Tresor now runs across five providers in total, with broader overlap on several of the most used models. That gives the platform more room to recover when one upstream slows down, rate-limits, or has a bad day.

The benefit is simple: more overlap means better fallback. Instead of a popular model depending on a single route, Tresor can now keep more requests moving through alternative routes while maintaining the transparency you are used to.

More ways through

• Broader model overlap - More of the popular models now exist on more than one provider, which reduces single-route risk.

• Stronger fallback behavior - When one upstream has trouble, Tresor has more chances to route around the issue before your app feels it.

• Better availability in practice - This wider provider layer helps improve the consistency you see in day-to-day use, not just in theory.

Built for production workloads

This matters most for products and agents that need steady behavior under real traffic. With five providers in the pool, Tresor is better positioned to absorb isolated provider problems while keeping the same private, attested execution model.

Privacy: Expanding fallback does not change the zero-access design. Your requests stay inside the same sealed, confidential path.

If you rely on Tresor for live features or long-running agents, this is the kind of infrastructure change that quietly pays off every day.

Tresor now supports prompt caching across multiple providers and models, including GLM 5.2 and Kimi K2.6. If your workflow sends the same large context over and over, you no longer have to pay full price every time.

That matters a lot for agentic coding. Coding agents tend to resend the same repository map, instructions, diffs, and tool state on every turn. With caching on supported routes, that repeated context becomes much cheaper, which makes confidential coding workflows far more competitive on price.

Big context, smaller bills

• Reuse repeated context - Large prompts, repo summaries, and long instructions can be treated as cached input instead of billed like brand-new input every turn.

• Run longer coding loops - Refactor, test, fix, and retry cycles become much easier to justify when the shared context is cheaper to carry forward.

• Keep model choice open - You can get the pricing benefit on more than one route, instead of tying your workflow to a single model or provider.

Better economics for private agents

Private workflows usually need more context, not less. Prompt caching helps you keep that context inside Tresor's sealed environment without turning every follow-up into a full-price request.

Privacy: Cached context keeps the same zero-access, sealed-environment path as the rest of the Tresor API.

If you're building coding agents, background automations, or long multi-step analysis flows, this is one of the most practical API upgrades yet.

Two useful upgrades just landed in the Tresor API. You can now choose a custom timeout for each request, and you can now use GLM 5.2, a model that feels genuinely competitive for coding-heavy work.

If you build user-facing products, both updates matter for the same reason: you get more control over how your product feels, and more choice in how strong the output can be.

Set the pace for each request

The new custom timeout option gives you more control over the experience you want to deliver.

• Fail faster when speed matters — For interactive features, you can stop waiting sooner and move to the next path instead of leaving users hanging.

• Be more patient when the task is worth it — For deeper or longer-running work, you can allow extra time when better output matters more than immediate speed.

• Tune the API to the job — The same API can now feel tighter for live experiences and more flexible for background workflows.

A serious new model for code

GLM 5.2 is now available in the API, and it is a strong addition for teams that do a lot of coding, refactoring, and debugging.

• Strong coding capability — On coding-heavy tasks, GLM 5.2 feels in the same league as GPT 5.4 xhigh.

• More choice without compromise — You have another high-end model to reach for when code quality is the priority.

• Useful across mixed tasks — It also holds up well when a request needs code, reasoning, and a clear written explanation in the same response.

If you want a third-party snapshot of where it sits, Artificial Analysis has a useful comparison.

🔒 Privacy: Like every model and API feature on Tresor, these upgrades keep the same zero-access, sealed-environment design.

If you want tighter control over response timing or a new top-tier coding model to test, both are ready to use now.

You can now send audio to the Tresor API and get back clean transcripts. That makes it easier to turn meeting recordings, voice notes, and interviews into text you can store, search, review, or feed into your own workflows.

For now, this is an API-only capability. Audio upload is not in the chat workspace yet, but it is something we're already thinking about as we plan the next layer of the product.

Audio in, transcript out

• Built for existing API workflows — If you already use the Tresor API, transcription fits into the same product with the same API keys, dashboard, receipts, and usage tracking.

• Useful for real-world audio — Send voice notes, call snippets, or longer recordings and get text back in a format that's easy to work with.

• Clear operational visibility — Transcription requests show up in usage and billing like the rest of your API activity, so they are easier to monitor and reconcile.

🔒 Privacy: Your audio files are encrypted and processed inside the sealed environment — Tresor never sees the contents.

If transcription belongs in your workflow today, you can use it through the API now. If Drop us a line, if you need it in chat ASAP, we’ll see what we can do. ;-)

This is a big milestone for Tresor, and an important one for customers who want to build on private AI without lowering their standards. You can now build directly on top of Tresor with an OpenAI-compatible API, while keeping the privacy, sealed execution, and proof that make the product different.

OpenAI-compatible from day one

Point your existing OpenAI client at Tresor, use a tr- API key, and start making requests. The API supports streaming out of the box, and newer capabilities like tools and reasoning content are there from the start.

