RutaAPI uses prepaid credits. Model rates vary by provider, model, and usage type. This page shows public examples for commonly used model categories. The developer dashboard shows the latest available rates for all enabled models after sign-in.
Each API request deducts credits from your prepaid balance based on the model used, number of input tokens, and number of output tokens. Rates are transparent — sign in to the dashboard to view the exact rate for each model before making a request.
| Model category | Example models | Input price | Output price | Best for | Exact live rates |
|---|---|---|---|---|---|
| Low-cost chat | Small chat models | from $0.10 / 1M tokens | from $0.40 / 1M tokens | Testing, agents, simple apps | Dashboard |
| General chat | General-purpose chat models | Varies by model | Varies by model | Production apps, assistants | Dashboard |
| Advanced reasoning | Larger reasoning models | Varies by model | Varies by model | Coding, complex tasks | Dashboard |
| Embeddings | Embedding models | Input-based pricing | — | Search, RAG, memory | Dashboard |
| Multimodal | Image/audio capable models | Varies by modality | Varies by modality | Media workflows | Dashboard |
Prices shown above are public examples for reference only and may change based on enabled routes and upstream providers. The developer dashboard shows the current enabled model rates before use. Exact rates are displayed per request in the dashboard after signing in.