Skip to main content
Connic
Back to BlogAnnouncement

Introducing Connic Models: Every Model EU-Hosted, Zero Config

Connic Models put 30 EU-hosted models from nine creators behind connic/* IDs. Reference one in agent YAML without a provider account, key, or region flag.

July 30, 202610 min readAuthor: Connic Engineering

Today we are shipping Connic Models: 30 models from nine creators, unified behind a single set of IDs that every Project can use right now. One line of agent YAML names the model without requiring a provider account, API key, or region flag, and every call stays on EU inference capacity.

We have wanted to make this release since Connic started because it removes the one step in getting an agent live that had nothing to do with building an agent. Developers wrote the YAML and tools, then stopped to open an account with a model provider, add a card, generate a key, paste it into every environment, and determine whether the provided endpoint was in the EU. That detour is now optional.

What are Connic Models?

Connic Models are managed models that Connic makes available to every deployed Project under the connic/ prefix, running on EU inference capacity. Selection happens by writing its exact catalog ID in the model field of an agent, the same field that has always taken a provider prefix and a model ID. Usage is charged against Project credit, the balance that already pays for runs, compute, storage, and retrieval.

The word doing the work there is managed. A connic/* ID provides one published rate, one line of config, one bill, and one documented set of capabilities. No separate provider account or provider credentials are required.

They are a third option, not a replacement. Bring-your-own-key and custom OpenAI-compatible endpoint work exactly as before, and any of the three can serve as an agent's primary or fallback model:

Connic-managedBring-your-own-keyCustom endpoint
Configuration valueconnic/glm-5.2anthropic/claude-sonnet-4-6vllm/mistral-7b
SetupNone, on by defaultAdd provider credentials to the ProjectPick a prefix, point it at a base URL
Who bills the tokensConnic, from Project creditThe provider, on the associated accountNobody; the organization runs the server
Where inference runsEU onlyWherever the provider runs itWherever the organization hosts it
Rate limitsManaged by ConnicThe provider contractThe organization's hardware
Works as fallback_modelYesYesYes

One Project can mix all three, and mixing them is the point. A managed primary with a BYOK fallback is a normal configuration, and so is the reverse:

agents/refund-agent.yaml
version: "1.0"
name: refund-agent
type: llm
description: Reviews refund requests and drafts a decision
system_prompt: |
  Review the refund request and draft a decision.

model: connic/glm-5.2
fallback_model: connic/gpt-5.6-terra  # or anthropic/claude-sonnet-4-6 with Anthropic BYOK configured
temperature: 0.3
reasoning_effort: high

Which models are in the catalog?

As of 30 July 2026 the catalog carries 30 models from nine creators: Anthropic, Google, Meta, MiniMax, Mistral, Moonshot AI, OpenAI, Qwen, and Z.ai. Open-weight models sit beside hosted proprietary ones, and every entry names its license. This shows whether a model can also run on infrastructure controlled by the organization using it.

The spread is deliberate. Twenty-two entries accept image input, three accept audio, and twenty-two do reasoning, seventeen of those with a configurable effort level. That means a small vision model can triage scanned invoices while a frontier reasoner handles the one decision that matters, both in the same Project, both named in YAML. Six entries, to show the range:

Model IDCreator and licenseContextInputsReasoning effort
connic/mistral-small-3.2-24b-instruct-2506Mistral, Apache-2.0128ktext, imagenot supported
connic/qwen3.6-35b-a3bQwen, Apache-2.0256ktext, imagenone, low, medium, high
connic/glm-5.2Z.ai, MIT256ktextnone, high, max
connic/gemini-3.5-flashGoogle, provider terms1Mtext, image, audiolow, medium, high
connic/claude-sonnet-5Anthropic, provider terms1Mtext, imagelow, medium, high
connic/gpt-5.6-solOpenAI, provider terms1Mtext, imagelow, medium, high

The full model catalog lists every ID, its capabilities and limits, its per-token price, and the date the catalog was last updated. It is searchable, filterable by creator, and sortable by price or context.

