v3.10.2

Released October 19, 2026

Adds two new models — Claude Haiku 5.5 and Google Gemini 4 Argon — and lowers the cost of cached input on Claude Sonnet 5.5 (government).

Confirming this release. Claude Haiku 5.5 and Google Gemini 4 Argon appear in the model picker. New models are visible only when enabled for your deployment, within your compliance boundary, and for your organization — if you don’t see one, contact your Ask Sage administrator.

🚀 New models

• Claude Haiku 5.5 — commercial through DoD. Anthropic’s fast Claude Haiku 5.5 is now available from commercial through DoD (IL5) deployments, with a 1M‑token context window, vision input, tool use, and prompt caching. It’s flagged for CUI / ITAR / EAR data controls.
• Google Gemini 4 Argon — commercial through DoD. Google’s flagship Gemini 4 Argon is now available from commercial through DoD deployments, with a 1M‑token context window. It’s flagged for CUI / ITAR / EAR data controls.

⚡ Improvements & fixes

• Lower cost for cached input on Claude Sonnet 5.5 (government). The cache‑read rate for Claude Sonnet 5.5 on government deployments has been reduced by half, so reusing cached context costs less.

🔒 Security & platform

Ask Sage services are delivered as FIPS‑hardened, digest‑pinned, and cosign‑signed images within the FedRAMP Class D authorization boundary, and are continuously rebuilt against the latest patched base images as part of Ask Sage’s continuous‑monitoring commitment.