---
title: "Kaeso 0.7: rerank, batches and decisions, 23 more providers, and guardrails"
description: "Kaeso 0.7.0 is out. Apps rerank, run batches, store Responses and ask decision models through the gateway, 23 more providers are built in, organizations add guardrails, SCIM, webhooks and their own currency, and installs get lighter and run on Kubernetes. Here is what changed and how to update."
url: https://kaeso.app/articles/kaeso-0-7
markdown: https://kaeso.app/articles/kaeso-0-7.md
language: en
alternates:
  de: https://kaeso.app/de/articles/kaeso-0-7.md
  zh-CN: https://kaeso.app/zh-CN/articles/kaeso-0-7.md
published: 2026-11-21
authors:
  - Kaeso Team
tags:
  - release
  - gateway
  - providers
  - security
image: https://kaeso.app/articles/kaeso-0-7/cover.jpg
index: https://kaeso.app/llms.txt
---

# Kaeso 0.7: rerank, batches and decisions, 23 more providers, and guardrails

Kaeso 0.7.0 is out. Apps rerank, run batches, store Responses and ask decision models through the gateway, 23 more providers are built in, organizations add guardrails, SCIM, webhooks and their own currency, and installs get lighter and run on Kubernetes. Here is what changed and how to update.

> Every page, article and docs page of Kaeso is listed in https://kaeso.app/llms.txt.

- Published: 21 November 2026
- Reading time: 7 min
- Author: Kaeso Team

Your apps already talk to more than one model. One team calls OpenAI, another Claude on Bedrock, a third ranks search results with Cohere, and every one of them has its own keys, its own bills and its own idea of what a log is. Kaeso is the open-source gateway you run yourself that puts all of it behind one address: one set of keys, limits, logs and costs, whichever provider answers.

Kaeso 0.7.0 is out, with nearly 300 pull requests merged since 0.6.0. It takes Kaeso past chat and media to every kind of request apps send to models, builds in 23 more providers, and adds what a whole company needs to run one gateway for many teams. Watch the 49-second film, then try each part yourself in the [live demo](https://demo.kaeso.app).

![The Kaeso 0.7.0 release film, 49 seconds: decision models, guardrails, key pools, model lifecycle, webhooks, SCIM and SSO groups, the new built-in providers, rerank, batches and Helm in the console](https://kaeso.app/articles/kaeso-0-7/film.mp4 "Kaeso 0.7 in 49 seconds.")

## Ask models more than chat

Chat is only part of what apps send. They also rank search results, run thousands of requests overnight and ask models to decide things. In 0.7 all of that goes through Kaeso, with the same keys, limits, logs and costs as every chat request:

- **Decisions.** Ask a model a typed question, yes or no, a choice, a score or a box, and get every answer back with its probability instead of a sentence to parse. Apps use OpenAI's Decisions API, TypeSafe's System One API or Gemini's Decisions API, and Kaeso translates between the three, so an app written for one asks the models of the others.
- **Rerank** at `/v1/rerank` and `/v2/rerank` in Cohere's format, answered by Cohere's Rerank 5 models and by Voyage AI and Jina AI.
- **Batches** through OpenAI's Batch API, checked against the app's key and charged at the batch price.
- **Stored responses**: Responses apps store and continue responses at OpenAI, where the organization and project allow it.

![The Playground asking Jev 1.14 and GPT-6 Sol the same decision: refund yes or no, which team, and how urgent, each answer with its probabilities](https://kaeso.app/articles/kaeso-0-7/still-decision-models.png "Decision models in the Playground: typed questions, answered with probabilities.")

The Playground asks decision models too. Put two side by side, ask "My parcel arrived broken; I want my money back," and see in a glance which one is surer that it's a refund, and which team should take it.

![A rerank request with curl to /v1/rerank: a query, three documents and top_n 2](https://kaeso.app/articles/kaeso-0-7/still-rerank-batches.png "Rerank in Cohere's format, beside batches and the Helm chart.")

## 50 providers, each one key away

Amazon Bedrock, Azure, Cloudflare AI Gateway, Standard Compute, Perplexity, TypeSafe, DeepInfra, Upstage, Volcengine Ark, IONOS AI Model Hub, Novita AI, OVHcloud AI Endpoints, StepFun, Tencent TokenHub, Venice, Baidu Qianfan, Voyage AI, Jina AI, fal, Replicate, Deepgram, Cartesia and AssemblyAI are now built in, 50 in all. Add a key, and their chat models answer from every app format, and the others through the API they serve. Your apps don't change.

Bedrock keys can be a Bedrock API key, an AWS access key or the gateway's own AWS role, and reach Claude, Amazon Nova and Meta Llama. Azure keys can sign in with a Microsoft Entra ID service principal. fal and Replicate make images and videos; Deepgram and Cartesia speak and transcribe, and AssemblyAI transcribes. The [providers page](https://kaeso.app/providers) lists all of them.