Deploy agents without a provider account

Name a connic/* model in agent YAML and deploy without a key, provider account, or region flag.

Start building

EU inference as a catalog boundary

We care most about this constraint of the catalog. The model ID has no region flag or worldwide fallback. Every connic/* request goes only to EU inference capacity. If that boundary cannot be held for a model, the model is removed from the catalog or the call fails closed.

EU-only by contract and routing
The ID encodes this boundary contractually and in routing, even under load.
No prompt training
Managed inference is not used to train models. We record model and token counts for billing, not prompt or response content, with narrow security and error-retention exceptions set out in the Privacy Policy.
Labels, not fine print
Where a model's upstream provider is not EU-native, or retains request data for 30 days under its own policy, the catalog carries that label next to the model name.

We could have left those labels out. We included them because inference location and provider origin are two different questions, and a catalog that answers only the first one is a catalog that is unsuitable for a procurement review.

The split is where it gets interesting. Twenty-one of the 30 entries carry no non-EU-native-provider label at all, and ten of those ship under an open or source-available license: Apache-2.0, MIT, Modified MIT, Llama 3.3 Community, and the Kimi K3 License. That is enough to build a whole agent fleet on EU-native capacity and open weights, and still reach for a labeled frontier model on the one task that needs it. Our guide to EU hosting without US hyperscalers covers the requirements when a US cloud must be excluded.

One limit, stated plainly: the connic/* guarantee covers the model call. A Project is fully EU-resident when its deployment region and every configured component, including BYOK providers, tools, guardrails, judges, and external data destinations, are EU-resident as well. Our data residency guide covers the entire agent platform. The EU-hosted model comparison explains provider and deployment options.

An ID that means what it says

A managed model ID that silently starts pointing somewhere new would be worse than shipping no managed models at all. Tests, judge scores, and cost baselines would all stop meaning anything, with no clear indication of when the change happened. So we made the guarantee explicit: every connic/* ID refers to the model named beside it in the catalog and keeps referring to it. When a model is retired, we announce the change before the ID goes away. A deploy never swaps out the tested model.

Rate limits, timeouts, and provider outages are ordinary events once agents run around the clock, so we handle failures at the model call instead of replaying the full run:

Then fallback_model
The agent's fallback_model takes over, managed or BYOK. Runs that switched are tagged, so filtering the run list on context.fallback_model_used shows exactly how often a provider failed during the previous week.
Retries at the failure point
We repeat the single failing model call rather than replaying the run. Tools that already executed keep their results and the conversation is not rebuilt.
Cut-short calls cost nothing
A managed call ended early by a run timeout or a stopped run settles at zero tokens, and the credit reserved for it goes straight back to the Project balance.

What comes with a managed ID

Fast IDs, when latency is the constraint

Seven models ship a companion ID with a -fast suffix: the same model through a latency-optimized execution path, at the same price. Two more, both Kimi models, are offered only on that path, so -fast is simply part of their ID. The suffix is the promise: if an ID does not carry it, the model is not served this way.

connic/glm-5.2andconnic/glm-5.2-fastone model, two execution paths

Two caveats belong here so they do not first surface in production.

First, the trade-off that makes it fast. A Fast ID can be served by a quantized deployment of the model, which is part of how the latency comes down and why its outputs may differ from the standard ID on the same prompt. Quantization is a quality trade-off, not a free win, so treat a switch as a model change: re-run the agent's tests, and keep accuracy-critical steps on the standard ID until evidence shows the Fast one holds up. The A/B comparison is the cheapest way to get that evidence, since it scores both sides on live traffic.

