Model Costs

[exotic lichen]

This tool charges based on "AI Requests" Do different models, consume different number of AI requests? (ie. Sonner vs Gemini vs Opus, etc)

[tidal aspen]

Hi @exotic lichen. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

---

Yes, different models in Warp can consume a different number of AI requests per interaction. According to Warp’s documentation, each time you submit a prompt, you consume at least one AI request, but more complex interactions—such as those involving multiple tool calls, large context, or file attachments—may use multiple requests. Importantly, the number of requests used can also vary depending on the model: “better models use more” requests, as confirmed by a Warp engineer. However, Warp does not publish a detailed list of how many requests each specific model (e.g., Sonnet, Gemini, Opus) consumes per interaction. The exact number of requests is determined by several factors, including the model’s token cost and the complexity of the interaction.

So, while the request cost is not strictly one-to-one across all models, the specifics are not fully disclosed. If you want to minimize request usage, using simpler models or less context may help, but the precise breakdown per model is not available publicly at this time. You can monitor your usage in the app under Settings > Billing and usageWhat counts as an AI request?, and see related discussion from Warp engineers on GitHub for more context on model request costsPotential Inconsistency: Premium Model Charges Despite Basic Model Selection.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: