Developers keep their workflow. AIMS meets them inside the editor, the CLI and Copilot, with entitled models, no key management, and attribution stamped on every request.
One governed gateway, many familiar clients. Each request carries entitlement, project context and feature attribution.
Entitled models appear in the native chat picker under “Synapx AIMS”. Every request is stamped with its project and feature, quota is tracked live, and access degrades gracefully offline.
AIMS mirrors your entitled models into Copilot’s custom-endpoint list and rotates the short-lived key for you, so no long-lived static key ever sits on disk.
One command launches GitHub Copilot CLI, OpenAI Codex CLI or Claude Code wired to the gateway. The key is passed only through the child process’s environment, never written to disk.
AIMS keeps provider credentials behind the gateway while developers work where they are fastest.
Connect once, then let AIMS keep the governance record current while developers get on with the work.
Bring your Azure AI Foundry, Azure OpenAI or other provider account to the encrypted gateway.
Turn GitHub Projects items into AIMS features and cost centres for delivery.
Use VS Code, Copilot BYOK or the CLI with entitled models and no extra workflow.
Every request is tied to its project and story, with budgets and evidence kept current.
Choose capability deliberately, keep provider liability in your tenancy, and make every model decision a costed decision.
Connect a provider once and scan-and-import its models. Azure AI Foundry / Azure OpenAI is supported first. Provider keys go straight to the encrypted gateway.
Around 400 models with pricing per million tokens, context windows, capability badges and benchmark scores.
| Model | Capability | Input / 1M | Context |
|---|---|---|---|
| GPT-4.1 | Code | $2.00 | 1M |
| Claude Sonnet 4.5 | Reasoning | $3.00 | 200K |
| Gemini 2.5 Pro | Vision | $1.25 | 1M |
| o4-mini | Fast | $0.55 | 200K |
Import a GitHub Projects board and its items become AIMS features. AI spend then attributes per story, with manual booking and spend aliases where you need them.
Make the place developers already work the safest place to spend.
Govern access, attribute spend, and keep the workflow familiar.
