LLMCogito (Decart) API pricing
2 Cogito (Decart) models. Source: https://cogito.decart.ai/pricing
- Provider type
- Inference host
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- US (outside EU) · Operated by Decart.AI, Inc.: the Cogito API Service Terms (last updated 2026-06-01) name Decart.Ai, Inc. as the contracting party (New York law); Decart Terms of Use give the address 1007 North Orange Street, 10th Floor, Wilmington, DE 19801, USA. Checked 2026-10-26. · legal source
- EU data residency
- unknown
- Residency notes
- Standard tier regions not published. Enterprise page: EU-region clusters available on enterprise contracts only; zero retention by default. Runs on AWS Trainium and NVIDIA Blackwell.
- Residency source
- https://cogito.decart.ai/enterprise
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
2 of 2 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Cogito (Decart) Inference host | Kimi K2.6 | $0.66 | $3.41 | $0.144 | $1.35 | — | unknown |
| Cogito (Decart) Inference host | GLM-5.2 | $1.20 | $4.00 | $0.20 | $1.90 | — | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Rows marked “Calculated from credits” have no official per-token price; see how they are calculated. Click a header to sort.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.