Model providers

OpenWiki supports the following providers:.

Provider	Credential	Notes
`openai`	`OPENAI_API_KEY`	Optional `OPENAI_BASE_URL` for OpenAI-compatible gateways that expose the Responses API
`openai-chatgpt`	ChatGPT OAuth tokens	Sign in with ChatGPT; usage draws on Plus/Pro/Team Codex allowance
`copilot`	GitHub CLI session or `COPILOT_API_KEY`	Optional `COPILOT_BASE_URL`. CI needs an OAuth token, not a classic PAT
`openrouter`	`OPENROUTER_API_KEY`	Optional `OPENWIKI_OPENROUTER_PROVIDER_ONLY` allowlist
`anthropic`	`ANTHROPIC_API_KEY`	Optional `ANTHROPIC_BASE_URL`
`gemini`	`GEMINI_API_KEY`	Google AI Studio
`gemini-enterprise`	Google ADC + `GOOGLE_CLOUD_PROJECT`	Optional `GOOGLE_CLOUD_LOCATION` (defaults to `global`)
`bedrock`	AWS credentials + region	Explicit Bedrock keys or the AWS SDK default chain
`baseten`	`BASETEN_API_KEY`	Optional `BASETEN_BASE_URL`
`fireworks`	`FIREWORKS_API_KEY`	Optional `FIREWORKS_BASE_URL`
`nebius`	`NEBIUS_API_KEY`	Nebius Token Factory
`nvidia`	`NVIDIA_API_KEY`	Optional `NVIDIA_BASE_URL`
`openai-compatible`	`OPENAI_COMPATIBLE_API_KEY`	Requires `OPENAI_COMPATIBLE_BASE_URL` and a custom model ID

Credentials and defaults are stored in ~/.openwiki/.env. Process environment values take priority over file values. You can set the active provider and model with:

OPENWIKI_PROVIDER=openai
OPENWIKI_MODEL_ID=gpt-5.6-terra

Provider retries

Override retries after the first provider request:

OPENWIKI_PROVIDER_RETRY_ATTEMPTS=3

The value must be a positive integer. If unset, OpenWiki defaults to 3 retries.

GitHub Copilot

To use GitHub Copilot:

Select GitHub Copilot during openwiki --init. If you have an active GitHub CLI session, OpenWiki can reuse it. Otherwise, run gh auth login from the credential prompt.
Choose a model (for example gpt-5.5).

OpenWiki leaves the GitHub CLI token in the GitHub CLI credential store. It does not copy that token into ~/.openwiki/.env. For CI or headless environments without a GitHub CLI session, set COPILOT_API_KEY to a GitHub OAuth token. Personal Access Tokens (classic or fine-grained) are rejected by the Copilot API for third-party integrations.

OPENWIKI_PROVIDER=copilot
OPENWIKI_MODEL_ID=gpt-5.5

The openai-chatgpt provider calls OpenAI’s Codex backend using your ChatGPT subscription instead of a metered API key:

OPENWIKI_PROVIDER=openai-chatgpt openwiki code --init

The wizard opens the OpenAI auth page in your browser (and prints the URL for headless use). After sign-in, OpenWiki stores managed OAuth tokens in ~/.openwiki/.env and refreshes the access token automatically. Treat the refresh token like a password.

Gemini Enterprise (Vertex AI)

The gemini-enterprise provider uses Google Application Default Credentials. No API key is required:

OPENWIKI_PROVIDER=gemini-enterprise
GOOGLE_CLOUD_PROJECT=your-gcp-project
GOOGLE_CLOUD_LOCATION=global

The credentials need Vertex AI access (roles/aiplatform.user), and the models you use must be enabled in Model Garden. Partner/open-weight (MaaS) models are region-specific, so set GOOGLE_CLOUD_LOCATION explicitly when using them.

AWS Bedrock

OPENWIKI_PROVIDER=bedrock
BEDROCK_AWS_ACCESS_KEY_ID=your-access-key-id
BEDROCK_AWS_SECRET_ACCESS_KEY=your-secret-access-key
BEDROCK_AWS_REGION=us-east-1
OPENWIKI_MODEL_ID=anthropic.claude-sonnet-5

When explicit Bedrock credentials are not set, OpenWiki uses the AWS SDK default credential provider chain. Paste the Bedrock model ID directly. Some newer models require a cross-region inference profile ID (for example us.anthropic.claude-sonnet-5) instead of the bare model ID.

OpenAI-compatible endpoints

Use the openai-compatible provider for gateways or local servers that expose OpenAI-compatible chat completions:

OPENWIKI_PROVIDER=openai-compatible
OPENAI_COMPATIBLE_API_KEY=your-gateway-key
OPENAI_COMPATIBLE_BASE_URL=https://your-gateway.example.com/v1
OPENWIKI_MODEL_ID=your-gateway-model-name

Local examples such as Ollama (http://localhost:11434/v1) and LM Studio (http://localhost:1234/v1) use the same pattern. OpenWiki still requires OPENAI_COMPATIBLE_API_KEY even when the local server ignores the key value.

OpenRouter provider pinning

When OpenRouter serves a model through multiple upstream providers, restrict routing:

OPENWIKI_PROVIDER=openrouter
OPENROUTER_API_KEY=your-key
OPENWIKI_OPENROUTER_PROVIDER_ONLY=Novita

Modes

Provider retries

GitHub Copilot

Gemini Enterprise (Vertex AI)

AWS Bedrock

OpenAI-compatible endpoints

OpenRouter provider pinning

See also

​Provider retries

​GitHub Copilot

​OpenAI (ChatGPT login)

​Gemini Enterprise (Vertex AI)

​AWS Bedrock

​OpenAI-compatible endpoints

​OpenRouter provider pinning

​See also

Provider retries

GitHub Copilot

OpenAI (ChatGPT login)

Gemini Enterprise (Vertex AI)

AWS Bedrock

OpenAI-compatible endpoints

OpenRouter provider pinning

See also