connic/claude-opus-5Anthropic · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €5.20
- Output / 1M
- €26.00
Use Connic models and your own providers
on one platform.
Choose the right AI model for each agent: directly through Connic with EU hosting, through your own API key, or at a self-hosted endpoint. You can configure automatic retries and fallback models for all three options.
Read the model configuration docsModel selection
Connic-managedEU-hosted
connic/glm-5.2
Z.ai · 256k context
Provider key
anthropic/claude-sonnet-4-5
Uses the provider account
Three ways to run a model. One YAML field.
Each agent selects one option, and any option can serve as that agent's fallback. Moving to a different provider is a one-line change, not a rewrite.
Connic-managed
No account to create
model: connic/gpt-5.6-terra- Enabled on every Project by default, with no key to configure
- EU-only inference at published EUR rates
- Paid from Project credit, with a one-time 20 EUR included in Basic
Provider key
Provider account
model: anthropic/claude-sonnet-5- OpenAI, Azure OpenAI, Anthropic, Gemini, OpenRouter, Bedrock, Vertex AI
- Provider contract, rates, and rate limits
- Credentials encrypted per Project and injected at runtime
Self-hosted endpoint
Any OpenAI-compatible server
model: vllm/mistral-7b- A prefix and base URL make the endpoint available like any provider
- vLLM, Ollama, an inference proxy, or a self-hosted model
- Bridge access to an endpoint inside a private network, with no inbound ports
A single Project can mix all three. Available configuration includes the provider prefixes and required credentials.
Compare AI models and pricing
Explore a selection of AI models available through Connic. Prices are listed in euros per million tokens, excluding tax. Pay for usage with your project credits.
| Model | Context | Inputs & strengths | Input / 1M | Output / 1M |
|---|---|---|---|---|
connic/claude-opus-5Anthropic · Provider terms | 1M | TextVisionReasoning | €5.20 | €26.00 |
connic/claude-sonnet-5Anthropic · Provider terms | 1M | TextVisionReasoning | €2.10 | €10.40 |
connic/gpt-5.6-solOpenAI · Provider terms | 1M | TextVisionReasoning | €5.20 | €31.20 |
connic/gpt-5.6-terraOpenAI · Provider terms | 1M | TextVisionReasoning | €2.10 | €12.50 |
connic/gpt-5.6-lunaOpenAI · Provider terms | 1M | TextVisionReasoning | €0.25 | €1.30 |
connic/gemini-3.5-flashGoogle · Provider terms | 1M | TextVisionReasoning | €1.60 | €9.40 |
connic/gemini-3.1-flash-liteGoogle · Provider terms | 1M | TextVisionReasoning | €0.30 | €1.60 |
connic/glm-5.2Z.ai · MIT | 256k | TextReasoning | €1.90 | €5.80 |
connic/qwen3.5-397b-a17bQwen · Apache-2.0 | 250k | TextVisionReasoning | €0.65 | €3.80 |
connic/qwen3.6-35b-a3bQwen · Apache-2.0 | 256k | TextVisionReasoning | €0.30 | €1.60 |
connic/mistral-large-2512Mistral · Provider terms | 256k | TextVision | €0.55 | €1.60 |
connic/mistral-small-2603Mistral · Provider terms | 256k | TextVisionReasoning | €0.25 | €0.65 |
connic/llama-3.3-70b-instructMeta · Llama 3.3 Community | 100k | Text | €0.95 | €0.95 |
connic/minimax-m2.7MiniMax · Provider terms | 197k | TextReasoning | €0.65 | €2.60 |
connic/claude-sonnet-5Anthropic · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €2.10
- Output / 1M
- €10.40
connic/gpt-5.6-solOpenAI · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €5.20
- Output / 1M
- €31.20
connic/gpt-5.6-terraOpenAI · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €2.10
- Output / 1M
- €12.50
connic/gpt-5.6-lunaOpenAI · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €0.25
- Output / 1M
- €1.30
connic/gemini-3.5-flashGoogle · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €1.60
- Output / 1M
- €9.40
connic/gemini-3.1-flash-liteGoogle · Provider terms
TextVisionReasoning
- Context
- 1M
- Input / 1M
- €0.30
- Output / 1M
- €1.60
connic/glm-5.2Z.ai · MIT
TextReasoning
- Context
- 256k
- Input / 1M
- €1.90
- Output / 1M
- €5.80
connic/qwen3.5-397b-a17bQwen · Apache-2.0
TextVisionReasoning
- Context
- 250k
- Input / 1M
- €0.65
- Output / 1M
- €3.80
connic/qwen3.6-35b-a3bQwen · Apache-2.0
TextVisionReasoning
- Context
- 256k
- Input / 1M
- €0.30
