Khanmigo By Khan Academy vs New API
Side-by-side comparison · Updated October 2026
| Description | Khanmigo is Khan Academy’s AI tutor and teaching assistant. Its tutoring approach uses questions and guided prompts to help learners reason through a problem, while teacher tools support lesson preparation, learning objectives, rubrics and exit tickets. Tutoring, writing practice, debate and coding feedback are available through the relevant learner or family plan. Free teacher access is separate from paid learner and parent access. Individual and family plans are listed at $4 per month or $44 per year, before applicable sales tax. A parent can enable Khanmigo for connected child accounts, review their interaction history and receive moderation alerts. Account, location and language eligibility apply; check the current signup requirements for your plan. Schools can request a separate Khanmigo District Tools quote. The district offering lists teacher and student access, school data, rostering, single sign-on through Clever SecureSync or ClassLink, implementation support and professional learning. A free teacher account does not automatically provide tutoring access to an entire class. For an evaluation, compare how the tutor guides a learner through a mistake, how an adult reviews the conversation, and whether the workflow fits the curriculum. Review AI suggestions before using them in teaching or assessed work. StudyMonkey offers a more direct question-and-explanation workflow, while Quizgecko focuses on practice material generated from your own sources. | New API is a self-hosted AI gateway and model-management project maintained in the QuantumNous repository. It brings provider channels, access tokens, model restrictions, usage statistics and cost accounting into one interface. Teams supply their own authorized model-provider access and operate the gateway in their chosen environment. The gateway supports several API formats, including OpenAI-compatible requests, Claude Messages and Google Gemini. Compatibility has boundaries: the README marks Gemini-to-OpenAI conversion as text-only without function calling, and OpenAI-compatible to Responses conversion as in development. Test the exact endpoints, streaming behavior and tool calls your application uses before switching traffic. Routing features include weighted channel selection, automatic retry after failures and user-level model rate limits. The dashboard supports request-based, usage-based and cache-hit cost accounting, with token grouping and model-access controls. These controls can help organize usage, but retries and a common API format do not guarantee uninterrupted service or identical behavior across providers. The current repository license is AGPLv3. Docker Compose is the recommended quick-start path in the README, which also documents Docker commands with SQLite or MySQL. Running the software still involves infrastructure, operations and upstream model charges. Review the current license, secure your deployment and validate accounting against provider bills. Compare LiteLLM if you also want a Python SDK or a documented gateway for MCP servers and agents. |
| Category | Education | Developer Tools |
| Rating | No reviews | No reviews |
| Pricing | Freemium | Open Source |
| Starting Price | Free | N/A |
| Plans |
| — |
| Use Cases |
|
|
| Tags | AI tutorKhan Academyteacher toolsguided learningparent tools | AI gatewayLLM routingmodel managementrate limitingusage accounting |
| Features | ||
| Guided tutoring tied to Khan Academy content | ||
| Writing and debate prompts | ||
| Coding feedback | ||
| Teacher lesson planning, objectives, rubrics and exit tickets | ||
| Parent-managed access to connected child accounts | ||
| Parent conversation history and moderation alerts | ||
| Separate district rostering, SSO and support | ||
| Self-hosted AI gateway and model management | ||
| Provider channels, token groups and model restrictions | ||
| OpenAI-compatible, Claude Messages and Gemini format support | ||
| Documented limits on protocol conversion | ||
| Weighted channel selection and failure retries | ||
| User-level model rate limiting | ||
| Request, usage and cache-hit cost accounting | ||
| Docker Compose deployment documentation | ||
| View Khanmigo By Khan Academy | View New API | |
Modify This Comparison
Also Compare
Explore more head-to-head comparisons with Khanmigo By Khan Academy and New API.