Cognition
SWE-1.6
SWE-1.6 is a Cognition model with Not verified context, Not verified in / Not verified out per million tokens, last verified October 2, 2026. Open weights: not verified. Status: Superseded; the current pick is SWE-2. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.
A previous-generation software-engineering agent model, introduced with an emphasis on interactive model behaviour.
Recorded profile verification October 2, 2026Individual provider fields may changeAccess: restricted — Current docs list SWE-1.6; the April general-availability announcement does not guarantee today's account entitlement.
| Specification | SWE-1.6 |
|---|---|
| Provider | Cognition |
| Tier | Balanced |
| Context window | Not verifiedUnverified |
| Max output | Not verifiedUnverified |
| Input / 1M tokens | Not verifiedUnverified |
| Output / 1M tokens | Not verifiedUnverified |
| Weights | Not verifiedUnverified |
| Parameters | Not verifiedUnverified |
| Reasoning levels | Not verifiedUnverified |
| Modalities | text |
| Released | April 7, 2026 |
Pricing tiers: In-product model access and billing vary by plan/account. Exact current model-specific rates were not recovered; the authenticated List Models response is the account source of truth. Historical free/speed offers are not current generic API prices.
Best for
- Comparing an enabled previous-generation Devin agent
Watch out
Source receipts
Catalog figures for this model were checked against the following sources.
- Current in-product model roles and access (accessed 2026-10-02)
- Publisher announcement / model identity (accessed 2026-10-02)
- Account-dependent List Models response contract (accessed 2026-10-02)
- Quota and extra usage (accessed 2026-10-02)
Common questions
SWE-1.6
Answered from the verified figures on this page rather than general guidance.