LLM Providers

HealOps is provider-agnostic: bring your own model. Selection is controlled by the LLM_PROVIDER environment variable, with per-provider API key and model overrides. Defaults are tracked in app/config.py and routing lives in app/services/llm_client.py.

Quick reference

Provider	`LLM_PROVIDER`	Auth	Reasoning model default	Toolcall model default
Anthropic	`anthropic`	`ANTHROPIC_API_KEY`	`claude-sonnet-4-6`	`claude-haiku-4-5-20251001`
OpenAI	`openai`	`OPENAI_API_KEY`	`gpt-5.4`	`gpt-5.4-mini`
OpenRouter	`openrouter`	`OPENROUTER_API_KEY`	`openrouter/auto`	`openrouter/auto`
Requesty	`requesty`	`REQUESTY_API_KEY`	`anthropic/claude-sonnet-4-6`	`anthropic/claude-sonnet-4-6`
Google Gemini	`gemini`	`GEMINI_API_KEY`	`gemini-3.1-pro-preview`	`gemini-3.1-flash-lite-preview`
NVIDIA NIM	`nvidia`	`NVIDIA_API_KEY`	`meta/llama-3.1-405b-instruct`	`meta/llama-3.1-8b-instruct`
MiniMax	`minimax`	`MINIMAX_API_KEY`	`MiniMax-M2.7`	`MiniMax-M2.7-highspeed`
Amazon Bedrock	`bedrock`	AWS IAM (`AWS_REGION`)	`us.anthropic.claude-sonnet-4-6`	`us.anthropic.claude-haiku-4-5-20251001-v1:0`
Ollama (local)	`ollama`	None (local daemon)	`llama3.2`	`llama3.2`
OpenAI Codex CLI	`codex`	`codex login` (CLI)	Codex CLI default	Codex CLI default
Claude Code CLI	`claude-code`	`claude login` (CLI)	Claude Code CLI default	Claude Code CLI default
GitHub Copilot CLI	`copilot`	`copilot login` or `gh auth login` (CLI)	Copilot CLI default	Copilot CLI default

HealOps distinguishes two model slots per provider:

Reasoning model — full-capability model used for diagnosis, claim validation, and multi-step analysis.
Toolcall model — lightweight, lower-cost model used for tool selection and routing.

Selecting a provider

Set LLM_PROVIDER (default: anthropic) in your environment or .env file:

export LLM_PROVIDER=openai
export OPENAI_API_KEY=sk-...

Or run the onboarding wizard, which writes the same values to .env:

healops onboard

Override the default model for a slot via env vars:

export OPENAI_REASONING_MODEL=gpt-5.4
export OPENAI_TOOLCALL_MODEL=gpt-5.4-mini

A shared LLM_MAX_TOKENS (default 4096) controls the response token budget for every provider.

API providers

Anthropic

export LLM_PROVIDER=anthropic
export ANTHROPIC_API_KEY=sk-ant-...
# Optional overrides:
export ANTHROPIC_REASONING_MODEL=claude-sonnet-4-6
export ANTHROPIC_TOOLCALL_MODEL=claude-haiku-4-5-20251001

The default. Uses the Anthropic Python SDK directly. Get an API key at console.anthropic.com.

OpenAI

export LLM_PROVIDER=openai
export OPENAI_API_KEY=sk-...
# Optional overrides:
export OPENAI_REASONING_MODEL=gpt-5.4
export OPENAI_TOOLCALL_MODEL=gpt-5.4-mini

Uses the OpenAI SDK. Reasoning models (o1, o3, o4, gpt-5*) automatically use max_completion_tokens instead of max_tokens.

OpenRouter

export LLM_PROVIDER=openrouter
export OPENROUTER_API_KEY=sk-or-...
# Optional override (single value applies to both slots if set):
export OPENROUTER_MODEL=openrouter/auto
# Or per-slot:
export OPENROUTER_REASONING_MODEL=anthropic/claude-sonnet-4-6
export OPENROUTER_TOOLCALL_MODEL=openai/gpt-4o-mini

OpenAI-compatible proxy — pick any model on openrouter.ai/models. Base URL: https://openrouter.ai/api/v1.

Requesty

export LLM_PROVIDER=requesty
export REQUESTY_API_KEY=...
# Optional override (single value applies to both slots if set):
export REQUESTY_MODEL=anthropic/claude-sonnet-4-6
# Or per-slot:
export REQUESTY_REASONING_MODEL=anthropic/claude-sonnet-4-6
export REQUESTY_TOOLCALL_MODEL=anthropic/claude-sonnet-4-6

OpenAI-compatible gateway at https://router.requesty.ai/v1. Sends an X-Title: HealOps header for usage attribution. Browse models on requesty.ai.