Second, a Fast ID can be narrower than its standard twin in three ways: fewer reasoning levels, a smaller context window, or fewer input types. connic/glm-5.2-fast accepts only high where the standard ID also takes none and max, and connic/qwen3.5-397b-a17b-fast takes text only where the standard ID also reads images. Three of the seven companions match their standard twin exactly, and the info icon beside every Fast ID states any differences.

Reasoning effort that survives a model swap

Every provider names its reasoning control something different and scales it differently. In Connic it is one field, reasoning_effort, and Connic translates the configured level into whatever the model underneath expects. Every managed model's accepted values sit in the catalog, and auto hands the decision back to the model.

The payoff lands at swap time. Changing the model line does not mean rewriting a provider-specific parameter beside it, and captured reasoning still appears in the run trace when the model returns it, whichever model that is. The runs and traces documentation explains the details.

How is managed usage billed?

Managed tokens draw on Project credit, the same balance that pays for runs, compute, storage, and retrieval. One balance, one currency, one number to quote when someone asks what an agent costs to run. Input, output, thinking, and cached input are priced independently per model, and the catalog carries the current rates beside each ID.

Turn on Auto-refill before production
Prepaid Projects pause new usage when available credit runs out, which is the right behavior for a runaway loop and the wrong surprise for a live agent. Set a threshold, an amount, and a monthly cap under Project → Billing before sending production traffic to a managed model. Enterprise Projects have custom commercial terms. The pricing page lists plans, credit, and platform rates.

Switch models on evidence, not on a benchmark chart

A cheaper model in the catalog is a hypothesis, not a saving. The three tools that turn one into the other were already in Connic, and managed models plug into all of them:

A/B on live traffic
Deploy the candidate as a variant and split real traffic. The comparison reports success rate, duration, token cost, and judge scores for both sides, and pauses a test that breaches a failure-rate or quality guardrail.
Test suites in CI
Point the same cases and assertions at the variant agent. Exit codes plug into any pipeline, and the deploy gate can run the suite before the variant goes live. A model swap that regresses never reaches production.
Cost per model
Token Usage reports spend by agent and by model, keeping EUR and USD in separate columns so a managed model and a BYOK model are never blended into one number.

Spend alerts and hard limits apply either way, scoped globally, per environment, or per agent, daily or monthly. Switch on anomaly detection and a run that costs far more than that agent's 30-day average raises an alert on its own. Our A/B testing guide describes the full workflow. The usage and budget documentation covers cost controls.

BYOK is not going anywhere

We built managed models to remove a barrier, not to divert existing traffic. Model spend already covered by a negotiated provider contract can stay there. Teams running a fine-tune on their own hardware can point a custom prefix at it and reach it over a Bridge with no inbound ports. Managed and BYOK are equal options in the same YAML field, and every observability, testing, and budgeting feature treats them the same way.

One more limit worth naming: connic/* models are part of the deployed Connic runtime, not a public pass-through model API. They exist to run agents on Connic.

Getting started with Connic Models

  • 1.Browse the model catalog and pick an exact ID, filtering by creator and sorting by price
  • 2.Set it as model in an agent file, or in a _defaults.yaml to change every agent in that directory and below
  • 3.Deploy without a key, provider account, or region flag
  • 4.Before production traffic, enable Auto-refill and set a spend limit on the agent

For teams new to Connic, the quickstart covers the first agent deployment without requiring another provider's API key. The models and providers documentation explains each configuration field, and the model selection overview describes the available options.

Frequently Asked Questions

Connic Models are managed models available to every deployed Connic Project under the connic/ prefix, running on EU inference capacity. Each ID has one published rate and works in the same agent model field as BYOK models, with no provider account or API key required. As of 30 July 2026 the catalog holds 30 models from nine creators, and usage is charged against Project credit.

No. Connic-managed models are enabled on every Project by default and need no provider key. Managed usage draws on Project credit, the same balance that pays for runs, compute, storage, and retrieval. Provider credentials are only needed for BYOK or for a custom OpenAI-compatible endpoint.

