Fireworks
Fast open-model inference. Bring your own key; nothing is billed by us.
Cette page est rédigée en anglais. Les termes qu'elle explique sont ceux que l'on cherche en anglais, et un terme technique traduit est un terme différent.
What the harness already knows
| Provider id | fireworks |
| Base URL | https://api.fireworks.ai/inference/v1 |
| Protocol | OpenAI-compatible chat completions |
| API key | FIREWORKS_API_KEY |
| Model discovery | Yes — the model list is asked of the endpoint rather than shipped. |
Connecting it
The endpoint above is built in, so there is nothing to configure. Put the key in the environment and the provider appears in the model picker:
export FIREWORKS_API_KEY="..."Keys are issued by Fireworks — where to get one.
Pointing it somewhere else
A regional host, a gateway, or a server of your own. Overrides in ~/.oharness/config.json are field level, so changing the endpoint does not mean restating the rest of the provider — this is the whole block, shown holding the default so the shape is clear:
{
"providers": {
"fireworks": {
"baseUrl": "https://api.fireworks.ai/inference/v1"
}
}
}What you get either way
The same agent loop, the same tools, the same MCP servers and the same permission rules, whichever provider is underneath — and switching between them mid-session converts nothing, because history is never stored in a vendor’s shape. What an agent harness is covers why that is the hard part, and the providers reference covers the catalogue itself.