Google Gemini

export LLM_PROVIDER=gemini
export GEMINI_API_KEY=...
# Optional override:
export GEMINI_MODEL=gemini-3.1-pro-preview
# Or per-slot:
export GEMINI_REASONING_MODEL=gemini-3.1-pro-preview
export GEMINI_TOOLCALL_MODEL=gemini-3.1-flash-lite-preview

Uses Google’s OpenAI-compatible endpoint at https://generativelanguage.googleapis.com/v1beta/openai/. Get an API key at aistudio.google.com.

NVIDIA NIM

export LLM_PROVIDER=nvidia
export NVIDIA_API_KEY=nvapi-...
# Optional override:
export NVIDIA_MODEL=meta/llama-3.1-405b-instruct
# Or per-slot:
export NVIDIA_REASONING_MODEL=meta/llama-3.1-405b-instruct
export NVIDIA_TOOLCALL_MODEL=meta/llama-3.1-8b-instruct

Uses NVIDIA’s OpenAI-compatible API at https://integrate.api.nvidia.com/v1. Browse available models on build.nvidia.com.

MiniMax

export LLM_PROVIDER=minimax
export MINIMAX_API_KEY=...
# Optional override (single value applies to both slots if set):
export MINIMAX_MODEL=MiniMax-M2.7
# Or per-slot:
export MINIMAX_REASONING_MODEL=MiniMax-M2.7
export MINIMAX_TOOLCALL_MODEL=MiniMax-M2.7-highspeed

OpenAI-compatible endpoint at https://api.minimax.io/v1. Temperature is fixed to 1.0 to match MiniMax recommendations.

Amazon Bedrock

export LLM_PROVIDER=bedrock
export AWS_REGION=us-east-1
# Optional overrides:
export BEDROCK_REASONING_MODEL=us.anthropic.claude-sonnet-4-6
export BEDROCK_TOOLCALL_MODEL=us.anthropic.claude-haiku-4-5-20251001-v1:0

No API key — auth uses the AWS credential chain (environment variables, shared credentials file, or IAM role). Your principal needs permission to invoke the model IDs you configure (for example Bedrock InvokeModel / Converse access scoped to those resources in IAM). Model routing:

Anthropic Claude on Bedrock (anthropic.claude-*, us.anthropic.claude-*, and foundation-model ARNs that contain anthropic.claude) use the existing AnthropicBedrock SDK path.
Other Bedrock foundation models (for example Mistral, Meta Llama, Amazon Titan IDs you enable in your account) use the Bedrock Converse API via boto3, so you can set BEDROCK_REASONING_MODEL to a non-Claude model ID when your use case requires it.
Application inference profile ARNs (…:application-inference-profile/…) do not encode the vendor in the ID; those are always sent through Converse, which works for any backing model in the profile.

Defaults in app/config.py are US cross-region inference profile IDs for Anthropic Claude; override with IDs or ARNs that are inference-access enabled in your account and region.

Ollama (local)

export LLM_PROVIDER=ollama
# Optional overrides:
export OLLAMA_HOST=http://localhost:11434
export OLLAMA_MODEL=llama3.2

Run any local model exposed by an Ollama daemon. No API key required — HealOps talks to Ollama’s OpenAI-compatible endpoint at ${OLLAMA_HOST}/v1.

CLI providers (subprocess)

CLI-backed providers shell out to a vendor CLI instead of an HTTP API. They authenticate via the vendor’s own login command; HealOps detects the binary on PATH (or via an explicit env var) and reuses the existing session.

OpenAI Codex

export LLM_PROVIDER=codex
# Authenticate the Codex CLI separately:
codex login
# Optional overrides (all blank-by-default):
export CODEX_MODEL=
export CODEX_BIN=

Requires the OpenAI Codex CLI. If CODEX_MODEL is unset, HealOps omits -m so codex exec uses the CLI’s currently configured model. If CODEX_BIN is unset, the binary is resolved via PATH and known install locations.

Claude Code

export LLM_PROVIDER=claude-code
# Authenticate the Claude Code CLI separately:
claude login
# Optional overrides (all blank-by-default):
export CLAUDE_CODE_MODEL=
export CLAUDE_CODE_BIN=

Requires the Claude Code CLI (npm i -g @anthropic-ai/claude-code). If CLAUDE_CODE_MODEL is unset, HealOps omits the --model flag and the CLI uses its configured default. If CLAUDE_CODE_BIN is unset, the binary is resolved via PATH and known install locations.