🔒 Privacy: The API keeps the same zero-access design people expect from Tresor.

A proper product, not just an endpoint

The new API dashboard gives you the basics you actually need on day one:

• API keys — Create and revoke keys from the dashboard, with clear prefixes and last-used visibility.

• Usage tracking — See spend over time, break it down by model, inspect individual rows, and export usage as CSV.

• Billing — Add credits, save payment methods, download invoices, and turn on auto-recharge.

• Operational emails — Get clearer alerts for low balance, depleted balance, payment failures, and API key activity.

Verifiable by default

Every API response can be tied to a signed receipt you can fetch and verify later. That receipt freezes the routed model, cryptographic fingerprints of the request and response, and the attestation trail behind the call.

If you want a stronger guarantee than TLS, tresor-attest lets your client verify it's talking to the genuine Tresor workload before any payload leaves your process.

Also in this launch

• OpenAI SDK examples — Quick-start docs for curl, Python, Node.js, and Go.

• Receipts in the dashboard — Usage entries make it easier to inspect verification details and timestamps.

• First-release polish — Better invoice empty states and fewer rough edges when creating new API keys.

This is the first release of the Tresor API, and it sets the baseline for what we want this product to feel like: easy to adopt, easy to operate, and much easier to trust.

Getting into Tresor now feels more dependable, and the proof behind each conversation is clearer once you're in. This release focuses on the first-run experience, verification, and everyday chat reliability.

Faster signup and email verification

• Cleaner email confirmation — Password setup and redirects now work more reliably after you verify your email.

• Better recovery when verification gets interrupted — If signup stalls, Tresor is better at getting you back on track instead of leaving you in a dead end.

• Invite-aware verification — Joining a workspace from an invite now completes more reliably and lands you in the right workspace.

• Lightweight bot protection — Signup and resend flows now include better abuse protection to keep the experience fast for real users.

• More reliable sign out — Leaving Tresor is less likely to get stuck in an awkward half-signed-in state.

Clearer proof in Private by design

The Private by design panel now does a better job surfacing the full verification path, including router and downstream checks where available.

If you stop a response early, Tresor is also better at preserving the proof behind what was generated instead of dropping into an unclear verification state.

🔒 Privacy: These improvements add clearer evidence, not more collection. Your messages and uploads stay private.

Improvements & fixes

• Better file uploads — Attachments are handled more robustly, with clearer failures when something goes wrong.

• Sidebar updates immediately — New chats now appear more reliably in the sidebar.

• Better stop behavior — Stopping a reply mid-stream is more reliable and less likely to leave verification in an odd state.

A smoother path from signup to first conversation, with stronger evidence all the way through.

When you opened the Private by design panel before today, Tresor showed you a hardware-signed proof that your message was processed inside a sealed environment. That proof now carries one extra piece of information that matters: which exact version of Tresor was running inside that sealed environment.

What changed

Every sealed environment now signs its identity — the workload name, the release version, and the exact image it was built from — and that identity is folded into the same hardware-signed proof you already see. The verifier that releases keys to the environment refuses to release them unless that identity check passes too. There is no longer a separate, after-the-fact check that could be skipped or bypassed.

What this means for you

• The proof you can inspect in the Private by design panel now binds the answer you got to a specific, signed Tresor build — not just to "some Tresor running on sealed hardware."

• A compromised host or a swapped container cannot quietly pass itself off as a genuine Tresor release. Without a release-signed identity for that build, the sealed environment is not allowed to start handling your traffic at all.

🔒 Privacy: This change is about adding evidence, not about collecting more data. Nothing about your messages or files is included in the proof.

For the technically curious

The full architecture, threat model, and verifier algorithm are public. See the Attestation Pinning guide and the open-source verifier SDKs at tresor-attest (Go, Python, TypeScript).

Safer accounts, clearer billing

This update makes the day-to-day basics feel more solid. Your account is easier to protect, billing is easier to stay on top of, and one of our strongest models just got better with images.

Two-Factor Authentication

You can now enable Two-Factor Authentication for your Tresor account. If you use Unlock encrypted chats, that flow is more consistent too, so getting back into protected conversations feels less fragile.

Better billing visibility

• Payment methods and invoices in one place — The billing page now does a better job surfacing saved payment methods, invoice history, and enterprise invoice status.

• Low-balance and payment alerts — Tresor now sends clearer emails for low balance, auto-recharge activity, payment failures, and API key events, so you get fewer surprises.

• Cleaner billing links — Billing-related emails and dashboard links now take you straight to the right place.

Better model support

• Gemma 4 31B now supports images — You can use it for image-aware work, not just text.

• Recommended models are easier to spot — Strong default picks are surfaced more clearly in the interface.

Like every model on Tresor, image processing stays inside the same secure, sealed environment.

Improvements & fixes

• Better French translations — A round of copy improvements across the chat experience.

• Smoother unlock flow — Unlocking encrypted chats is more reliable.

Small improvements, less friction. More on the way.