- Output / 1M
- €1.60
connic/mistral-large-2512Mistral · Provider terms
TextVision
- Context
- 256k
- Input / 1M
- €0.55
- Output / 1M
- €1.60
connic/mistral-small-2603Mistral · Provider terms
TextVisionReasoning
- Context
- 256k
- Input / 1M
- €0.25
- Output / 1M
- €0.65
connic/llama-3.3-70b-instructMeta · Llama 3.3 Community
Text
- Context
- 100k
- Input / 1M
- €0.95
- Output / 1M
- €0.95
connic/minimax-m2.7MiniMax · Provider terms
TextReasoning
- Context
- 197k
- Input / 1M
- €0.65
- Output / 1M
- €2.60
Catalog updated September 9, 2026See the full model catalog
Use Connic models with EU processing
Process requests in the EU with Connic models. No additional configuration is needed.
EU-only by contract and routing
Every connic/* request is sent only to EU inference capacity. A model is removed or fails closed if that boundary cannot be maintained.
No prompt training
Connic-managed inference is not used to train models. Connic records model and token counts for billing, not prompt or response content; narrow security and error-retention exceptions are described in our Privacy Policy.
A clear Project boundary
connic/* covers the model call. A Project is fully EU-resident when its deployment region and every configured provider, tool, guardrail, judge, and data destination are EU-resident too.
A direct model API may be preferable to an agent runtime. Compare EU-hosted model providers and deployment options.
Configure models, prompts, and tools together
Define which AI model your agent uses in the agent file. Version it in Git and review model changes through the same process as other code changes.
agents/refund-agent.yaml
version: "1.0"
name: refund-agent
description: Reviews refund requests and drafts a decision
system_prompt: |
Review the refund request and draft a decision.
model: connic/qwen3.6-35b-a3b
fallback_model: connic/claude-sonnet-5 # or anthropic/claude-sonnet-4-5 with Anthropic BYOK configured
temperature: 0.3
reasoning_effort: high
retry_options:
attempts: 5
max_delay: 60What each field does
model- A provider prefix plus a model ID. Required for LLM agents, and managed, BYOK, and custom endpoints all use this one field.
fallback_model- A second model, usually at a different provider, that takes over when the primary provider fails.
temperature- 0.0 to 2.0, within what the model accepts. Lower is more deterministic.
reasoning_effort- auto, off, minimal, low, medium, high, or xhigh. The level is translated to each provider's own parameter, so the file survives a model swap.
retry_options- Up to 10 attempts for the request being retried. With a fallback, the primary is tried once and this budget applies to the fallback.
One line changes a whole fleet
A _defaults.yaml file sets the model for every agent in that directory and below, and an individual agent still wins on conflict. See cascading defaults
Tool calling and structured output
Managed models accept tool definitions and response-format constraints, so agent tools and output_schema behave the same on connic/* as they do on a BYOK model.
Retry failed model requests
Connic handles errors such as rate limits, timeouts, and invalid API keys. Configure retries and an optional fallback model for each agent.
LLM call, one run
- connic/qwen3.6-35b-a3battempt 1 of 4429primary request failed
- anthropic/claude-sonnet-4-5fallback, attempt 1 of 4503request failed, retrying fallback
- anthropic/claude-sonnet-4-5fallback, attempt 2 of 42001.9s, run continues
Run finished successfully and is tagged
fallback_model_usedRetries at the failure point
Connic repeats the single failing model call instead of replaying the run. Tools that already executed keep their results, and the conversation is not rebuilt from scratch.
Fallback after the primary fails
If fallback_model is configured, the primary model is tried once. If that request fails, the fallback receives the configured attempt budget. A managed primary model can use a BYOK fallback, and vice versa.
Visible after the fact
A run that switched is flagged in its trace. The expression context.fallback_model_used filters the run list to show provider failovers over a selected period.