GitHub Copilot

export LLM_PROVIDER=copilot
# Authenticate the Copilot CLI separately. Either flow works — the adapter
# detects both. The interactive `/login` slash command inside `copilot` writes
# to the platform credential store; `gh auth login` is an equivalent path that
# Copilot CLI delegates to automatically.
copilot login          # OAuth device flow; preferred CLI-first onboarding
# or:
gh auth login          # logs you into the gh CLI; Copilot will use that token
# Optional overrides (all blank-by-default):
export COPILOT_MODEL=
export COPILOT_BIN=
# Optional auth bypass for automation (only used when no CLI login is detected):
# export COPILOT_GITHUB_TOKEN=
# export GH_TOKEN=
# export GITHUB_TOKEN=

Requires the GitHub Copilot CLI (npm i -g @github/copilot). Login uses the interactive /login slash command or copilot login. HealOps detects auth in this order: (1) COPILOT_GITHUB_TOKEN / GH_TOKEN / GITHUB_TOKEN env, (2) gh auth status when gh is on PATH (including ✓ Logged in to github.com account …, - Active account: true, or a supported - Token: prefix: gho_, github_pat_, ghu_ per Copilot docs — not ghp_), with gh auth status --hostname … when COPILOT_GH_HOST or GH_HOST targets a non-github.com host. It does not read plaintext $COPILOT_HOME/config.json (keychain-backed installs may omit it; mis-parsing arbitrary JSON risks false positives). If nothing matches, detection reports logged_in=None and the runner verifies at invoke time. If COPILOT_MODEL is unset, HealOps omits --model. Invocations run as copilot -p PROMPT --no-color --no-ask-user --silent so they never block on user input. BYOK / COPILOT_OFFLINE: GitHub auth may be unnecessary; a None probe can still be fine if Copilot is configured for offline or external providers only. See app/integrations/llm_cli/AGENTS.md for the adapter pattern used to add new CLI providers.

Reasoning effort (interactive shell)

In the TTY REPL (healops with no subcommand), /effort stores a session preference for how strongly reasoning models should think before answering. It applies only when LLM_PROVIDER is openai (HTTP API) or codex (Codex CLI); other providers ignore the setting and the shell notes that.

Input	Sent to the model
`low`, `medium`, `high`, `xhigh`	same string
`max`	`xhigh`

Run /effort alone to show the current choice (or (default) when unset) and the usage line. /reset clears investigation state but keeps /effort (and trust mode), consistent with other session prefs. Outside the REPL, optional defaults use the environment variable:

export HEALOPS_REASONING_EFFORT=high   # low | medium | high | xhigh

Session /effort overrides this for interactive runs. Implementation: app/llm_reasoning_effort.py.

Switching providers at runtime

HealOps caches LLM clients on first use. To switch providers within a single process (tests, benchmarks), call reset_llm_singletons() from app.services.llm_client after updating the env vars; otherwise a fresh process picks up the new LLM_PROVIDER automatically.

Where this lives in the code

Provider literals and defaults: app/config.py (LLMProvider, LLMSettings).
Runtime routing: app/services/llm_client.py (_create_llm_client).
API-backed provider guide: app/services/AGENTS.md.
CLI-backed provider guide: app/integrations/llm_cli/AGENTS.md.

Overview

Observability and incidents

Cloud, code, and collaboration

Messaging

Data and workflow systems

LLM Providers

Quick reference

Selecting a provider

API providers

Anthropic

OpenAI

OpenRouter

Requesty

Google Gemini

NVIDIA NIM

MiniMax

Amazon Bedrock

Ollama (local)

CLI providers (subprocess)

OpenAI Codex

Claude Code

GitHub Copilot

Reasoning effort (interactive shell)

Switching providers at runtime

Where this lives in the code

​Quick reference

​Selecting a provider

​API providers

​Anthropic

​OpenAI

​OpenRouter

​Requesty

​Google Gemini

​NVIDIA NIM

​MiniMax

​Amazon Bedrock

​Ollama (local)

​CLI providers (subprocess)

​OpenAI Codex

​Claude Code

​GitHub Copilot

​Reasoning effort (interactive shell)

​Switching providers at runtime

​Where this lives in the code

Quick reference

Selecting a provider

API providers

Anthropic

OpenAI

OpenRouter

Requesty

Google Gemini

NVIDIA NIM

MiniMax

Amazon Bedrock

Ollama (local)

CLI providers (subprocess)

OpenAI Codex

Claude Code

GitHub Copilot

Reasoning effort (interactive shell)

Switching providers at runtime

Where this lives in the code