Managed model usage is charged against Project credit at the rate published next to each ID in the Connic model catalog. Input, output, thinking, and cached input are priced independently per model. Standard Projects are prepaid and can add credit manually or through capped auto-refill; Enterprise Projects have custom commercial terms. BYOK usage stays on the associated provider account.

Yes. Each connic/* ID refers to the model named beside it in the catalog and keeps referring to it, so a deploy never swaps out the tested model. If a model is retired, Connic announces the change before removing the ID.

A -fast ID runs the same model through a latency-optimized execution path at the same price. It may be served by a quantized deployment of the model, which is part of how latency comes down and why its outputs may differ from the standard ID on the same prompt. Treat a switch as a model change: re-run the tests and keep accuracy-critical steps on the standard ID until an A/B comparison shows the Fast ID holds up. A Fast ID can also be narrower than its standard twin: fewer reasoning levels, a smaller context window, or fewer input types. The catalog states the difference per model.

The failed model call follows the agent's retry settings. If fallback_model is configured, the fallback takes over after the first failed primary request and can be a managed or BYOK model.

It guarantees the managed model call runs on EU inference capacity. A Project is fully EU-resident when its deployment region and every configured component, including BYOK providers, tools, guardrails, judges, and external data destinations, are EU-resident too. The catalog also labels entries whose provider is not EU-native or retains request data for 30 days.

No. BYOK and Connic-managed models are equal options in the same YAML field, and either can be an agent's primary or fallback model. BYOK keeps model spend and rate limits on the associated provider contract. A custom prefix can also point at any OpenAI-compatible endpoint, including one hosted inside an organization's own network and reached over a Bridge.

No. Managed models are part of the deployed Connic runtime, not a public pass-through model API. They are available to agents running in a deployed Connic Project.

More from the Blog

Industry Insights

AI Agent Platform SLA Checklist: What Enterprise Buyers Should Verify

Evaluate an AI agent platform SLA across uptime scope, dependencies, incident response, recovery, security evidence, remedies, and exit terms.

August 29, 202612 min read
Industry Insights

EU-Hosted AI Models in 2026: Providers, Dependence & Options

EU-hosted AI models compared by location, retention, operator, portability, legal exposure, and deployment model, using a 2026 Commission-requested study.

August 18, 202611 min read
Announcement

Introducing Connic MCP: Operate Connic from a Coding Agent

An MCP coding agent such as Codex, Claude Code, or Cursor can connect to a Connic project for debugging runs, shipping deployments, and managing agents without leaving the editor.

August 10, 20267 min read
Product Spotlight

Staging to Production: How Connic Environments Isolate AI Agents

Connic environments map git branches to isolated deployments, each with its own secrets, connectors, budgets, and run history, so one agent spec ships safely.

August 6, 20268 min read
Announcement

Introducing the Connic Marketplace

The Connic Marketplace is the new home for agent templates, connectors, and retrieval sources. One catalog, one publisher model, one CLI install.

July 5, 20265 min read
Product Spotlight

Connic Tests: Catch Agent Regressions Before They Reach Production

A YAML-driven testing framework built for non-deterministic AI agents. Repeated-run pass thresholds, expression-based assertions, custom-code mocking, multimodal fixtures, and a deploy gate that blocks failed checks by default.

May 6, 20268 min read
Product Spotlight

Secure AI Agents: A Production Safety Checklist

Shipping AI agents without a security strategy is a liability. A practical checklist for prompt injection, PII handling, output validation, and pre-launch guardrails.

March 21, 202612 min read
Changelog

What We Shipped in January 2026

Custom observability dashboards with drag-and-drop widgets, model pricing for cost tracking, refreshed connector and runs UI, and llms.txt support.

February 10, 20265 min read
Tutorial

AI Agents: From Prototype to Production

A demo works great until 1,000 concurrent users arrive. A practical guide to the production requirements most teams find out about too late.

January 10, 202610 min read