Venice key

Bring your own Venice key to reach many open models (Llama, Qwen, DeepSeek, Mistral and more) through one OpenAI-compatible endpoint. Venice serves open-weight models, not the closed flagships (Claude, GPT, Gemini), which stay with their own vendors.

What it unlocks

• AI sentiment, category and priority on each mention instead of the free offline word-list scorer.
• A one-time background re-score of your existing mentions when a Venice model starts powering filtering.
• Its models can join your AI share-of-voice comparison, several at once.

Venice's model list is fetched live from its API, so the model picker always reflects what your key can use, with current prices and which models support structured output and reasoning effort.

Get your API key

1. Sign in at Venice and open API settings.
2. Create an API key and copy it.

Add it in BackTalk

1. Go to Settings and find the Venice card under AI providers.
2. Pick a model and paste your key.
3. Save. BackTalk sends one tiny test request to confirm the key and model, then stores the key encrypted.
4. Under What runs each task, point signal filtering and the models-to-compare set at the Venice models you want. One key can run different models for different jobs.

Models & cost

Billed by Venice directly at their token rates, with no markup from BackTalk. The picker shows each model's current input / output price. Only models that return structured output can run filtering; reasoning models add a low / medium / high effort control.

Troubleshooting

• "The provider rejected that API key." Wrong or revoked key. Create a fresh key in Venice API settings and re-paste.
• "That model isn't available on this key." Your Venice account can't use that model. Pick another from the list.
• Key check failed. Usually no credit on the Venice account. Add credit, then retry.

Your key stays private. It's encrypted at rest and only decrypted server-side when a call runs. It is never returned to your browser and never logged. Settings shows only a masked hint.