Context limits recover
With context_compression enabled, a context-window error triggers one pass that summarizes older turns and oversized tool results, then retries. The run keeps going instead of dying on a provider error.
Attempts, backoff, and delays are configurable per agent. See execution limits and retries
Find the right AI model for the task
Test a new AI model against the current one in Connic. Compare cost and quality on real production requests to decide whether switching is worthwhile.
agents/refund-agent-test-cheaper.yaml
# Copy of refund-agent.yaml, one line changed
version: "1.0"
name: refund-agent-test-cheaper
description: Reviews refund requests and drafts a decision
system_prompt: |
Review the refund request and draft a decision.
model: connic/qwen3.6-35b-a3brefund-agent, cheaper test
MetricControlVariantDelta
- Token cost per run€0.021€0.006-71%
- Success rate97.4%97.1%-0.3pp
- Judge score17/2017/20even
- Duration P952.4s3.1s+0.7s
Confidence mode plans the sample size and issues a recommendation at each analysis checkpoint. Guardrails pause a test whose failure rate or judge quality slips.
Prove it before live traffic
A test suite can target the variant agent with the same cases and assertions. Exit codes plug into any pipeline, and the deploy gate can run the suite before the variant goes live. See testing
Cost broken out per model
Token Usage reports spend by agent and by model, with EUR and USD kept in separate columns so a managed model and a BYOK model are never blended into one number. See usage docs
Limits that stop spend
Alerts or hard limits on token cost can be scoped globally, per environment, or per agent, daily or monthly. Anomaly detection flags a run that costs far more than that agent's 30-day average. See observability
See what Connic handles beyond model access
Compare the capabilities included in Connic for running your AI agents with what you need to build or add with other approaches.
| Feature | Connic | Provider SDK | Model router | Self-hosted |
|---|---|---|---|---|
| Ship without creating a provider account | Included | Not included | Not included | Not included |
| EU-only inference option | Included | Partial | Partial | Included |
| Per-model prices published in EUR | Included | Not included | Not included | Not included |
| Model-call retries and fallback models | Included | Not included | Included | Not included |
| One config for managed, BYOK, and self-hosted models | Included | Not included | Partial | Not included |
| Per-run trace with tool calls and token cost | Included | Not included | Partial | Not included |
| Spend alerts and hard limits | Included | Partial | Partial | Not included |
| A/B a model swap on live traffic | Included | Not included | Not included | Not included |
| Test suites and judges gating a model change | Included | Not included | Not included | Not included |
| No GPU capacity to operate | Included | Included | Included | Not included |
Frequently Asked Questions
No. Connic-managed models are enabled on every Project by default and need no provider key. The free Basic plan starts with a one-time 20 EUR of Project credit, the same balance that pays for runs, compute, and storage. Provider credentials are only needed for BYOK or custom providers.
The catalog includes both open-weight and hosted proprietary models. Each entry lists its creator and applicable model terms. A self-hosted open model can also connect to Connic through a custom OpenAI-compatible endpoint.
Yes. Each agent YAML names its own model, so a cheap model can handle classification while a stronger model handles the reasoning step. A _defaults.yaml file sets a shared model for every agent in a directory and below, and an individual agent still overrides it.
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.
Yes. Managed models accept tool definitions and response-format constraints, so agent tools, MCP servers, and output_schema behave the same way they do on a BYOK model.
A test suite can run the same cases and assertions against the variant agent in CI, or the candidate can deploy as an A/B variant with a share of live traffic. The A/B 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. Judges score deployed runs, so they apply to the A/B comparison rather than to the test suite.
No. BYOK and Connic-managed models are equal options. Either can be the primary or fallback model for an agent.
No. Managed models are part of the deployed Connic runtime, not a public pass-through model API.
Standard Projects can add prepaid credit manually or enable auto-refill with a threshold, amount, and monthly cap. Calls pause when a prepaid Project has no credit. Enterprise Projects have custom pricing and commercial terms.
Purchased credits stay available while the Project remains active. If the Project or contract closes, unused purchased credit is refunded after any outstanding amount is settled. Monthly credit expires at cycle end; promotional credit follows its disclosed expiry.
It guarantees the managed model call stays in the EU. The whole Project is EU-only when every other configured component, such as BYOK models, tools, guardrails, and external data destinations, also stays in the EU.