requests directly to that endpoint:

auxiliary:
  vision:
    base_url: "http://localhost:1234/v1"
    api_key: "local-key"
    model: "qwen2.5-vl"

base_url takes precedence over provider. Hermes uses the configured api_key for authentication, falling back to OPENAI_API_KEY if not set. It does not reuse OPENROUTER_API_KEY for custom endpoints.

---

Context Compression Fallback

Context compression has a legacy configuration path in addition to the auxiliary system:

compression:
  summary_provider: "auto"                    # auto | openrouter | nous | main
  summary_model: "google/gemini-3-flash-preview"

This is equivalent to configuring auxiliary.compression.provider and auxiliary.compression.model. If both are set, the auxiliary.compression values take precedence.

If no provider is available for compression, Hermes drops middle conversation turns without generating a summary rather than failing the session.

---

Delegation Provider Override

Subagents spawned by delegate_task do not use the primary fallback model. However, they can be routed to a different provider:model pair for cost optimization:

delegation:
  provider: "openrouter"                      # override provider for all subagents
  model: "google/gemini-3-flash-preview"      # override model
  # base_url: "http://localhost:1234/v1"      # or use a direct endpoint
  # api_key: "local-key"

See Subagent Delegation for full configuration details.

---

Cron Job Providers

Cron jobs run with whatever provider is configured at execution time. They do not support a fallback model. To use a different provider for cron jobs, configure provider and model overrides on the cron job itself:

cronjob(
    action="create",
    schedule="every 2h",
    prompt="Check server status",
    provider="openrouter",
    model="google/gemini-3-flash-preview"
)

See Scheduled Tasks (Cron) for full configuration details.

---

Summary

Feature	Fallback Mechanism	Config Location
Main agent model	fallback_model in config.yaml — one-shot failover on errors	fallback_model: (top-level)
Vision	Auto-detection chain + internal OpenRouter retry	auxiliary.vision
Web extraction	Auto-detection chain + internal OpenRouter retry	auxiliary.web_extract
Context compression	Auto-detection chain, degrades to no-summary if unavailable	auxiliary.compression or compression.summary_provider
Session search	Auto-detection chain	auxiliary.session_search
Skills hub	Auto-detection chain	auxiliary.skills_hub
MCP helpers	Auto-detection chain	auxiliary.mcp
Memory flush	Auto-detection chain	auxiliary.flush_memories
Delegation	Provider override only (no automatic fallback)	delegation.provider / delegation.model
Cron jobs	Per-job provider override only (no automatic fallback)	Per-job provider / model