![The Add provider key dialog listing built-in providers, from Cartesia, Cerebras and Cloudflare AI Gateway to Mistral](https://kaeso.app/articles/kaeso-0-7/still-providers.png "The new built-in providers in the Add provider key dialog.")

## Requests that keep going

A provider's rate limit, a dropped connection or a model that shuts down next month shouldn't become your app's outage. 0.7 handles each one in the gateway:

- **Key pools.** Spread a project over several keys of one provider, by weight. A key that is refused or rate limited gives way to the next.
- **Retries.** A step tries its model again after a dropped connection, a 5xx or an overloaded provider before it fails or falls back, and a stream that fails before any output falls back to the next step.
- **Model lifecycle.** Projects see when their models shut down and who still calls them, and move to the replacement in one click or on their own. **Model lines** such as `claude-opus-latest` follow a provider's newest stable model, so an app can stay current without a deploy.
- **Headers for apps.** Apps shorten how long Kaeso waits with `kaeso-timeout`, keep a request's content out of the log with `kaeso-log-content: off` and tag requests with `kaeso-tags`, and, where the key may see them, read what is left of their limits and budgets in `kaeso-limits` and what an unstreamed reply cost in `kaeso-cost`.

![Assigning the key OpenAI · Overflow to the Checkout assistant project with a weight of 30, beside its other keys](https://kaeso.app/articles/kaeso-0-7/still-key-pools.png "Key pools: a project draws its keys by weight, and a refused or rate-limited key gives way.")

![gpt-5.5 marked Deprecated, shutting down in 23 days: its dates, its replacement gpt-6-sol, the price change and a Move to replacement button](https://kaeso.app/articles/kaeso-0-7/still-model-lifecycle.png "Model lifecycle: a retiring model shows who still calls it and what replaces it.")

## Ready for the whole company

Once more than one team uses AI, someone has to answer: what data leaves the building, who has access, and who hears about it when a budget runs out. 0.7 gives the answers a place in Kaeso:

- **Guardrails.** Built-in rules find secrets and personal data in requests, an API key, an email address, an order number, and mask, block or count them, and can keep them out of the request log. Masked values go to the model as placeholders and come back filled in, so the app sees the real reply. Chat requests and their replies can also be checked by services of your own.
- **SCIM 2.0 and SSO groups.** Your identity provider adds and removes members, and single sign-on sets their roles and projects from its groups, Microsoft Entra ID included. Someone who leaves the company leaves Kaeso too.
- **Webhooks.** Budget alerts, limits reached, expiring keys and more go, signed as Standard Webhooks or as a Slack line, to the systems your team already watches.
- **Your currency.** Each organization picks the currency Kaeso shows all its money in, spend, prices and budgets, at the ECB's daily reference rates. Kaeso still stores and costs everything in US dollars underneath.
- **Shared links** give read-only access to usage, a member's stats, a project's budgets or its summary, for the people who need the numbers but not an account.

![Trying guardrail rules on a sample text: an order number, an email address and an API key are rewritten to placeholders](https://kaeso.app/articles/kaeso-0-7/still-guardrails.png "Guardrails mask secrets and personal data before the model and restore them in the reply.")

![The organization's provisioning settings: the SCIM base URL, its token and the last request, with group rules below](https://kaeso.app/articles/kaeso-0-7/still-scim.png "SCIM 2.0 and SSO groups: the identity provider adds members and sets their roles and projects.")

![A webhook named On-call with its URL, format and events, and its last deliveries, each delivered with 204](https://kaeso.app/articles/kaeso-0-7/still-webhooks.png "Webhooks: budget alerts, limits reached, expiring keys and more, signed or as a Slack line.")

## Find any request

![The request log of the demo's Checkout assistant project, filtered to failed requests: above the list, the most common errors with how many requests each one failed, such as a client that closed the connection and an overloaded provider](https://kaeso.app/articles/kaeso-0-7/request-log-light.png "The request log, filtered to failed requests, with the most common errors first.")

When something goes wrong, the request log now leads you to it. Filter by alias, fallback, endpoint, cost, the name the app sent, outcome, cache, duration, tag or client app, and find failures by their message, with the most common errors on top. Open a logged request in the Playground or copy it as a curl command; every Playground reply links to its entry, and the command palette opens a pasted request id. Agent conversations take far less space: the log stores each long message a session repeats only once.

## A console for every screen

![The demo organization's Overview: Running now, Kaeso 0.7.0 with its release artwork, a note that two projects use retiring models, and the activity of the last 14 days](https://kaeso.app/articles/kaeso-0-7/overview-light.png "The organization's Overview on 0.7.0, with the projects whose models are retiring.")

