Skip to main content
FireConnect routes OpenCode through Fireworks AI models. See the FireConnect overview for install and CLI basics.

​
Prerequisites

​
Enable Fireworks routing

Restart OpenCode after enabling, then confirm routing:

​
Using Fire Pass

Use your fpk_... key during login or with --api-key:
FireConnect detects Fire Pass keys and defaults OpenCode to glm-fast-latest.

​
Default model

OpenCode routes a single default model (no opus/sonnet/haiku alias slots). The default is glm-fast-latest, written to config as fireworks-ai/glm-fast-latest. Short model IDs like glm-5p1 are expanded to full Fireworks paths (for example, accounts/fireworks/models/glm-5p1).

​
What gets written

FireConnect merges a fireworks-ai provider block into ~/.config/opencode/opencode.json:
  • An OpenAI-compatible adapter pointed at https://api.fireworks.ai/inference/v1
  • A default model set to fireworks-ai/<model-id> (for example, fireworks-ai/glm-fast-latest)
  • options.apiKey as a baked plaintext literal (file mode 0600)
  • The preferred serverless catalog registered in the provider’s models for OpenCode’s /model picker
FireConnect snapshots your original opencode.json before the first change. The snapshot lives in ~/.fireconnect/opencode/. Running fireconnect opencode off restores the file byte-for-byte. OpenCode’s auth.json is never touched.

​
Browsing and picking models

fireconnect model list resolves the API key from the OS keychain or global config. Fire Pass keys (fpk_...) show Fire Pass-supported routers only and cannot select firerouter. Standard keys include firerouter.

​
FireRouter

Pass --anthropic-api-key sk-ant-... when your workspace does not have Anthropic BYOK provisioned server-side.

​
CLI reference

Run fireconnect opencode help for all options.

​
Switch models

​
Turn off Fireworks routing

This restores your previous opencode.json from the backup in ~/.fireconnect/opencode/.

​
Use a non-default config file

​
Fireworks on Microsoft Foundry

OpenCode supports Fireworks on Microsoft Foundry (CLI: --provider azure or on --azure). See the FireConnect overview and Microsoft Foundry integration guide for portal setup.

​
Configure and enable

One-off routing without changing global config:
Pass your Foundry model with --model (for example, FW-GLM-5.2), not a Fireworks serverless short ID like glm-latest.

​
What gets written

FireConnect adds a fireworks-azure provider labeled Fireworks on Microsoft Foundry to opencode.json, pointed at your Foundry OpenAI-compatible endpoint (.../openai/v1). The default model reference becomes fireworks-azure/FW-GLM-5.2. Use fireconnect model list only for browsing Fireworks serverless models on the direct gateway path. With Foundry, switch models with on --model FW-GLM-5.2.

​
Turn off Foundry routing

To switch back to the Fireworks gateway, change the global provider and re-enable:
To remove FireConnect entirely and restore your original opencode.json:
See Turn off Foundry routing for details on global config behavior and uninstall.

​
Built-in provider connection

OpenCode also supports connecting to Fireworks directly without FireConnect:
  1. Type /connect in OpenCode and search for fireworks.ai
  2. Paste your Fireworks API key and press Enter
  3. Type /models and select a model (for Fire Pass, choose a supported model such as GLM Fast Latest)

​
Source

FireConnect is open source: github.com/fw-ai/fireconnect