ARBR vs Chalked: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of ARBR and Chalked — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
ARBR
Gyde & Domkundwar Foundation
Open-source, MIT-licensed AI gateway and control plane that routes, governs and observes every LLM request behind one OpenAI-compatible endpoint.
Key features
- OpenAI-Compatible Routing: A single drop-in endpoint over every major provider, with rules, difficulty-aware selection, cost guardrails and automatic fallback choosing the model per request.
- In-Path Governance: Budgets, rate limits, output guardrails, prompt-injection checks and kill switches enforce policy before inference rather than auditing it afterwards.
- Structured Observability: Cost, latency, tokens and routing decisions are emitted as structured events attributed by application, team, model and user, viewable in local dashboards or exported to OpenTelemetry backends such as Datadog, Grafana and Prometheus.
- LLM-Judge Evaluation: A sample of live traffic is scored for quality so requests can be routed to the cheapest model that provably clears the bar, rather than optimising on price alone.
- Safe Model Deployment: Canary and shadow new models against real traffic with regression gates that block promotion until evaluations pass, plus instant rollback.
- Broad Provider Coverage: One layer over Anthropic, OpenAI, Google Gemini, Amazon Bedrock, Azure OpenAI, Vertex AI, Groq, DeepSeek, Moonshot, xAI and Mistral, plus LiteLLM and NVIDIA NIM, with pricing and benchmark data for over 3,000 models.
- Drop-In SDK Compatibility: Change only the base URL and existing OpenAI SDKs, agent frameworks and chat UIs keep working, gaining streaming chat completions, embeddings, a realtime voice proxy and JavaScript and Python SDKs.
- Self-Hosted and MIT Licensed: The full control plane runs inside your own infrastructure under an MIT licence, with a hosted option available for teams that do not want to operate it.
Best for
- LLM Cost Reduction: Route summarisation and extraction traffic to cheap small models while reserving frontier models for analysis, cutting spend without hand-editing every call site.
- AI Spend Attribution: Give finance and engineering a per-application, per-team and per-user breakdown of token spend so AI budgets can be owned by the groups that generate them.
- Enterprise AI Governance: Enforce departmental budgets, rate limits and kill switches in the request path so a runaway agent cannot exhaust a quarter's inference budget.
- Provider Risk Mitigation: Keep applications provider-neutral behind one endpoint with automatic fallback, so a single vendor outage or price change does not require a code change.
- Model Migration Testing: Shadow or canary a newly released model against production traffic and let regression gates decide whether it is promoted.
- Prompt-Injection Defence: Apply output guardrails and prompt-injection checks centrally for every application instead of reimplementing them per service.
C
Chalked
Mates Rates Services Pty
Mac assistant that drafts the reply you'd actually send, grounded in the open conversation, your calendar and kept commitments.
Key features
- Context-grounded replies: Reads the open conversation via Accessibility and drafts the reply you would actually send
- Tab to insert: Prepared drafts land in the existing Messages composer and are inserted with a single Tab press
- fn to redirect: Hold fn and say what you want instead to steer the draft before inserting it
- Commitment ledger: Captured commitments keep their source and status, and superseded entries are marked rather than duplicated
- Calendar grounding: Pulls availability from your calendar so proposed times are real, not invented
- Global fn dictation: Works anywhere else on the Mac even outside eligible Messages threads
- No screenshots or recording: On-screen text is read through Accessibility and stays on your Mac
- Minimum context by design: Requests only the thread and verified facts relevant to the reply
Best for
- An agency operator answers a client asking about a delivery date without re-checking the calendar and the approved budget by hand
- A consultant returns to a client thread days later and replies with the engagement's commitments intact instead of rebuilding them from memory
- A founder moves between customer, investor and team conversations in one sitting without losing which promise belongs to whom
- A team lead confirms a meeting time that is actually free because the draft was written against the live calendar
- Someone dictates a longer message into any Mac app using the global fn shortcut rather than typing it out
- A user corrects a suggested reply by voice — changing a day or a cap — before it is inserted and sent