The console takes kaeso.app's design, and every page, from a project's analytics to the instance settings, fits a phone, a tablet and a wide screen in English, German and Chinese. For Claude on the web, desktop and mobile, Account › Agents has an **Add to Claude** button that opens Claude's connector form with your install's MCP address filled in, and the Kaeso plugin for Claude Code asks for that address when you install it.

## Runs where you run things

An install now takes less memory, CPU and disk: the bundled ClickHouse writes only the diagnostics an operator reads, and the gateway allocates with mimalloc. Requests after a pause no longer wait for the database, and large Responses requests from coding agents decode in about three quarters of the time.

Kaeso installs on **Kubernetes** with a Helm chart that each release publishes next to the images, exports **OpenTelemetry** traces of model requests and tool calls, and reports more in `/metrics`, such as requests in flight and how old the model data is.

![Installing Kaeso with helm install from the chart on ghcr.io at version 0.7.0, then kubectl exec running kaeso setup-link](https://kaeso.app/articles/kaeso-0-7/still-helm.png "Kaeso on Kubernetes with the Helm chart.")

## Try it

See it first: the [live demo](https://demo.kaeso.app) runs 0.7.0 with sample data, decision models, guardrails, key pools and all.

Then run your own. On a server with Docker, one command installs Kaeso and prints the link to set it up:

```sh
curl -fsSL https://kaeso.app/install.sh | sh
```

On Kubernetes, the Helm chart does the same:

```sh
helm install kaeso oci://ghcr.io/logicplanes/charts/kaeso --version 0.7.0 \
  --namespace kaeso --values values.yaml --wait
kubectl --namespace kaeso exec deployment/kaeso-gateway -- kaeso setup-link
```

[Where to run Kaeso](https://kaeso.app/articles/where-to-run-kaeso) compares the places it runs, and the [installation guide](https://docs.kaeso.app/self-hosting/installation) has every option. Add a provider key, point an app's base URL at your Kaeso, and the requests show up in the log. [Tell us](https://kaeso.app/contact) what you build with it.

## Updating from 0.6

Most installs update with one click from Instance › Updates: the updater installs 0.7.0 from 0.6.0 by itself, and the database migrations run on their own.

One thing to check first. 0.7.0 refuses to start with three settings that 0.6.0 accepted. Look for them in `.env`, `compose.override.yaml`, the file `KAESO_CONFIG` names or your platform's variables, and fix each one before you update:

- **`kpmr.interval` (`KAESO_KPMR_INTERVAL`) under 5 minutes:** set it to `5m` or longer, or remove it for `auto`.
- **`mcp_servers.sync_interval` (`KAESO_MCP_SERVERS_SYNC_INTERVAL`) under a minute:** set it to `1m` or longer, or remove it.
- **`smtp.user` (`KAESO_SMTP_USER`) without `smtp.password`:** add `KAESO_SMTP_PASSWORD`, or remove the user if your mail server takes mail without authentication.

0.6.0 ran those jobs every 5 minutes and every minute anyway, and removing the SMTP user keeps sending mail as 0.6.0 did. If automatic updates are on, fix them now, before the update arrives.

How an update that still finds one of them ends:

- **From the console or the update window:** it stops before it switches anything, and 0.6.0 keeps running. The progress window shows **Not installed** with the setting and its fix. Correct it, apply it with `docker compose up -d --wait` and update again; an automatic update tries again in its next window.
- **With the installer:** it checks the settings before it stops the old gateway, prints the error and leaves 0.6.0 running.
- **By hand or on a platform:** the new gateway stops at startup. Correct the setting and run `docker compose up -d --wait`, or deploy again.

[Upgrading to 0.7.0](https://docs.kaeso.app/self-hosting/upgrades#upgrading-to-070) in the docs has the details, and the [full changelog](https://kaeso.app/changelog/0.7.0) lists every change.

By Kaeso Team

## More articles

- [Bring your own key to Linear's coding agent, through Kaeso](https://kaeso.app/articles/linear-byok-through-kaeso.md): Linear's cloud coding agent now takes your own key, and any gateway that speaks Anthropic Messages or OpenAI Responses. Point it at Kaeso to put its sessions under your own keys, limits, routes and request logs. Step by step.
- [Kaeso 0.6: one gateway for chat and media, with alias routes and an MCP portal](https://kaeso.app/articles/kaeso-0-6.md): Kaeso 0.6.0 is out. Apps make images, speech and video through the same gateway as chat, Gemini apps connect under /v1beta, aliases become routes with fallbacks and splits, and every project gets an MCP portal. Here is what changed and how to update.

[See all articles](https://kaeso.app/articles.md)

## Own the gateway. Own the record

```bash
curl -fsSL https://kaeso.app/install.sh | sh
```

[Install Kaeso](https://docs.kaeso.app/self-hosting/installation) · [Open the live demo](https://demo.kaeso.app)
