Skip to main content

Google Gemini

Fabric supports Google Gemini as a native provider using the Google AI Studio / Gemini API — not the OpenAI-compatible endpoint. This lets Fabric translate its internal OpenAI-shaped message and tool loop into Gemini's native generateContent API while preserving tool calling, streaming, multimodal inputs, and Gemini-specific response metadata.

Prerequisites​

  • Google AI Studio API key — create one at aistudio.google.com/apikey
  • Billing-enabled Google Cloud project — recommended for agent use. Gemini's free tier is too small for long-running agent sessions because Fabric may make several model calls per user turn.
  • Fabric installed — no extra Python package is required for the native Gemini provider.
API key path

Set GOOGLE_API_KEY or GEMINI_API_KEY. Fabric checks both names for the gemini provider.

Quick Start​

# Add your Gemini API key
echo "GOOGLE_API_KEY=..." >> ~/.fabric/.env

# Select Gemini as your provider
fabric model
# → Choose "More providers..." → "Google AI Studio"
# → Fabric checks your key tier and shows Gemini models
# → Select a model

# Start chatting
fabric chat

If you prefer direct config editing, use the native Gemini API base URL:

model:
  default: gemini-3-flash-preview
  provider: gemini
  base_url: https://generativelanguage.googleapis.com/v1beta

Configuration​

After running fabric model, your ~/.fabric/config.yaml will contain:

model:
  default: gemini-3-flash-preview
  provider: gemini
  base_url: https://generativelanguage.googleapis.com/v1beta

And in ~/.fabric/.env:

GOOGLE_API_KEY=...

Native Gemini API​

The recommended endpoint is:

https://generativelanguage.googleapis.com/v1beta

Fabric detects this endpoint and creates its native Gemini adapter. Internally, Fabric still keeps the agent loop in OpenAI-shaped messages, then translates each request to Gemini's native schema:

  • messages[] → Gemini contents[]
  • system prompts → Gemini systemInstruction
  • tool schemas → Gemini functionDeclarations
  • tool results → Gemini functionResponse parts
  • streaming responses → OpenAI-shaped stream chunks for the Fabric loop
Gemini 3 thought signatures

For Gemini 3 tool use, Fabric preserves the thoughtSignature values attached to function-call parts and replays them on the next tool turn. That covers the validation-critical path for multi-step agent workflows.

Gemini 3 may also attach thought signatures to other response parts. Fabric's native adapter is optimized for agent tool loops today, so it does not yet replay every non-tool-call signature with full part-level fidelity.

Prefer the Native Endpoint​

Google also exposes an OpenAI-compatible endpoint:

https://generativelanguage.googleapis.com/v1beta/openai/

For Fabric agent sessions, prefer the native Gemini endpoint above. Fabric includes a native Gemini adapter so it can map multi-turn tool use, tool-call results, streaming, multimodal inputs, and Gemini response metadata directly onto Gemini's generateContent API. The OpenAI-compatible endpoint is still useful when you specifically need OpenAI API compatibility.

If you previously set GEMINI_BASE_URL to the /openai URL, remove it or change it:

GEMINI_BASE_URL=https://generativelanguage.googleapis.com/v1beta

Available Models​

The fabric model picker shows Gemini models maintained in Fabric's provider registry. Common choices include:

ModelIDNotes
Gemini 3.1 Pro Previewgemini-3.1-pro-previewMost capable preview model when available
Gemini 3 Pro Previewgemini-3-pro-previewStrong reasoning and coding model
Gemini 3 Flash Previewgemini-3-flash-previewRecommended default balance of speed and capability
Gemini 3.1 Flash Lite Previewgemini-3.1-flash-lite-previewFastest / lowest-cost option when available

Model availability changes over time. If a model disappears or is not enabled for your key, run fabric model again and pick one from the current list.

Model IDs

Use Gemini's native model IDs such as gemini-3-flash-preview, not OpenRouter-style IDs like google/gemini-3-flash-preview, when provider: gemini.

Latest Aliases​

Google publishes moving aliases for the Pro and Flash Gemini families. gemini-pro-latest and gemini-flash-latest are useful when you want Google to advance the model automatically without changing your Fabric config.

AliasCurrently tracksNotes
gemini-pro-latestLatest Gemini Pro modelBest when you want Google's current Pro default
gemini-flash-latestLatest Gemini Flash modelBest when you want Google's current Flash default
model:
  default: gemini-pro-latest
  provider: gemini
  base_url: https://generativelanguage.googleapis.com/v1beta

If you need strict reproducibility, prefer explicit model IDs such as gemini-3.1-pro-preview or gemini-3-flash-preview.

Gemma via the Gemini API​

Google also exposes Gemma models through the Gemini API. Fabric recognizes these as Google models, but hides very low-throughput Gemma entries from the default model picker so new users do not accidentally select an evaluation-tier model for a long-running agent session.

Useful evaluation IDs include:

ModelIDNotes
Gemma 4 31B ITgemma-4-31b-itLarger Gemma model; useful for compatibility and quality evaluation
Gemma 4 26B A4B ITgemma-4-26b-a4b-itSmaller active-parameter variant when available

These models are best treated as evaluation options on Gemini API keys. Google's Gemma API pricing is free-tier-only and the usage caps are low compared with production Gemini models, so sustained Fabric agent use should normally move to a paid Gemini model, a self-hosted deployment, or another provider with appropriate quota.

To use a Gemma model that is hidden from the picker, set it directly:

model:
  default: gemma-4-31b-it
  provider: gemini
  base_url: https://generativelanguage.googleapis.com/v1beta

Switching Models Mid-Session​

Use the /model command during a conversation:

/model gemini-3-flash-preview
/model gemini-flash-latest
/model gemini-3-pro-preview
/model gemini-pro-latest
/model gemma-4-31b-it
/model gemini-3.1-flash-lite-preview

If you have not configured Gemini yet, exit the session and run fabric model first. /model switches among already-configured providers and models; it does not collect new API keys.

Diagnostics​

fabric doctor

The doctor checks:

  • Whether GOOGLE_API_KEY or GEMINI_API_KEY is available
  • Whether configured provider credentials can be resolved

Gateway (Messaging Platforms)​

Gemini works with all Fabric gateway platforms (Telegram, Discord, Slack, WhatsApp, LINE, Feishu, etc.). Configure Gemini as your provider, then start the gateway normally:

fabric gateway setup
fabric gateway start

The gateway reads config.yaml and uses the same Gemini provider configuration.

Troubleshooting​

"Gemini native client requires an API key"​

Fabric could not find a usable API key. Add one of these to ~/.fabric/.env:

GOOGLE_API_KEY=...
# or
GEMINI_API_KEY=...

Then run fabric model again.

"This Google API key is on the free tier"​

Fabric probes Gemini API keys during setup. Free-tier quotas can be exhausted after a handful of agent turns because tool use, retries, compression, and auxiliary tasks may require multiple model calls.

Enable billing on the Google Cloud project attached to your key, regenerate the key if needed, then run:

fabric model

"404 model not found"​

The selected model is not available for your account, region, or key. Run fabric model again and pick another Gemini model from the current list.

Gemma model is not shown in fabric model​

Fabric may hide low-throughput Gemma models from the picker by default. If you intentionally want to evaluate one, set the model ID directly in ~/.fabric/config.yaml.

"429 quota exceeded" on Gemma​

Gemma models exposed through the Gemini API are useful for evaluation, but their Gemini API free-tier caps are low. Use them for compatibility testing, then switch to a paid Gemini model or another provider for sustained agent sessions.

OpenAI-compatible endpoint is configured​

Check ~/.fabric/.env for:

GEMINI_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai/

Change it to the native endpoint or remove the override:

GEMINI_BASE_URL=https://generativelanguage.googleapis.com/v1beta

Tool calling fails with schema errors​

Upgrade Fabric and rerun fabric model. The native Gemini adapter sanitizes tool schemas for Gemini's stricter function-declaration format; older builds or custom endpoints may not.